IEEE Trans Image Process - Unified structured learning for simultaneous human pose estimation and garment attribute classification.

Tópicos

{ learn(2355) train(1041) set(1003) }
{ structur(1116) can(940) graph(676) }
{ problem(2511) optim(1539) algorithm(950) }
{ gene(2352) biolog(1181) express(1162) }
{ perform(1367) use(1326) method(1137) }
{ data(1737) use(1416) pattern(1282) }
{ featur(3375) classif(2383) classifi(1994) }
{ motion(1329) object(1292) video(1091) }
{ result(1111) use(1088) new(759) }
{ take(945) account(800) differ(722) }
{ can(981) present(881) function(850) }
{ estim(2440) model(1874) function(577) }
{ network(2748) neural(1063) input(814) }
{ data(3963) clinic(1234) research(1004) }
{ activ(1138) subject(705) human(624) }
{ method(1219) similar(1157) match(930) }
{ imag(1057) registr(996) error(939) }
{ framework(1458) process(801) describ(734) }
{ concept(1167) ontolog(924) domain(897) }
{ data(1714) softwar(1251) tool(1186) }
{ featur(1941) imag(1645) propos(1176) }
{ spatial(1525) area(1432) region(1030) }
{ health(3367) inform(1360) care(1135) }
{ data(3008) multipl(1320) sourc(1022) }
{ high(1669) rate(1365) level(1280) }
{ drug(1928) target(777) effect(648) }
{ implement(1333) system(1263) develop(1122) }
{ process(1125) use(805) approach(778) }
{ imag(1947) propos(1133) code(1026) }
{ clinic(1479) use(1117) guidelin(835) }
{ algorithm(1844) comput(1787) effici(935) }
{ design(1359) user(1324) use(1319) }
{ care(1570) inform(1187) nurs(1089) }
{ general(901) number(790) one(736) }
{ studi(1410) differ(1259) use(1210) }
{ system(1050) medic(1026) inform(1018) }
{ model(2341) predict(2261) use(1141) }
{ studi(1119) effect(1106) posit(819) }
{ ehr(2073) health(1662) electron(1139) }
{ first(2504) two(1366) second(1323) }
{ method(1969) cluster(1462) data(1082) }
{ model(3404) distribut(989) bayesian(671) }
{ can(774) often(719) complex(702) }
{ inform(2794) health(2639) internet(1427) }
{ system(1976) rule(880) can(841) }
{ measur(2081) correl(1212) valu(896) }
{ bind(1733) structur(1185) ligand(1036) }
{ sequenc(1873) structur(1644) protein(1328) }
{ imag(2830) propos(1344) filter(1198) }
{ imag(2675) segment(2577) method(1081) }
{ patient(2315) diseas(1263) diabet(1191) }
{ studi(2440) review(1878) systemat(933) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ error(1145) method(1030) estim(1020) }
{ chang(1828) time(1643) increas(1301) }
{ extract(1171) text(1153) clinic(932) }
{ method(1557) propos(1049) approach(1037) }
{ control(1307) perform(991) simul(935) }
{ model(2220) cell(1177) simul(1124) }
{ method(984) reconstruct(947) comput(926) }
{ search(2224) databas(1162) retriev(909) }
{ case(1353) use(1143) diagnosi(1136) }
{ howev(809) still(633) remain(590) }
{ risk(3053) factor(974) diseas(938) }
{ perform(999) metric(946) measur(919) }
{ research(1085) discuss(1038) issu(1018) }
{ import(1318) role(1303) understand(862) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ blood(1257) pressur(1144) flow(957) }
{ record(1888) medic(1808) patient(1693) }
{ model(3480) simul(1196) paramet(876) }
{ monitor(1329) mobil(1314) devic(1160) }
{ state(1844) use(1261) util(961) }
{ research(1218) medic(880) student(794) }
{ patient(2837) hospit(1953) medic(668) }
{ model(2656) set(1616) predict(1553) }
{ data(2317) use(1299) case(1017) }
{ age(1611) year(1155) adult(843) }
{ medic(1828) order(1363) alert(1069) }
{ signal(2180) analysi(812) frequenc(800) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ sampl(1606) size(1419) use(1276) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ use(2086) technolog(871) perceiv(783) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ cancer(2502) breast(956) screen(824) }
{ use(976) code(926) identifi(902) }
{ use(1733) differ(960) four(931) }
{ survey(1388) particip(1329) question(1065) }
{ decis(3086) make(1611) patient(1517) }
{ activ(1452) weight(1219) physic(1104) }
{ method(2212) result(1239) propos(1039) }
{ detect(2391) sensit(1101) algorithm(908) }

Resumo

In this paper, we utilize structured learning to simultaneously address two intertwined problems: 1) human pose estimation (HPE) and 2) garment attribute classification (GAC), which are valuable for a variety of computer vision and multimedia applications. Unlike previous works that usually handle the two problems separately, our approach aims to produce an optimal joint estimation for both HPE and GAC via a unified inference procedure. To this end, we adopt a preprocessing step to detect potential human parts from each image (i.e., a set of candidates) that allows us to have a manageable input space. In this way, the simultaneous inference of HPE and GAC is converted to a structured learning problem, where the inputs are the collections of candidate ensembles, outputs are the joint labels of human parts and garment attributes, and joint feature representation involves various cues such as pose-specific features, garment-specific features, and cross-task features that encode correlations between human parts and garment attributes. Furthermore, we explore the strong edge evidence around the potential human parts so as to derive more powerful representations for oriented human parts. Such evidences can be seamlessly integrated into our structured learning model as a kind of energy function, and the learning process could be performed by standard structured support vector machines algorithm. However, the joint structure of the two problems is a cyclic graph, which hinders efficient inference. To resolve this issue, we compute instead approximate optima using an iterative procedure, where in each iteration, the variables of one problem are fixed. In this way, satisfactory solutions can be efficiently computed by dynamic programming. Experimental results on two benchmark data sets show the state-of-the-art performance of our approach.

Resumo Limpo

paper util structur learn simultan address two intertwin problem human pose estim hpe garment attribut classif gac valuabl varieti comput vision multimedia applic unlik previous work usual handl two problem separ approach aim produc optim joint estim hpe gac via unifi infer procedur end adopt preprocess step detect potenti human part imag ie set candid allow us manag input space way simultan infer hpe gac convert structur learn problem input collect candid ensembl output joint label human part garment attribut joint featur represent involv various cue posespecif featur garmentspecif featur crosstask featur encod correl human part garment attribut furthermor explor strong edg evid around potenti human part deriv power represent orient human part evid can seamless integr structur learn model kind energi function learn process perform standard structur support vector machin algorithm howev joint structur two problem cyclic graph hinder effici infer resolv issu comput instead approxim optima use iter procedur iter variabl one problem fix way satisfactori solut can effici comput dynam program experiment result two benchmark data set show stateoftheart perform approach

Resumos Similares

Comput. Biol. Med. - Locally linear representation Fisher criterion based tumor gene expressive data classification. ( 0,757593787735666 )
IEEE Trans Pattern Anal Mach Intell - Feature Selection with Conjunctions of Decision Stumps and Learning from Microarray Data. ( 0,728873404272348 )
IEEE Trans Neural Netw Learn Syst - Kernel reconstruction ICA for sparse representation. ( 0,693827799095502 )
Neural Comput - Large margin low rank tensor analysis. ( 0,680413817439772 )
J Chem Inf Model - Classifying large chemical data sets: using a regularized potential function method. ( 0,65549574725903 )
IEEE Trans Neural Netw Learn Syst - An efficient topological distance-based tree kernel. ( 0,654119573637352 )
IEEE Trans Neural Netw Learn Syst - ML-Tree: a tree-structure-based approach to multilabel learning. ( 0,651996965154982 )
J Biomed Inform - Class proximity measures--dissimilarity-based classification and display of high-dimensional data. ( 0,65164481698093 )
IEEE Trans Image Process - Task-specific image partitioning. ( 0,651591639879684 )
IEEE Trans Image Process - Multiview Hessian regularization for image annotation. ( 0,65099404853601 )
IEEE Trans Pattern Anal Mach Intell - Representation Learning: A Review and New Perspectives. ( 0,647780344773907 )
IEEE Trans Image Process - Real-time object tracking via online discriminative feature selection. ( 0,646732005891681 )
Neural Comput - Learning rates of lq coefficient regularization learning with gaussian kernel. ( 0,645468119166994 )
IEEE Trans Pattern Anal Mach Intell - A Variance Minimization Criterion to Feature Selection Using Laplacian Regularization. ( 0,645241531260478 )
Neural Comput - Incremental learning by message passing in hierarchical temporal memory. ( 0,642746491985372 )
Comput. Biol. Med. - Sparse Manifold Clustering and Embedding to discriminate gene expression profiles of glioblastoma and meningioma tumors. ( 0,642018486954202 )
Neural Comput - Refined rademacher chaos complexity bounds with applications to the multikernel learning problem. ( 0,640257040581503 )
IEEE Trans Pattern Anal Mach Intell - Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-scale Image Retrieval. ( 0,630342405693831 )
IEEE Trans Pattern Anal Mach Intell - Learning Categories from Few Examples with Multi Model Knowledge Transfer. ( 0,625334698460502 )
IEEE Trans Image Process - Manifold regularized multitask learning for semi-supervised multilabel image classification. ( 0,625257494420729 )
J. Comput. Biol. - Finding alternative expression quantitative trait loci by exploring sparse model space. ( 0,624872453792001 )
Neural Comput - Online learning with (multiple) kernels: a review. ( 0,624727321100901 )
Neural Comput - Computing sparse representations of multidimensional signals using Kronecker bases. ( 0,620898118468631 )
IEEE Trans Neural Netw Learn Syst - Learning With Mixed Hard/Soft Pointwise Constraints. ( 0,619912827913956 )
Int J Neural Syst - Aggregation of sparse linear discriminant analyses for event-related potential classification in brain-computer interface. ( 0,618414723958658 )
IEEE Trans Pattern Anal Mach Intell - Consistent Latent Position Estimation and Vertex Classification for Random Dot Product Graphs. ( 0,611953418968296 )
IEEE Trans Image Process - Visual classification with multitask joint sparse representation. ( 0,611313741095917 )
IEEE Trans Neural Netw Learn Syst - MTC: A Fast and Robust Graph-Based Transductive Learning Method. ( 0,608707393874943 )
IEEE Trans Neural Netw Learn Syst - Online Sequential Extreme Learning Machine With Kernels. ( 0,60517003332185 )
IEEE Trans Image Process - Grassmannian regularized structured multi-view embedding for image classification. ( 0,604661479374943 )
IEEE Trans Image Process - Incremental training of a detector using online sparse eigendecomposition. ( 0,602118542388169 )
Neural Comput - Adaptive multiclass classification for brain computer interfaces. ( 0,594027029700209 )
IEEE Trans Image Process - Multiple-kernel, multiple-instance similarity features for efficient visual object detection. ( 0,594001964739769 )
J Chem Inf Model - Atom environment kernels on molecules. ( 0,592805936536201 )
J. Comput. Biol. - The approximability of shortest path-based graph orientations of protein-protein interaction networks. ( 0,589635107186749 )
IEEE Trans Vis Comput Graph - Flow Visualization with Quantified Spatial and Temporal Errors Using Edge Maps. ( 0,586545448505612 )
Neural Comput - Reduction from cost-sensitive ordinal ranking to weighted binary classification. ( 0,586076022617863 )
IEEE Trans Neural Netw Learn Syst - An incremental design of radial basis function networks. ( 0,584718168549754 )
IEEE Trans Image Process - Artistic image analysis using graph-based learning approaches. ( 0,583530778176779 )
J Biomed Inform - Incremental Gaussian Discriminant Analysis based on Graybill and Deal weighted combination of estimators for brain tumour diagnosis. ( 0,581707646110341 )
IEEE Trans Pattern Anal Mach Intell - Learning with Box Kernels. ( 0,581352909708889 )
IEEE Trans Pattern Anal Mach Intell - Trinary-Projection Trees for Approximate Nearest Neighbor Search. ( 0,580666225312995 )
IEEE Trans Pattern Anal Mach Intell - C^4: Exploring Multiple Solutions in Graphical Models by Cluster Sampling. ( 0,580620894016133 )
Neural Comput - Representing objects, relations, and sequences. ( 0,578821078527334 )
IEEE Trans Image Process - Geodesic propagation for semantic labeling. ( 0,577364789889045 )
J Biomed Inform - A medical diagnostic tool based on radial basis function classifiers and evolutionary simulated annealing. ( 0,576087256752154 )
Neural Comput - Multiple spectral kernel learning and a gaussian complexity computation. ( 0,576041479011638 )
IEEE Trans Image Process - Discriminative shared Gaussian processes for multiview and view-invariant facial expression recognition. ( 0,576021645214213 )
Comput Methods Programs Biomed - Design of fuzzy classifier for diabetes disease using Modified Artificial Bee Colony algorithm. ( 0,575830092745013 )
IEEE Trans Image Process - Edge-preserving image regularization based on morphological wavelets and dyadic trees. ( 0,575126952416605 )
IEEE Trans Pattern Anal Mach Intell - Distance-Based Image Classification: Generalizing to New Classes at Near Zero Cost. ( 0,573779027168234 )
Neural Comput - Guaranteed classification via regularized similarity learning. ( 0,572745478530883 )
IEEE Trans Pattern Anal Mach Intell - Feature Selection and Kernel Learning for Local Learning-Based Clustering. ( 0,572215801063269 )
Artif Intell Med - A fuzzy-based data transformation for feature extraction to increase classification performance with small medical data sets. ( 0,571464934916125 )
IEEE Trans Neural Netw Learn Syst - A one-class kernel fisher criterion for outlier detection. ( 0,569929358395944 )
IEEE Trans Image Process - Structured max-margin learning for inter-related classifier training and multilabel image annotation. ( 0,569276079199991 )
IEEE Trans Pattern Anal Mach Intell - Label Consistent K-SVD: Learning A Discriminative Dictionary for Recognition. ( 0,56836857411486 )
J Med Syst - 3D matrix pattern based Support Vector Machines for identifying pulmonary cancer in CT scanned images. ( 0,56813147123417 )
Comput. Biol. Med. - Identification of epilepsy stages from ECoG using genetic programming classifiers. ( 0,566525053102874 )
J Am Med Inform Assoc - Missing values in deduplication of electronic patient data. ( 0,566363130656645 )
Neural Comput - U-processes and preference learning. ( 0,565960311878333 )
IEEE Trans Pattern Anal Mach Intell - Latent Dirichlet Allocation Models for Image Classification. ( 0,565730750491152 )
Brief. Bioinformatics - A bioinformatician's guide to the forefront of suffix array construction algorithms. ( 0,565047124239727 )
Neural Comput - Foundations of support constraint machines. ( 0,564477746183152 )
IEEE Trans Neural Netw Learn Syst - Multitask Classification Hypothesis Space With Improved Generalization Bounds. ( 0,564413509963464 )
Comput Biol Chem - Classification of splice-junction sequences via weighted position specific scoring approach. ( 0,564141215608922 )
IEEE Trans Neural Netw Learn Syst - Comparison of l1-Norm SVR and Sparse Coding Algorithms for Linear Regression. ( 0,563888888888889 )
Neural Comput - Multilabel classification with principal label space transformation. ( 0,56334946885745 )
IEEE Trans Pattern Anal Mach Intell - Good Practice in Large-Scale Learning for Image Classification. ( 0,563156900508632 )
Methods Inf Med - Simulation of range imaging-based estimation of respiratory lung motion. Influence of noise, signal dimensionality and sampling patterns. ( 0,562471333182977 )
IEEE Trans Image Process - Random forest construction with robust semisupervised node splitting. ( 0,562186950989574 )
IEEE Trans Neural Netw Learn Syst - Semi-supervised domain adaptation on manifolds. ( 0,56160372459299 )
IEEE Trans Vis Comput Graph - Animating Wrinkles by Example on Non-Skinned Cloth. ( 0,561111111111111 )
Comput Biol Chem - A hyper-heuristic for the Longest Common Subsequence problem. ( 0,560754020162725 )
IEEE Trans Neural Netw Learn Syst - Partially shared latent factor learning with multiview data. ( 0,559670496129442 )
Int J Neural Syst - Structurally enhanced incremental neural learning for image classification with subgraph extraction. ( 0,55917381081503 )
IEEE J Biomed Health Inform - Service-oriented medical system for supporting decisions with missing and imbalanced data. ( 0,558657698766644 )
IEEE Trans Neural Netw Learn Syst - Scalable Nonparametric Low-Rank Kernel Learning Using Block Coordinate Descent. ( 0,55744939405271 )
IEEE Trans Image Process - Minimization of monotonically levelable higher order MRF energies via graph cuts. ( 0,557421790375761 )
Comput Math Methods Med - Particle system based adaptive sampling on spherical parameter space to improve the MDL method for construction of statistical shape models. ( 0,557163243979577 )
IEEE Trans Image Process - Tensor learning for regression. ( 0,556378029968644 )
IEEE Trans Image Process - Active learning for solving the incomplete data problem in facial age classification by the furthest nearest-neighbor criterion. ( 0,556227906989351 )
J. Comput. Biol. - A polynomial-time algorithm computing lower and upper bounds of the rooted subtree prune and regraft distance. ( 0,555544396508365 )
IEEE Trans Image Process - Double shrinking sparse dimension reduction. ( 0,55528580290282 )
Neural Comput - Incremental slow feature analysis: adaptive low-complexity slow feature updating from high-dimensional input streams. ( 0,554183246611815 )
Neural Comput - An efficient learning procedure for deep Boltzmann machines. ( 0,551690257225642 )
Comput. Biol. Med. - Forest classification trees and forest support vector machines algorithms: Demonstration using microarray data. ( 0,551490979250732 )
Comput Math Methods Med - On multilabel classification methods of incompletely labeled biomedical text data. ( 0,55067061400694 )
J Med Syst - 3D similarity-dissimilarity plot for high dimensional data visualization in the context of biomedical pattern classification. ( 0,549892939937401 )
IEEE Trans Image Process - Real-time probabilistic covariance tracking with efficient model update. ( 0,549700952022002 )
Neural Comput - Learning with boundary conditions. ( 0,549488872436242 )
Artif Intell Med - A classifier ensemble approach for the missing feature problem. ( 0,547459211832297 )
Neural Comput - Recurrent kernel machines: computing with infinite echo state networks. ( 0,546717758824896 )
IEEE Trans Image Process - An automatic graph-based approach for artery/vein classification in retinal images. ( 0,546585102487804 )
IEEE Trans Neural Netw Learn Syst - On recursive edit distance kernels with application to time series classification. ( 0,545314398352714 )
J Biomed Inform - A machine-learned knowledge discovery method for associating complex phenotypes with complex genotypes. Application to pain. ( 0,544444444444444 )
IEEE Trans Image Process - Contextual kernel and spectral methods for learning the semantics of images. ( 0,544335818733606 )
J Chem Inf Model - Note on naive Bayes based on binary descriptors in cheminformatics. ( 0,544333728527862 )
Artif Intell Med - Multi-test decision tree and its application to microarray data classification. ( 0,54365408515872 )
Methods Inf Med - The evolution of boosting algorithms. From machine learning to statistical modelling. ( 0,542753260871387 )