Deformable Part Descriptors for Finegrained Recognition and Attribute Prediction


 Arline Patrick
 1 years ago
 Views:
Transcription
1 Deformable Part Descrptors for Fnegraned Recognton and Attrbute Predcton Nng Zhang Ryan Farrell,2 Forrest Iandola Trevor Darrell ICSI / UC Berkeley 2 Brgham Young Unversty 2 Abstract Recognzng objects n fnegraned domans can be extremely challengng due to the subtle dfferences between subcategores. Dscrmnatve markngs are often hghly localzed, leadng tradtonal object recognton approaches to struggle wth the large pose varaton often present n these domans. Posenormalzaton seeks to algn tranng exemplars, ether pecewse by part or globally for the whole object, effectvely factorng out dfferences n pose and n vewng angle. Pror approaches reled on computatonallyexpensve fter ensembles for part localzaton and requred extensve supervson. Ths paper proposes two posenormalzed descrptors based on computatonallyeffcent deformable part models. The frst leverages the semantcs nherent n stronglysupervsed DPM parts. The second explots weak semantc annotatons to learn crosscomponent correspondences, computng posenormalzed descrptors from the latent parts of a weaklysupervsed DPM. These representatons enable poolng across pose and vewpont, n turn factatng tasks such as fnegraned recognton and attrbute predcton. Experments conducted on the CaltechUCSD Brds 2 dataset and Berkeley Human Attrbute dataset demonstrate sgnfcant mprovements over stateofart algorthms.. Introducton Despte the many mportant applcatons and domans under nvestgaton, fnegraned recognton remans very challengng. As descrbed n [23], what often dfferentates basclevel categores s the presence or absence of parts (e.g. an elephant has 4 legs and a trunk, whereas subordnate categores are more often dscrmnated by subtle varatons n the shape, sze and/or appearance propertes of these parts (e.g. elephant speces can be dstngushed by localzed cues such as ear shape and sze. Localzng and descrbng the object s parts therefore becomes central to uncoverng ts fnegraned dentty. Several approaches have been proposed for localzng and descrbng object parts n fnegraned domans. Posenormalzaton was proposed for fnegraned recognton by Farrell et al. [23] and extended n Zhang et al. [47]. Ths paradgm seeks to dscount varatons n pose, artculaton and camera vewng angle by localzng semantc object parts and extractng appearance features wth respect to those localzed parts. In these approaches part localzaton was accomplshed usng Poselets [, ], whch requre computatonallyexpensve fter ensembles for part localzaton as well as extensve supervson. Parkh et al. [36, 37] provde an alternate way of detectng basclevel category objects such as dogs and cats by usng a Deformable Part Model [24] traned specfcally on the head. Once a head has been detected n a test mage, ths regon s used to ntalze a grabcut [38] segmentaton and obtan a mask/shouette of the entre object. Classfcaton s then performed usng a combnaton of the head shape and features extracted from wthn the head/body mask. Whe ths method s relatvely effectve for frontfacng cats and dogs, subjects n other domans (such as brds and people often exhbt greater varaton n pose and appearance and can be far more dffcult to segment from ther surroundngs (see examples n Fgure. In ths work, we ntroduce deformable part descrptors (DPD, a robust and effcent framework for posenormalzed descrpton based on DPM parts and demonstrate ts effectveness for both fnegraned recognton and attrbute predcton (see Fgure 2. We propose two deformable part descrptors: the DPDstrong leverages the semantcs nherent n stronglysupervsed DPM parts; the DPDweak explots semantc annotatons to learn crosscomponent correspondences, computng posenormalzed descrptors from weaklysupervsed DPM parts. We present stateoftheart results n evaluatng our approach on standard fnegraned and domanspecfc attrbute datasets ncludng the CaltechUCSD brds dataset [3] and Human Attrbutes dataset []. An endtoend opensource mplementaton of our method has been released wth ths paper and s avaable at
2 Partbased OnevsOne Features (POOF proposed by Berg and Belhumeur [6] whch leverages robust keypont predcton learnng a descrptor coordnate frame for each par of keyponts. Approaches such as [4, 36, 37] use regonlevel cues to estmate object segmentatons whch factate fnegraned classfcaton. Some technques use humansntheloop, askng human annotators to clck on object parts, answer questons regardng object attrbutes [3], or mark the regon that best dfferentates two confusng categores [7]. Templatebased methods have also been nvestgated by Yao et al. [45] and by Yang et al. [43]. Such approaches use a set of fxedposton templates, thereby mtgatng much of the computatonal cost of sldng wndow approaches, yet lack the spatal flexbty to deal wth substantal pose varaton Attrbute Predcton Fgure. Robustness of Deformable Part Descrptors (DPDs. Whe they work well for generally homogeneous objects such as dogs and cats, headseeded segmentatonbased descrptors often fa for other domans such as brds and humans. Examples of ths are shown n the mddle column. The ground truth segmentaton s overlad n red; the grabcut based segmentaton [38], seeded wth the head as foreground and everythng outsde the boundng box as background, s overlad n whte. The rght column shows our part localzaton results usng the stronglysupervsed DPM. Best vewed n color. 2. Background 2.. Fnegraned categorzaton Fnegraned classfcaton has recently emerged as a topc of great nterest. A growng body of lterature has proposed varous technques and has addressed recognton on a large number of fnegraned domans. These domans nclude: dog breed classfcaton [26, 29, 37], subordnate categores of flowers [2,, 33, 34] and plants [4, 39], recognton of nvertebrates [32], fnegraned classfcaton on subsets of ImageNet [6] such as fung [5], and speceslevel categorzaton of brds [23, 46]. We antcpate more work n the near future on manmade categores such as cars [4] and arplanes [3]. Followng recent work by Belhumeur et al. [5] on localzng fducal ponts n faces, Lu et al. [29] present an alternate approach to bud an exemplarbased geometrc and appearance models for detectng dog faces and localzng the facal keyponts. Another work n ths ven s that of Sfar et al. [39] who classfy leaves and flowers by descrbng appearance wth multple coordnate or vantage frames. A very recent and closely related contrbuton s the Attrbutebased representatons [22, 27, 28] present another promsng drecton, offerng the possbty of recognzng a novel category wth only a category descrpton (no magery. Relevant subsequent work on attrbutes ncludes that of Parkh and Grauman [35] explorng relatve attrbute strength and that of Berg et al. [7] and Duan et al. [9] propose automatc dscover of attrbutes to ad n fnegraned classfcaton. Perhaps the most closely related work on attrbute predcton s Bourdev et al. [], whch uses features extracted from Poselet [, 9] actvatons to predct nne bnary attrbutes on mages of humans. Another promsng alternatve to Poseletbased approaches for effectve transfer of pose annotaton from tranng mages to test mages s the Exemplar SVM proposed by Malsewcz et al. [3] Deformable Parts Model Inspred by the Pctoral Structures work of Fschler and Elschlager [25], the Deformable Parts Model (DPM of Felzenszwalb et al. [24] has become one of the most effectve and wdelyused object detecton approaches to date. The object s represented by a coarse root HOG fter and several hgher resoluton part fters. The DPM model uses a mxture of components to capture varaton n vewpont and/or pose (e.g. for a car, the three components mght correspond roughly to the front, sde and threequarter vews. Stronglysupervsed DPM Whe the lmted supervson requred for the DPM s advantageous, the latent parts provde no semantc nformaton about the object whch makes posenormalzaton challengng. Related work has used strong supervson to tran DPMs for human pose estmaton [4, 44], part localzaton [2] and object detecton [3]. Whe these methods focus on detecton, our objectve s dfferent, poolng semantc part features across components to derve a posenormalzed representaton.
3 Test Image Part Localzaton Posenormalzaton Stronglysupervsed DPM Classfcaton Class CN... Class C2 Class C Predcted Class: Lncoln Sparrow Ψpn Weaklysupervsed DPM Attrb αn... Attrb α2 Attrb α P(α[sMale] =.2 P(α2[hasHat] = P(αN[hasShorts] =.38 Fgure 2. Overvew. Both of the proposed Deformable Part Descrptors (DPDs are depcted above. The frst descrptor (top row apples a stronglysupervsed DPM [3] for part localzaton and then performs posenormalzaton by poolng features from these nherently semantc parts. The posenormalzed features Ψpn n Equaton 3 can be used for ether fnegraned recognton or attrbute predcton (as ndcated by the dotted arrows. The second descrptor employs a weaklysupervsed DPM [24] for part localzaton and then uses a learned semantc correspondence model to pool features from the componentspecfc localzed latent parts nto semantc regons (the posenormalzed descrptor Ψpn shared by all components. In the part to regon poolng (the black, yellow, magenta, and cyan lnes, wder lnes ndcate hgher weght. Best vewed n color. In ths work, we adopt a varant of the stronglysupervsed DPM [3]. We use object part annotatons and am to localze the semantc parts for posenormalzed descrptors. Instead of ntalzng the fxedsze part fters heurstcally (energy maxmzaton, we ntalze the part fters by usng semantc part annotatons. As n [3], we ntalze the mxture components by clusterng the annotated poses nstead of usng the aspect rato. After tranng the mxture of root fters, we process the tranng mages to get the component assgnment for each tranng example. Then, for each component c, the part fters of ths component are ntalzed at the average relatve locatons wth average sze among all the examples wth component assgnment c. Unlke [3], we do not mpose constrants on part overlap durng tranng. Notaton For both types of DPM, we use a latent SVM to tran the model parameters. The matchng score of a model β for a gven mage I s n X Spart (p, I, β + b S(I, β = Fβ Φ(I, p + = Spart (p, I, β = Fβ Φ(I, p d Φd (dx, dy ( where Fβ s the root fter, Fβ s the part fter, b s the bas term, Φ(I, p s the mage feature vector of the subwndow located at poston p, (dx, dy and d are respectvely s the dsplacement and dsplacement weght of the th part, and Φd (dx, dy = (dx, dy, dx2, dy 2 s used to penalze the part dsplacement[24]. The overall score s computed usng the best possble placements,.e. fβ = maxz Z(I S(I, β where Z(I s the set of all possble latent values. The model s traned by teratvely assgnng the best possble placements and learnng the parameter β by stochastc gradent descent. Then, the part locatons are predcted by Z(I = argmax(z,β S(I, β s.t. O(p (I, bbox > δ Z(I = (c(i, p (I,, pn (I (2 where c(i s the component assgnment, p (I s the predcted boundng box, p (I s the predcted locaton of part p and O(p, bbox s the overlap between the predcted boundng box and ground truth boundng box. δ s a threshold to control predctons and we set t to be.65 n our experments. Gven the part localzatons, we show below how to form DPMbased posenormalzed descrptors and pool them across components, n a manner analogous to what the Posepoolng Kernel (PPK [47] does va Poselets. 3. Deformable Part Descrptors (DPD We use the deformable part model (DPM s demonstrated effectveness for detectng objects as a foundaton for our posenormalzed approach to fnegraned recognton and attrbute predcton. We do ths as a faster and more relable alternatve to Poselets whch were prevously proposed for posenormalzaton n both fnegraned recognton [23, 47] and attrbute predcton []. As noted earler,
4 we are not the frst to consder usng DPMs for fnegraned recognton. Parkh et al. [36, 37] traned a DPM model to locate a cat s or a dog s head and then used ths detecton both to descrbe the head appearance and to seed a segmentaton whch would recover the rest of the body (See Fgure. Our goal s to use DPM to localze the parts and pool the posenormalzed mage features nduced by the part locatons. 3.. Stronglysupervsed DPD The underlyng prncple n posenormalzaton s that one can decompose an object s appearance as observed n one mage and compare t to the same object (or object category as observed n a dfferent mage. Ths decomposton generally equates to localzng semantc parts and then descrbng them. From the DPM models, suppose that we have a total of C components ncludng mrror pars C = {c (, c (2,..., c (C }, where for odd values of j, c (j+ s the mrror component of c (j. Each component c (j has a set of parts P (j = {p (j, p(j 2,..., p(j P }, p(j denotng the th part for component c (j. We now defne a posenormalzed representaton wth R semantc poolng regons R = {r, r 2,..., r R }. We defne the posenormalzed representaton as Ψ pn (I = [Ψ (I, r, Ψ (I, r,..., Ψ (I, r R ]. (3 where I, r l s the pooled mage feature for semantc regon r l and I, r s the mage feature nsde the root fter or boundng box and we concatenate the mage features together to get the fnal posenormalzed representaton Ψ pn. To derve the posenormalzed representaton for a gven detecton Z(I n Equaton 2 (from component c (j = c(i, we must fgure out a mappng S (j : P (j R. For each part p (j, we seek to determne whch posenormalzed poolng regon or regons {r l } the features I, p (j should be mapped nto. For stronglysupervsed DPM, we use the semantc part annotatons and t s straghtforward to pool the correspondng part descrptor across dfferent components by settng the semantc regons the same as the semantc parts from the strong DPM,.e. R = P (j for all j {,..., C}. I, r l = I, p (j l j {,..., C} ( Weaklysupervsed DPD Usng a weak DPM, the latent parts of dfferent components have no explct semantc correlaton, nor s such correspondence guaranteed to exst. We have explored two optons for dealng wth ths: one based on a percomponent appearance representaton wth no semantc parts; the other leverages addtonal annotatons to estmate semantc correspondence of the latent parts across components. The percomponent representaton s very straghtforward. The tranng and test sets are parttoned nto subsets accordng to whch component fres on them. A separate classfcaton model s traned for each component usng the features extracted on that component s subset of tranng mages. Ths creates reasonable classfers, however, there are two shortcomngs. Frst, the parts carry no semantc nformaton (though ths s not nherently necessary. Second, the tranng data s fragmented across the C components, so models wl be accordngly weaker. Tranng fragmentaton s partcularly problematc for fnegraned recognton where you may only have 53 tranng examples total for each category. Experments usng ths model are ncluded n Secton 4.3. The second representaton, however, solves both of these problems. By provdng semantc annotatons at tranng tme, we can model semantc correspondence between the latent parts of dfferent components. In effect, we learn the semantc dentty of each latent part n the model and can thus pool features to a global posenormalzed model, ndependent of whch component fres durng detecton. We model the posenormalzaton as a weghted bpartte graph G = (P, R, W where w (j W ndcates the, the th part of component c (j con degree to whch p (j trbutes to r l. Ψ (I, r l = N P = w (j ( Ψ I, p (j where N = P w(j s used for normalzaton. W s a three dmensonal matrx wth sze P R C and w (j s modeled as a functon of the annotatons A. Annotatons a k A could be keyponts (as used to tran Poselets, rectangular regons (as used to tran Strong DPM or any other type of semantc labels. In our example, we use the keypont annotatons ncluded wth the CUB2 dataset [42] and H3D dataset []. More precsely, we defne w (j as: w (j = k= A ( ρ kl overlap a k, p (j where ρ kl [, ] ndcates a specfed semantc relevance for annotaton a k to regon r l (e.g.( left ear s relevant to head, left knee s not. The overlap a k, p (j functon encodes the dstrbuton of annotaton a k wthn part p (j. Let I jk be the set of tranng mages that have semantc annotaton a k and where c (j s the component whch fres. We can formally defne the fractonal overlap ( overlap a k, p (j = {I I jk a k (I p (j }. (7 I jk It s worth notng that the tranng set need not be exhaustvely labeled wth semantc annotatons. Fewer annotatons (5 (6
5 just mean smaller I jk and thus coarser predctons of the weghts w (j Classfcaton Gven the posenormalzed representaton Ψ pn (I n Equaton 3, we employ a lnear SVM for the fnal classfcaton. For the stronglysupervsed DPD, we use the annotated semantc parts to get Ψ pn for tranng and part localzaton from Equaton 2 for testng; for the weaklysupervsed DPD, we utze Ψ pn from Equaton 2 for both tranng and testng. Due to the sparsty of tranng examples for certan poses, there wl be some test mages for whch a correct detecton cannot be found even gven a specfed object boundng box. Ths means that we don t have predctons for the part locatons n Equaton 2. In such cases, we can use the classfer traned on the feature descrptor nsde the boundng box I, r wthout any posenormalzaton. 4. Experments In ths secton, we wl present a comparatve performance evaluaton of our proposed method. We conduct experments on the commonly used fnegraned benchmark CaltechUCSD brd dataset [42] as well as the Berkeley Human Attrbute dataset from []. Our system can process several mages per second, leveragng the avaable fast DPM mplementaton n [2]. An opensource verson of our endtoend DPD mplementaton s avaable at In contrast, the fastest avaable mplementaton of Poseletbased [47] reles on a C++ remplementaton of [] and takes approxmately seconds per frame on a comparable machne. 4.. Implementaton Detas Image Features and Classfcaton After predctng the part regons va DPM, we use kernel descrptors [8] to extract feature vectors for fnal classfcaton. Specfcally, we use four types of kernel descrptors: gradent, local bnary pattern (lbp, rgb color, and normalzed rgb color. Followng the settng n [8], we compute kernel descrptors on local mage patches of sze 6 x 6 over a dense regular grd of step sze 8 and then apply a spatal pyramd on top. We use vector quantzaton of these descrptors wth a element codebook, concatenatng perregon descrptor hstograms nto a sngle vector per mage. These vectors are provded as nput to a lnear support vector machne (lblnear wth power scaled features. Effcent Weak Poolng In Equaton 6, whe a fully optmal formulaton would lkely learn the best convex combnaton of ρ kl and utze sophstcated dstrbutons for all For results usng deep convolutonal features, see [8] for more detas. pars (a k, p (j, we make two smplfyng assumptons for effcency and smplcty. Frst, we defne ρ kl as an ndcator such that ρ kl {,, } and l ρ kl = ; n other words, each semantc part a k s assocated wth one or more regons r l (n a few cases t s shared between two, such as the shoulder between head and torso regons. Ths represents parttonng the semantc parts A amongst the poolng regons R. Second, to evaluate the overlap(a k, p (j functon n Equaton 7, we evaluate the weaklysupervsed detector on the semantcally annotated data, notng for each detecton where the varous parts {a k } fall. Across the annotated data we accumulate dstrbutons for each part p (j (we only nclude contrbutons toward p (j when c (j fres. Whe the optmal method would lkely model these spatal dstrbutons wth respect to p (j, we relax ths and smply record the fracton of semantcally annotated mages whch have a k, for whch c (j fres and where a k has hgh overlap wth (or falls wthn p (j CaltechUCSD Brds2 Dataset We conduct our experments on the 2category Caltech UCSD brd dataset, one of the most wdely used and compettve fnegraned classfcaton benchmarks. Followng [23], we use two semantc parts for the brd dataset: head and body. We utze both the earler (CUB22 and current (CUB22 versons of the brd dataset for better comparson. CUB22 The ntal verson of the CUB2 dataset contans 633 mages of 2 dfferent brd speces n North Amerca. There are around 3 mages per class. We use the provded trantest splt whch uses 5 mages per class for tranng and the balance for testng. Each mage n the dataset has a boundng box annotaton but no other annotaton s provded. In order to tran the strong DPM wth semantc parts, we manually annotate the part locatons for the tranng mages,.e. head and body boxes. If one of the parts s not vsble, we mark ts vsbty state as. Gven those annotatons on tranng mages, we tran a strong DPM wth 5 components, each wth these two parts. Due to the lack of addtonal annotatons, we are unable to evaluate the DPDweak approach on ths dataset. Table shows the mean accuracy of our method on the CUB22 dataset. We also compare wth other publshed methods, ncludng MKL [3], random forest [46], TrCos [4], template matchng [43], segmentaton [] and the recentlypublshed Bubblebank method [7]. One baselne s to use the same mage descrptors used by our methods nsde the boundng box but wthout any pose normalzaton,.e. KDES [8], whch yelds 26.4% mean accuracy, better than some prevous methods. Our approach acheves 34.5% mean accuracy, whch outperforms the best prevous
6 Method MKL [3] Random Forest [46] KDES [8] TrCos [4] Template matchng [43] Segmentaton [] Bubblebank [7] DPDstrong2 Mean Accuracy(% %.7% 32.7% 2.5% 3.3% 3.% 2.6% HEAD 7.5% 2.7% 25.5% 2.8% 5.4%.% 3.9% 4.% BODY 2 Table. Results on CUB22 dataset. We note that [7] uses addtonal human labels. The best performance s acheved by the twopart stronglysupervsed DPD model (DPDstrong2. Method KDES [8] Template matchng[43] Oracle DPDweak8 DPDstrong2 DPDstrong2nohead DPDstrong2nobody Mean Accuracy(% Table 2. Results on CUB22 dataset usng KDES features. The best performance s acheved by the 8part weaklysupervsed DPD model (DPDweak8. Oracle s akn to DPDstrong but uses the ground truth head and body locatons. result [7], and that requres human annotatons obtaned usng a crowdsourced onlne game to fnd the most dscrmnatve regons. CUB22 The CUB22 s the latest verson of the dataset, whch ncludes more hghqualty mages and has 5 part annotatons, e.g. beak, crest, throat, lefteye, leftwng, nape, etc. Ths dataset contans,788 mages of the same 2 brd speces as CUB22. We use the default tranng/test splt, whch gves us around 3 tranng examples per class. We tran both a weak DPM and a strong DPM to factate part localzaton. For the strong DPM, we tran a mxture of fve components, each wth two parts and we partton the keypont annotatons to generate the head and body part annotatons. Specfcally, we choose the semantc part annotatons as the mnmum rectangular regon to cover the part s specfed subset of keyponts. Ths strong DPM enables part localzaton wth the followng accuraces: the head part wth 45.% precson and 43.5% recall, the body part wth 77.5% precson and 75.2% recall. Here we mark a correct predcton when the predcted part box and the ground truth part box have an overlap over. For the weak DPM, we tran a mxture of three components, each wth 8 parts and usng poolng as descrbed n Equaton 5. The poolng weghts learned for the brd model are HEAD %.% 9.6%.2%.%.%.% TORSO 2.4% 2.6%.2% 2.9% 27.2%.3% 26.3%.2% LEGS.%.2% 32.%.2%.6% 8.7% 8.2% 29.9% Fgure 3. Learned Percomponent Poolng Weghts. Pctured are examples of the weghtng models that are learned for the weaklysupervsed brd (above and human (below models (DPDweak. Shown s just one of the components for each model. In each weght matrx, rows correspond to the semantc regons that the eght latent parts (columns are pooled to. We emphasze that the weghts are learned automatcally. Best vewed n color. vsualzed n the top part of Fgure 3. Table 2 presents our classfcaton results on the CUB22 dataset usng KDES [8] features. To compute the baselne method, we use only the boundng box regon, yeldng 42.53% mean accuracy. We also evaluate the template matchng method of [43], usng code released by the authors. Our DPDstrong acheves 5.5% mean accuracy and DPDweak acheves 5.98% on ths dataset, outperformng other stateofart methods. To understand the contrbuton of ndvdual DPM parts to the classfcaton accuracy, we blnd a DPDstrong to ndvdual semantc parts n an ablaton study. These results are ncluded n Table 2. We fnd that localzng the head part of the brd s especally mportant: removng the head part, the CUB22 accuracy falls to 43.5%. Addtonal experments on the mportance of ndvdual parts are avaable on our DPD project webpage. In terms of other publshed work on ths dataset, PPK [47] makes use of Poselet actvatons to generate posenormalzed representaton and acheves a
7 Attrbute Freq SPM [] Poselets [] Percomponent DPDweak8 DPDstrong3 s male has long har has glasses has hat has tshrt has long sleeves has shorts has jeans has long pants Mean AP Table 3. Results on the Human Attrbutes dataset. Freq s the label frequency (fracton of specfed attrbutes that are postve and Percomponent gves the results when usng the percomponent poolng method dscussed n the begnnng of Secton 3.2. The values above denote mean average precson. For the full PrecsonRecall curves, see Fgure 4. Another baselne usng the same mage features but consderng only the boundng box regon acheves 66.58% mean AP. mean accuracy of 28.8%. The authors of POOF [6] recently reported performance of 56.89% enabled both by accurate part (keypont localzaton and through the tranng of thousands of classfers. We have expermented wth replacng the KDES features wth deep convolutonal features and have reported 64.96% performance (please see [8] for detas Human Attrbutes Dataset The human attrbutes dataset [] contans 835 mages collected from the H3D [] and PASCAL VOC 2 [2] datasets. There are nne attrbutes (e.g. has tshrt, has jeans, and each one has a label of {,, } respectvely meanng absent, present and unspecfed. We use the H3D data to tran a strong DPM wth 3 components and 3 semantc parts (head, torso and legs and a weak DPM wth 3 components and 8 parts. Example poolng weghts learned for the weak DPM are vsualzed n the lower part of Fgure 3. Smar to the CUB22 dataset, the semantc part annotatons are generated from the keypont annotatons avaable from H3D. We then test on both the tranng and test mages of the human attrbutes dataset to localze the parts and get posenormalzed mage descrptors for attrbute predcton. Table 3 shows predcton results on these nne attrbutes. Two baselnes are ncluded for comparson: SPM whch uses spatal pyramd match nsde the boundng box and the Poselet approach of Bourdev, et al.; both results are taken from []. We also nclude the results of usng percomponent classfers, measurng average precson under the precsonrecall curve. PrecsonRecall curves for each of the nne attrbutes are shown n Fgure 4. We use mean AP nstead of mean accuracy for ths dataset because the percentage of postve examples for each attrbute s qute vared. From the table, we see that both DPD methods outperform posenormalzaton usng Poselets and moreover, our method s approxmately 3 tmes more effcent. AP: 73.4 AP: 7.3 AP: 6. s male AP: 83.7 AP: 82.9 AP: 82.4 has hat has shorts AP: 64. AP: 59.4 AP: 45.5 has long har AP: 72.5 AP: 7. AP: 67.8 has tshrt has jeans AP: 5.2 AP: 49.8 AP: 46. AP: 78. AP: 77. AP: 54.7 AP: 78. AP: 76.5 AP: 74.2 has glasses AP: 55.6 AP: 4.7 AP: 38. has long sleeves has long pants AP: 93.5 AP: 93. AP: 9.3 Fgure 4. Attrbute Predcton PrecsonRecall Curves. Results are shown for each gven attrbute. The blue curve and mean average precson (AP scores are for the DPDstrong. The green curve and mean AP scores are for the DPDweak. The red curve and mean AP scores are for the prevous startofthe art technque of Bourdev et al. []. The dashed lne ndcates the frequency (fracton of postves. Best vewed n color. 5. Concluson In ths paper we have proposed Deformable Part Descrptors (DPDs, a posenormalzed representaton based on DPMs. We descrbed two such posenormalzed methods, respectvely applcable to stronglysupervsed and weaklysupervsed varants of deformable part models. The frst method explots the semantcs nherent n the stronglysupervsed DPM s parts, poolng them drectly to form a posenormalzed descrptor. The second uses semantc an
8 notatons to learn crosscomponent correspondences between parts of the weaklysupervsed DPM. These correspondences are then used to generate a posenormalzed descrptor. We have evaluated the proposed DPD methods, surpassng the prevous stateoftheart performance on standard datasets for both fnegraned recognton and attrbute predcton. In concluson, we outlne some drectons for future work. Frst, we suggest that a greater number of supervsed parts (as used n Azzpour et al. [3] would ncrease the descrptve power of the DPD model. However, to do ths, we would need to address the ssue of selfoccluson. Second, learnng of crosscomponent part correspondences could be enhanced by consderng unconstraned convex combnatons for the semantc relevance coeffcents ρ kl and more optmal overlap( functons that address the spatal dstrbutons of the semantc annotatons wthn parts, nstead of smply consderng occurrence frequency. Acknowledgments Ths research s funded by NSF grants IIS64 and IIS22928, by DARPA s Mnds Eye and MSEE programs, and by the Toyota Motor Corporaton. The thrd author s supported by the NDSEG Fellowshp program. References [] A. Angelova and S. Zhu. Effcent object detecton and segmentaton for fnegraned recognton. In CVPR, 23. [2] A. Angelova, S. Zhu, and Y. Ln. Image segmentaton for largescale subcategory flower recognton. In WACV, 23. [3] H. Azzpour and I. Laptev. Object Detecton Usng StronglySupervsed Deformable Part Models. In ECCV, 22. [4] P. N. Belhumeur, D. Chen, S. Fener, D. Jacobs, W. J. Kress, H. Lng, I. Lopez, R. Ramamoorth, S. Sheorey, S. Whte, and L. Zhang. Searchng the Worlds Herbara: a System for Vsual Identfcaton of Plant Speces. In ECCV, 28. [5] P. N. Belhumeur, D. W. Jacobs, D. J. Kregman, and N. Kumar. Localzng Parts of Faces Usng a Consensus of Exemplars. In CVPR, 2. [6] T. Berg and P. N. Belhumeur. Poof: Partbased onevsone features for fnegraned categorzaton, face vercaton, and attrbute estmaton. In CVPR, 23. [7] T. Berg, A. Berg, and J. Shh. Automatc Attrbute Dscovery and Characterzaton from Nosy Web Data. In ECCV, 2. [8] L. Bo, X. Ren, and D. Fox. Kernel Descrptors for Vsual Recognton. In NIPS, 2. [9] L. Bourdev, S. Maj, T. Brox, and J. Malk. Detectng People Usng Mutually Consstent Poselet Actvatons. In ECCV, 2. [] L. Bourdev, S. Maj, and J. Malk. Descrbng People: PoseletBased Approach to Attrbute Classfcaton. In ICCV, 2. [] L. Bourdev and J. Malk. Poselets: Body Part Detectors Traned Usng 3D Human Pose Annotatons. In ICCV, 29. [2] S. Branson, P. Perona, and S. Belonge. Strong Supervson From Weak Annotaton: Interactve Tranng of Deformable Part Models. In ICCV, 2. [3] S. Branson, C. Wah, F. Schroff, B. Babenko, P. Welnder, P. Perona, and S. Belonge. Vsual Recognton wth Humans n the Loop. In ECCV, 2. [4] Y. Cha, E. Rahtu, V. Lemptsky, L. V. Gool, and A. Zsserman. Trcos: A trevel classdscrmnatve cosegmentaton method for mage classfcaton. In ECCV, 22. [5] J. Deng, A. Berg, K. L, and L. FeFe. What Does Classfyng More Than, Image Categores Tell Us? In ECCV, 2. [6] J. Deng, W. Dong, R. Socher, L.J. L, K. L, and L. FeFe. ImageNet: A LargeScale Herarchcal Image Database. In CVPR, 29. [7] J. Deng, J. Krause, and L. FeFe. FneGraned Crowdsourcng for Fne Graned Recognton. In CVPR, 23. [8] J. Donahue, Y. Ja, O. Vnyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell. DeCAF: A Deep Convolutonal Actvaton Feature for Generc Vsual Recognton. In arxv, 23. [9] K. Duan, D. Parkh, D. Crandall, and K. Grauman. Dscoverng Localzed Attrbutes for Fnegraned Recognton. In CVPR, 22. [2] C. Dubout and F. Fleuret. Exact Acceleraton of Lnear Object Detectors. In ECCV, 22. [2] M. Everngham, L. Van Gool, C. K. I. Wlams, J. Wnn, and A. Zsserman. The Pascal Vsual Object Classes (VOC Challenge. IJCV, 88(2, June 2. [22] A. Farhad, I. Endres, D. Hoem, and D. Forsyth. Descrbng Objects by ther Attrbutes. In CVPR, 29. [23] R. Farrell, O. Oza, N. Zhang, V. I. Moraru, T. Darrell, and L. S. Davs. Brdlets: Subordnate Categorzaton usng Volumetrc Prmtves and Posenormalzed Appearance. In ICCV, 2. [24] P. Felzenszwalb, R. Grshck, D. McAllester, and D. Ramanan. Object Detecton wth Dscrmnatvely Traned Part Based Models. PAMI, 32(3, 2. [25] M. A. Fschler and R. A. Elschlager. The representaton and matchng of pctoral structures. IEEE Transactons on Computers, 22(:67 92, January 973. [26] A. Khosla, N. Jayadevaprakash, B. Yao, and L. FeFe. Novel dataset for fnegraned mage categorzaton. In FGVC Workshop, CVPR, 2. [27] N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attrbute and Sme Classfers for Face Verfcaton. In ICCV, 29. [28] C. H. Lampert, H. Ncksch, and S. Harmelng. Learnng to Detect Unseen Object Classes by BetweenClass Attrbute Transfer. In CVPR, 29. [29] J. Lu, A. Kanazawa, D. Jacobs, and P. Belhumeur. Dog Breed Classfcaton Usng Part Localzaton. In ECCV, 22. [3] S. Maj, J. Kannala, E. Rahtu, M. Blaschko, and A. Vedald. FneGraned Vsual Classfcaton of Arcraft. Techncal report, 23. [3] T. Malsewcz, A. Gupta, and A. A. Efros. Ensemble of ExemplarSVMs for Object Detecton and Beyond. In ICCV, 2. [32] G. MartnezMunoz, N. Laros, E. Mortensen, W. Zhang, A. Yamamuro, R. Paasch, N. Payet, D. Lytle, L. Shapro, S. Todorovc, A. Moldenke, and T. Detterch. Dctonaryfree categorzaton of very smar objects va stacked evdence trees. In CVPR, 29. [33] M.E. Nsback and A. Zsserman. A Vsual Vocabulary for Flower Classfcaton. In CVPR, 26. [34] M.E. Nsback and A. Zsserman. Automated Flower Classfcaton over a Large Number of Classes. In ICVGIP, 28. [35] D. Parkh and K. Grauman. Relatve Attrbutes. In ICCV, 2. [36] O. M. Parkh, A. Vedald, C. V. Jawahar, and A. Zsserman. The Truth About Cats and Dogs. In ICCV, 2. [37] O. M. Parkh, A. Vedald, A. Zsserman, and C. V. Jawahar. Cats and Dogs. In CVPR, 22. [38] C. Rother, V. Kolmogorov, and A. Blake. GrabCut Interactve Foreground Extracton usng Iterated Graph Cuts. In SIGGRAPH, 24. [39] A. R. Sfar, N. Boujemaa, and D. Geman. Vantage Feature Frames For Fne Graned Categorzaton. In CVPR, 23. [4] M. Stark, J. Krause, B. Pepk, D. Meger, J. J. Lttle, B. Schele, and D. Koller. FneGraned Categorzaton for 3D Scene Understandng. In BMVC, 22. [4] M. Sun and S. Savarese. Artculated Partbased Model for Jont Object Detecton and Pose Estmaton. In ICCV, 2. [42] P. Welnder, S. Branson, T. Mta, C. Wah, F. S. chroff, S. Belonge, and P. Perona. CaltechUCSD Brds 2. Techncal Report CNSTR2, Calforna Insttute of Technology, 2. [43] S. Yang, L. Bo, J. Wang, and L. Shapro. Unsupervsed Template Learnng for FneGraned Object Recognton. In NIPS, 22. [44] Y. Yang and D. Ramanan. Artculated Pose Estmaton usng Flexble Mxtures of Parts. In CVPR, 2. [45] B. Yao, G. Bradsk, and L. FeFe. A CodebookFree and AnnotatonFree Approach for Fnegraned Image Categorzaton. In CVPR, 22. [46] B. Yao, A. Khosla, and L. FeFe. Combnng Randomzaton and Dscrmnaton for Fnegraned Image Categorzaton. In CVPR, 2. [47] N. Zhang, R. Farrell, and T. Darrell. Pose poolng kernels for subcategory recognton. In CVPR, 22.
What is Candidate Sampling
What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble
More informationForecasting the Direction and Strength of Stock Market Movement
Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract  Stock market s one of the most complcated systems
More informationAn Alternative Way to Measure Private Equity Performance
An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate
More informationFace Verification Problem. Face Recognition Problem. Application: Access Control. Biometric Authentication. Face Verification (1:1 matching)
Face Recognton Problem Face Verfcaton Problem Face Verfcaton (1:1 matchng) Querymage face query Face Recognton (1:N matchng) database Applcaton: Access Control www.vsage.com www.vsoncs.com Bometrc Authentcaton
More informationNonlinear data mapping by neural networks
Nonlnear data mappng by neural networks R.P.W. Dun Delft Unversty of Technology, Netherlands Abstract A revew s gven of the use of neural networks for nonlnear mappng of hgh dmensonal data on lower dmensonal
More informationThe Development of Web Log Mining Based on ImproveKMeans Clustering Analysis
The Development of Web Log Mnng Based on ImproveKMeans Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.
More informationFeature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College
Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure
More informationBERNSTEIN POLYNOMIALS
OnLne Geometrc Modelng Notes BERNSTEIN POLYNOMIALS Kenneth I. Joy Vsualzaton and Graphcs Research Group Department of Computer Scence Unversty of Calforna, Davs Overvew Polynomals are ncredbly useful
More informationLogistic Regression. Lecture 4: More classifiers and classes. Logistic regression. Adaboost. Optimization. Multiple class classification
Lecture 4: More classfers and classes C4B Machne Learnng Hlary 20 A. Zsserman Logstc regresson Loss functons revsted Adaboost Loss functons revsted Optmzaton Multple class classfcaton Logstc Regresson
More informationSingle and multiple stage classifiers implementing logistic discrimination
Sngle and multple stage classfers mplementng logstc dscrmnaton Hélo Radke Bttencourt 1 Dens Alter de Olvera Moraes 2 Vctor Haertel 2 1 Pontfíca Unversdade Católca do Ro Grande do Sul  PUCRS Av. Ipranga,
More informationDescriptive Models. Cluster Analysis. Example. General Applications of Clustering. Examples of Clustering Applications
CMSC828G Prncples of Data Mnng Lecture #9 Today s Readng: HMS, chapter 9 Today s Lecture: Descrptve Modelng Clusterng Algorthms Descrptve Models model presents the man features of the data, a global summary
More informationVision Mouse. Saurabh Sarkar a* University of Cincinnati, Cincinnati, USA ABSTRACT 1. INTRODUCTION
Vson Mouse Saurabh Sarkar a* a Unversty of Cncnnat, Cncnnat, USA ABSTRACT The report dscusses a vson based approach towards trackng of eyes and fngers. The report descrbes the process of locatng the possble
More informationBagofWords models. Lecture 9. Slides from: S. Lazebnik, A. Torralba, L. FeiFei, D. Lowe, C. Szurka
BagofWords models Lecture 9 Sldes from: S. Lazebnk, A. Torralba, L. FeFe, D. Lowe, C. Szurka Bagoffeatures models Overvew: Bagoffeatures models Orgns and motvaton Image representaton Dscrmnatve
More information1 Approximation Algorithms
CME 305: Dscrete Mathematcs and Algorthms 1 Approxmaton Algorthms In lght of the apparent ntractablty of the problems we beleve not to le n P, t makes sense to pursue deas other than complete solutons
More informationCan Auto Liability Insurance Purchases Signal Risk Attitude?
Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? ChuShu L Department of Internatonal Busness, Asa Unversty, Tawan ShengChang
More informationMAPP. MERIS level 3 cloud and water vapour products. Issue: 1. Revision: 0. Date: 9.12.1998. Function Name Organisation Signature Date
Ttel: Project: Doc. No.: MERIS level 3 cloud and water vapour products MAPP MAPPATBDClWVL3 Issue: 1 Revson: 0 Date: 9.12.1998 Functon Name Organsaton Sgnature Date Author: Bennartz FUB Preusker FUB Schüller
More informationBrigid Mullany, Ph.D University of North Carolina, Charlotte
Evaluaton And Comparson Of The Dfferent Standards Used To Defne The Postonal Accuracy And Repeatablty Of Numercally Controlled Machnng Center Axes Brgd Mullany, Ph.D Unversty of North Carolna, Charlotte
More informationModule 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur
Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..
More informationA machine vision approach for detecting and inspecting circular parts
A machne vson approach for detectng and nspectng crcular parts DuMng Tsa Machne Vson Lab. Department of Industral Engneerng and Management YuanZe Unversty, ChungL, Tawan, R.O.C. Emal: edmtsa@saturn.yzu.edu.tw
More informationInequality and The Accounting Period. Quentin Wodon and Shlomo Yitzhaki. World Bank and Hebrew University. September 2001.
Inequalty and The Accountng Perod Quentn Wodon and Shlomo Ytzha World Ban and Hebrew Unversty September Abstract Income nequalty typcally declnes wth the length of tme taen nto account for measurement.
More informationSupport Vector Machines
Support Vector Machnes Max Wellng Department of Computer Scence Unversty of Toronto 10 Kng s College Road Toronto, M5S 3G5 Canada wellng@cs.toronto.edu Abstract Ths s a note to explan support vector machnes.
More informationGender Classification for RealTime Audience Analysis System
Gender Classfcaton for RealTme Audence Analyss System Vladmr Khryashchev, Lev Shmaglt, Andrey Shemyakov, Anton Lebedev Yaroslavl State Unversty Yaroslavl, Russa vhr@yandex.ru, shmaglt_lev@yahoo.com, andrey.shemakov@gmal.com,
More informationCausal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting
Causal, Explanatory Forecastng Assumes causeandeffect relatonshp between system nputs and ts output Forecastng wth Regresson Analyss Rchard S. Barr Inputs System Cause + Effect Relatonshp The job of
More informationAn interactive system for structurebased ASCII art creation
An nteractve system for structurebased ASCII art creaton Katsunor Myake Henry Johan Tomoyuk Nshta The Unversty of Tokyo Nanyang Technologcal Unversty Abstract NonPhotorealstc Renderng (NPR), whose am
More informationAnalysis of Premium Liabilities for Australian Lines of Business
Summary of Analyss of Premum Labltes for Australan Lnes of Busness Emly Tao Honours Research Paper, The Unversty of Melbourne Emly Tao Acknowledgements I am grateful to the Australan Prudental Regulaton
More informationDEFINING %COMPLETE IN MICROSOFT PROJECT
CelersSystems DEFINING %COMPLETE IN MICROSOFT PROJECT PREPARED BY James E Aksel, PMP, PMISP, MVP For Addtonal Informaton about Earned Value Management Systems and reportng, please contact: CelersSystems,
More informationCommunication Networks II Contents
8 / 1  Communcaton Networs II (Görg)  www.comnets.unbremen.de Communcaton Networs II Contents 1 Fundamentals of probablty theory 2 Traffc n communcaton networs 3 Stochastc & Marovan Processes (SP
More informationPerformance Analysis and Coding Strategy of ECOC SVMs
Internatonal Journal of Grd and Dstrbuted Computng Vol.7, No. (04), pp.6776 http://dx.do.org/0.457/jgdc.04.7..07 Performance Analyss and Codng Strategy of ECOC SVMs Zhgang Yan, and Yuanxuan Yang, School
More information8.5 UNITARY AND HERMITIAN MATRICES. The conjugate transpose of a complex matrix A, denoted by A*, is given by
6 CHAPTER 8 COMPLEX VECTOR SPACES 5. Fnd the kernel of the lnear transformaton gven n Exercse 5. In Exercses 55 and 56, fnd the mage of v, for the ndcated composton, where and are gven by the followng
More informationDetecting Global Motion Patterns in Complex Videos
Detectng Global Moton Patterns n Complex Vdeos Mn Hu, Saad Al, Mubarak Shah Computer Vson Lab, Unversty of Central Florda {mhu,sal,shah}@eecs.ucf.edu Abstract Learnng domnant moton patterns or actvtes
More informationLecture 2: Single Layer Perceptrons Kevin Swingler
Lecture 2: Sngle Layer Perceptrons Kevn Sngler kms@cs.str.ac.uk Recap: McCullochPtts Neuron Ths vastly smplfed model of real neurons s also knon as a Threshold Logc Unt: W 2 A Y 3 n W n. A set of synapses
More informationStatistical Methods to Develop Rating Models
Statstcal Methods to Develop Ratng Models [Evelyn Hayden and Danel Porath, Österrechsche Natonalbank and Unversty of Appled Scences at Manz] Source: The Basel II Rsk Parameters Estmaton, Valdaton, and
More informationPSYCHOLOGICAL RESEARCH (PYC 304C) Lecture 12
14 The Chsquared dstrbuton PSYCHOLOGICAL RESEARCH (PYC 304C) Lecture 1 If a normal varable X, havng mean µ and varance σ, s standardsed, the new varable Z has a mean 0 and varance 1. When ths standardsed
More informationCHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol
CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK Sample Stablty Protocol Background The Cholesterol Reference Method Laboratory Network (CRMLN) developed certfcaton protocols for total cholesterol, HDL
More informationCalculating the high frequency transmission line parameters of power cables
< ' Calculatng the hgh frequency transmsson lne parameters of power cables Authors: Dr. John Dcknson, Laboratory Servces Manager, N 0 RW E B Communcatons Mr. Peter J. Ncholson, Project Assgnment Manager,
More informationThe Analysis of Outliers in Statistical Data
THALES Project No. xxxx The Analyss of Outlers n Statstcal Data Research Team Chrysses Caron, Assocate Professor (P.I.) Vaslk Karot, Doctoral canddate Polychrons Economou, Chrstna Perrakou, Postgraduate
More informationLatent Class Regression. Statistics for Psychosocial Research II: Structural Models December 4 and 6, 2006
Latent Class Regresson Statstcs for Psychosocal Research II: Structural Models December 4 and 6, 2006 Latent Class Regresson (LCR) What s t and when do we use t? Recall the standard latent class model
More informationWho are you with and Where are you going?
Who are you wth and Where are you gong? Kota Yamaguch Alexander C. Berg Lus E. Ortz Tamara L. Berg Stony Brook Unversty Stony Brook Unversty, NY 11794, USA {kyamagu, aberg, leortz, tlberg}@cs.stonybrook.edu
More informationDocument Clustering Analysis Based on Hybrid PSO+Kmeans Algorithm
Document Clusterng Analyss Based on Hybrd PSO+Kmeans Algorthm Xaohu Cu, Thomas E. Potok Appled Software Engneerng Research Group, Computatonal Scences and Engneerng Dvson, Oak Rdge Natonal Laboratory,
More information) of the Cell class is created containing information about events associated with the cell. Events are added to the Cell instance
Calbraton Method Instances of the Cell class (one nstance for each FMS cell) contan ADC raw data and methods assocated wth each partcular FMS cell. The calbraton method ncludes event selecton (Class Cell
More informationAn InterestOriented Network Evolution Mechanism for Online Communities
An InterestOrented Network Evoluton Mechansm for Onlne Communtes Cahong Sun and Xaopng Yang School of Informaton, Renmn Unversty of Chna, Bejng 100872, P.R. Chna {chsun,yang}@ruc.edu.cn Abstract. Onlne
More informationRank Based Clustering For Document Retrieval From Biomedical Databases
Jayanth Mancassamy et al /Internatonal Journal on Computer Scence and Engneerng Vol.1(2), 2009, 111115 Rank Based Clusterng For Document Retreval From Bomedcal Databases Jayanth Mancassamy Department
More informationBypassing Synthesis: PLS for Face Recognition with Pose, LowResolution and Sketch
Bypassng Synthess: PLS for Face Recognton wth Pose, LowResoluton and Setch Abhshe Sharma Insttute of Advanced Computer Scence Unversty of Maryland, USA bhoaal@umacs.umd.edu Davd W Jacobs Insttute of Advanced
More informationCredit Limit Optimization (CLO) for Credit Cards
Credt Lmt Optmzaton (CLO) for Credt Cards Vay S. Desa CSCC IX, Ednburgh September 8, 2005 Copyrght 2003, SAS Insttute Inc. All rghts reserved. SAS Propretary Agenda Background Tradtonal approaches to credt
More information1 Example 1: Axisaligned rectangles
COS 511: Theoretcal Machne Learnng Lecturer: Rob Schapre Lecture # 6 Scrbe: Aaron Schld February 21, 2013 Last class, we dscussed an analogue for Occam s Razor for nfnte hypothess spaces that, n conjuncton
More informationGRAVITY DATA VALIDATION AND OUTLIER DETECTION USING L 1 NORM
GRAVITY DATA VALIDATION AND OUTLIER DETECTION USING L 1 NORM BARRIOT JeanPerre, SARRAILH Mchel BGI/CNES 18.av.E.Beln 31401 TOULOUSE Cedex 4 (France) Emal: jeanperre.barrot@cnes.fr 1/Introducton The
More informationCHAPTER 14 MORE ABOUT REGRESSION
CHAPTER 14 MORE ABOUT REGRESSION We learned n Chapter 5 that often a straght lne descrbes the pattern of a relatonshp between two quanttatve varables. For nstance, n Example 5.1 we explored the relatonshp
More informationStudy on CET4 Marks in China s Graded English Teaching
Study on CET4 Marks n Chna s Graded Englsh Teachng CHE We College of Foregn Studes, Shandong Insttute of Busness and Technology, P.R.Chna, 264005 Abstract: Ths paper deploys Logt model, and decomposes
More informationCONSISTENT VEHICLES TRACKING BY USING A COOPERATIVE DISTRIBUTED VIDEO SURVEILLANCESYSTEM
Internatonal Research Journal of Appled and Basc Scences 2013 Avalable onlne at www.rjabs.com ISSN 2251838X / Vol, 4 (12):36583663 Scence Explorer Publcatons CONSISTENT VEHICLES TRACKING BY USING A COOPERATIVE
More informationEffective waveletbased compression method with adaptive quantization threshold and zerotree coding
Effectve waveletbased compresson method wth adaptve quantzaton threshold and zerotree codng Artur Przelaskowsk, Maran Kazubek, Tomasz Jamrógewcz Insttute of Radoelectroncs, Warsaw Unversty of Technology,
More informationDamage detection in composite laminates using cointap method
Damage detecton n composte lamnates usng contap method S.J. Km Korea Aerospace Research Insttute, 45 EoeunDong, YouseongGu, 35333 Daejeon, Republc of Korea yaeln@kar.re.kr 45 The contap test has the
More informationL10: Linear discriminants analysis
L0: Lnear dscrmnants analyss Lnear dscrmnant analyss, two classes Lnear dscrmnant analyss, C classes LDA vs. PCA Lmtatons of LDA Varants of LDA Other dmensonalty reducton methods CSCE 666 Pattern Analyss
More informationFast Fuzzy Clustering of Web Page Collections
Fast Fuzzy Clusterng of Web Page Collectons Chrstan Borgelt and Andreas Nürnberger Dept. of Knowledge Processng and Language Engneerng OttovonGuerckeUnversty of Magdeburg Unverstätsplatz, D396 Magdeburg,
More informationThe Analysis of Covariance. ERSH 8310 Keppel and Wickens Chapter 15
The Analyss of Covarance ERSH 830 Keppel and Wckens Chapter 5 Today s Class Intal Consderatons Covarance and Lnear Regresson The Lnear Regresson Equaton TheAnalyss of Covarance Assumptons Underlyng the
More informationFREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES
FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES Zuzanna BRO EKMUCHA, Grzegorz ZADORA, 2 Insttute of Forensc Research, Cracow, Poland 2 Faculty of Chemstry, Jagellonan
More information320 The Internatonal Arab Journal of Informaton Technology, Vol. 5, No. 3, July 2008 Comparsons Between Data Clusterng Algorthms Osama Abu Abbas Computer Scence Department, Yarmouk Unversty, Jordan Abstract:
More informationRealistic Image Synthesis
Realstc Image Synthess  Combned Samplng and Path Tracng  Phlpp Slusallek Karol Myszkowsk Vncent Pegoraro Overvew: Today Combned Samplng (Multple Importance Samplng) Renderng and Measurng Equaton Random
More informationAn Enhanced SuperResolution System with Improved Image Registration, Automatic Image Selection, and Image Enhancement
An Enhanced SuperResoluton System wth Improved Image Regstraton, Automatc Image Selecton, and Image Enhancement YuChuan Kuo ( ), ChenYu Chen ( ), and ChouShann Fuh ( ) Department of Computer Scence
More informationRecurrence. 1 Definitions and main statements
Recurrence 1 Defntons and man statements Let X n, n = 0, 1, 2,... be a MC wth the state space S = (1, 2,...), transton probabltes p j = P {X n+1 = j X n = }, and the transton matrx P = (p j ),j S def.
More informationInstitute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic
Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange
More informationbenefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).
REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or
More informationConversion between the vector and raster data structures using Fuzzy Geographical Entities
Converson between the vector and raster data structures usng Fuzzy Geographcal Enttes Cdála Fonte Department of Mathematcs Faculty of Scences and Technology Unversty of Combra, Apartado 38, 3 454 Combra,
More informationAssessing Student Learning Through Keyword Density Analysis of Online Class Messages
Assessng Student Learnng Through Keyword Densty Analyss of Onlne Class Messages Xn Chen New Jersey Insttute of Technology xc7@njt.edu Brook Wu New Jersey Insttute of Technology wu@njt.edu ABSTRACT Ths
More informationTraffic State Estimation in the Traffic Management Center of Berlin
Traffc State Estmaton n the Traffc Management Center of Berln Authors: Peter Vortsch, PTV AG, Stumpfstrasse, D763 Karlsruhe, Germany phone ++49/72/965/35, emal peter.vortsch@ptv.de Peter Möhl, PTV AG,
More informationLuby s Alg. for Maximal Independent Sets using Pairwise Independence
Lecture Notes for Randomzed Algorthms Luby s Alg. for Maxmal Independent Sets usng Parwse Independence Last Updated by Erc Vgoda on February, 006 8. Maxmal Independent Sets For a graph G = (V, E), an ndependent
More information1. Measuring association using correlation and regression
How to measure assocaton I: Correlaton. 1. Measurng assocaton usng correlaton and regresson We often would lke to know how one varable, such as a mother's weght, s related to another varable, such as a
More informationJoe Pimbley, unpublished, 2005. Yield Curve Calculations
Joe Pmbley, unpublshed, 005. Yeld Curve Calculatons Background: Everythng s dscount factors Yeld curve calculatons nclude valuaton of forward rate agreements (FRAs), swaps, nterest rate optons, and forward
More informationWeb Object Indexing Using Domain Knowledge *
Web Object Indexng Usng Doman Knowledge * Muyuan Wang Department of Automaton Tsnghua Unversty Bejng 100084, Chna (8610)51774518 Zhwe L, Le Lu, WeYng Ma Mcrosoft Research Asa Sgma Center, Hadan Dstrct
More informationAdaptive Fractal Image Coding in the Frequency Domain
PROCEEDINGS OF INTERNATIONAL WORKSHOP ON IMAGE PROCESSING: THEORY, METHODOLOGY, SYSTEMS AND APPLICATIONS 222 JUNE,1994 BUDAPEST,HUNGARY Adaptve Fractal Image Codng n the Frequency Doman K AI UWE BARTHEL
More informationVehicle Detection and Tracking in Video from Moving Airborne Platform
Journal of Computatonal Informaton Systems 10: 12 (2014) 4965 4972 Avalable at http://www.jofcs.com Vehcle Detecton and Trackng n Vdeo from Movng Arborne Platform Lye ZHANG 1,2,, Hua WANG 3, L LI 2 1 School
More informationA Secure PasswordAuthenticated Key Agreement Using Smart Cards
A Secure PasswordAuthentcated Key Agreement Usng Smart Cards Ka Chan 1, WenChung Kuo 2 and JnChou Cheng 3 1 Department of Computer and Informaton Scence, R.O.C. Mltary Academy, Kaohsung 83059, Tawan,
More information1.1 The University may award Higher Doctorate degrees as specified from timetotime in UPR AS11 1.
HIGHER DOCTORATE DEGREES SUMMARY OF PRINCIPAL CHANGES General changes None Secton 3.2 Refer to text (Amendments to verson 03.0, UPR AS02 are shown n talcs.) 1 INTRODUCTION 1.1 The Unversty may award Hgher
More informationA Multimode Image Tracking System Based on Distributed Fusion
A Multmode Image Tracng System Based on Dstrbuted Fuson Ln zheng Chongzhao Han Dongguang Zuo Hongsen Yan School of Electroncs & nformaton engneerng, X an Jaotong Unversty X an, Shaanx, Chna Lnzheng@malst.xjtu.edu.cn
More information"Research Note" APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES *
Iranan Journal of Scence & Technology, Transacton B, Engneerng, ol. 30, No. B6, 789794 rnted n The Islamc Republc of Iran, 006 Shraz Unversty "Research Note" ALICATION OF CHARGE SIMULATION METHOD TO ELECTRIC
More informationMining Feature Importance: Applying Evolutionary Algorithms within a Webbased Educational System
Mnng Feature Importance: Applyng Evolutonary Algorthms wthn a Webbased Educatonal System Behrouz MINAEIBIDGOLI 1, and Gerd KORTEMEYER 2, and Wllam F. PUNCH 1 1 Genetc Algorthms Research and Applcatons
More informationThe OC Curve of Attribute Acceptance Plans
The OC Curve of Attrbute Acceptance Plans The Operatng Characterstc (OC) curve descrbes the probablty of acceptng a lot as a functon of the lot s qualty. Fgure 1 shows a typcal OC Curve. 10 8 6 4 1 3 4
More informationCS 2750 Machine Learning. Lecture 17a. Clustering. CS 2750 Machine Learning. Clustering
Lecture 7a Clusterng Mlos Hauskrecht mlos@cs.ptt.edu 539 Sennott Square Clusterng Groups together smlar nstances n the data sample Basc clusterng problem: dstrbute data nto k dfferent groups such that
More informationCS 2750 Machine Learning. Lecture 3. Density estimation. CS 2750 Machine Learning. Announcements
Lecture 3 Densty estmaton Mlos Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square Next lecture: Matlab tutoral Announcements Rules for attendng the class: Regstered for credt Regstered for audt (only f there
More information8 Algorithm for Binary Searching in Trees
8 Algorthm for Bnary Searchng n Trees In ths secton we present our algorthm for bnary searchng n trees. A crucal observaton employed by the algorthm s that ths problem can be effcently solved when the
More informationExhaustive Regression. An Exploration of RegressionBased Data Mining Techniques Using Super Computation
Exhaustve Regresson An Exploraton of RegressonBased Data Mnng Technques Usng Super Computaton Antony Daves, Ph.D. Assocate Professor of Economcs Duquesne Unversty Pttsburgh, PA 58 Research Fellow The
More informationEye Center Localization on a Facial Image Based on MultiBlock Local Binary Patterns
Eye Center Localzaton on a Facal Image Based on MultBloc Local Bnary Patterns Anatoly tn, Vladmr Khryashchev, Olga Stepanova Yaroslavl State Unversty Yaroslavl, Russa anatolyntnyar@gmal.com, vhr@yandex.ru,
More informationSIMPLE LINEAR CORRELATION
SIMPLE LINEAR CORRELATION Smple lnear correlaton s a measure of the degree to whch two varables vary together, or a measure of the ntensty of the assocaton between two varables. Correlaton often s abused.
More informationEfficient Project Portfolio as a tool for Enterprise Risk Management
Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse
More informationProject Networks With MixedTime Constraints
Project Networs Wth MxedTme Constrants L Caccetta and B Wattananon Western Australan Centre of Excellence n Industral Optmsaton (WACEIO) Curtn Unversty of Technology GPO Box U1987 Perth Western Australa
More informationForecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network
700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School
More informationTrafficlight a stress test for life insurance provisions
MEMORANDUM Date 006097 Authors Bengt von Bahr, Göran Ronge Traffclght a stress test for lfe nsurance provsons Fnansnspetonen P.O. Box 6750 SE113 85 Stocholm [Sveavägen 167] Tel +46 8 787 80 00 Fax
More informationDropout: A Simple Way to Prevent Neural Networks from Overfitting
Journal of Machne Learnng Research 15 (2014) 19291958 Submtted 11/13; Publshed 6/14 Dropout: A Smple Way to Prevent Neural Networks from Overfttng Ntsh Srvastava Geoffrey Hnton Alex Krzhevsky Ilya Sutskever
More informationPRACTICE 1: MUTUAL FUNDS EVALUATION USING MATLAB.
PRACTICE 1: MUTUAL FUNDS EVALUATION USING MATLAB. INDEX 1. Load data usng the Edtor wndow and mfle 2. Learnng to save results from the Edtor wndow. 3. Computng the Sharpe Rato 4. Obtanng the Treynor Rato
More informationBayesian Network Based Causal Relationship Identification and Funding Success Prediction in P2P Lending
Proceedngs of 2012 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 25 (2012) (2012) IACSIT Press, Sngapore Bayesan Network Based Causal Relatonshp Identfcaton and Fundng Success
More informationFrequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters
Frequency Selectve IQ Phase and IQ Ampltude Imbalance Adjustments for OFDM Drect Converson ransmtters Edmund Coersmeer, Ernst Zelnsk Noka, Meesmannstrasse 103, 44807 Bochum, Germany edmund.coersmeer@noka.com,
More informationCharacterization of Assembly. Variation Analysis Methods. A Thesis. Presented to the. Department of Mechanical Engineering. Brigham Young University
Characterzaton of Assembly Varaton Analyss Methods A Thess Presented to the Department of Mechancal Engneerng Brgham Young Unversty In Partal Fulfllment of the Requrements for the Degree Master of Scence
More informationTechniques for multiresolution image registration in the presence of occlusions 1
Technques for multresoluton mage regstraton n the presence of occlusons organ cgure Harold S. Stone morganm@mt.edu, hstone@research.n.nec.com Abstract Ths paper descrbes and compares technques for regsterng
More informationNumber of Levels Cumulative Annual operating Income per year construction costs costs ($) ($) ($) 1 600,000 35,000 100,000 2 2,200,000 60,000 350,000
Problem Set 5 Solutons 1 MIT s consderng buldng a new car park near Kendall Square. o unversty funds are avalable (overhead rates are under pressure and the new faclty would have to pay for tself from
More informationRing structure of splines on triangulations
www.oeaw.ac.at Rng structure of splnes on trangulatons N. Vllamzar RICAMReport 201448 www.rcam.oeaw.ac.at RING STRUCTURE OF SPLINES ON TRIANGULATIONS NELLY VILLAMIZAR Introducton For a trangulated regon
More informationLecture 18: Clustering & classification
O CPS260/BGT204. Algorthms n Computatonal Bology October 30, 2003 Lecturer: Pana K. Agarwal Lecture 8: Clusterng & classfcaton Scrbe: Daun Hou Open Problem In HomeWor 2, problem 5 has an open problem whch
More informationAn Empirical Study of Search Engine Advertising Effectiveness
An Emprcal Study of Search Engne Advertsng Effectveness Sanjog Msra, Smon School of Busness Unversty of Rochester Edeal Pnker, Smon School of Busness Unversty of Rochester Alan RmmKaufman, RmmKaufman
More informationHuman behaviour analysis and event recognition at a point of sale
Human behavour analyss and event recognton at a pont of sale R. Scre MIRANE S.A.S. Cenon, France scre@labr.fr H. Ncolas LaBRI, Unversty of Bordeaux Talence, France ncolas@labr.fr Abstract Ths paper presents
More informationImplementation of Deutsch's Algorithm Using Mathcad
Implementaton of Deutsch's Algorthm Usng Mathcad Frank Roux The followng s a Mathcad mplementaton of Davd Deutsch's quantum computer prototype as presented on pages  n "Machnes, Logc and Quantum Physcs"
More information3 Supervised Learning
3 Supervsed Learnng Supervsed learnng has been a great success n realworld applcatons. It s used n almost every doman, ncludng text and Web domans. Supervsed learnng s also called classfcaton or nductve
More informationCHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES
CHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES In ths chapter, we wll learn how to descrbe the relatonshp between two quanttatve varables. Remember (from Chapter 2) that the terms quanttatve varable
More information