IEEE Trans Image Process - Human motion tracking by temporal-spatial local gaussian process experts.

Tópicos

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

Resumo

Human pose estimation via motion tracking systems can be considered as a regression problem within a discriminative framework. It is always a challenging task to model the mapping from observation space to state space because of the high-dimensional characteristic in the multimodal conditional distribution. In order to build the mapping, existing techniques usually involve a large set of training samples in the learning process which are limited in their capability to deal with multimodality. We propose, in this work, a novel online sparse Gaussian Process (GP) regression model to recover 3-D human motion in monocular videos. Particularly, we investigate the fact that for a given test input, its output is mainly determined by the training samples potentially residing in its local neighborhood and defined in the unified input-output space. This leads to a local mixture GP experts system composed of different local GP experts, each of which dominates a mapping behavior with the specific covariance function adapting to a local region. To handle the multimodality, we combine both temporal and spatial information therefore to obtain two categories of local experts. The temporal and spatial experts are integrated into a seamless hybrid system, which is automatically self-initialized and robust for visual tracking of nonlinear human motion. Learning and inference are extremely efficient as all the local experts are defined online within very small neighborhoods. Extensive experiments on two real-world databases, HumanEva and PEAR, demonstrate the effectiveness of our proposed model, which significantly improve the performance of existing models.

Resumo Limpo

human pose estim via motion track system can consid regress problem within discrimin framework alway challeng task model map observ space state space highdimension characterist multimod condit distribut order build map exist techniqu usual involv larg set train sampl learn process limit capabl deal multimod propos work novel onlin spars gaussian process gp regress model recov d human motion monocular video particular investig fact given test input output main determin train sampl potenti resid local neighborhood defin unifi inputoutput space lead local mixtur gp expert system compos differ local gp expert domin map behavior specif covari function adapt local region handl multimod combin tempor spatial inform therefor obtain two categori local expert tempor spatial expert integr seamless hybrid system automat selfiniti robust visual track nonlinear human motion learn infer extrem effici local expert defin onlin within small neighborhood extens experi two realworld databas humaneva pear demonstr effect propos model signific improv perform exist model

Resumos Similares

IEEE Trans Pattern Anal Mach Intell - Efficient Subframe Video Alignment using Short Descriptors. ( 0,738869049153006 )
IEEE Trans Image Process - Learning dynamic hybrid Markov random field for image labeling. ( 0,681914576861671 )
IEEE Trans Image Process - Automatic dynamic texture segmentation using local descriptors and optical flow. ( 0,675326611328072 )
IEEE Trans Pattern Anal Mach Intell - Learning Actionlet Ensemble for 3D Human Action Recognition. ( 0,675023264411093 )
IEEE Trans Pattern Anal Mach Intell - Object Tracking by Oversampling Local Features. ( 0,672897801787151 )
IEEE Trans Pattern Anal Mach Intell - Anomaly Detection and Localization in Crowded Scenes. ( 0,672392836505689 )
IEEE Trans Pattern Anal Mach Intell - A Physics-Based Analysis of Image Appearance Models. ( 0,672196897456689 )
IEEE Trans Image Process - Occlusion-aware motion layer extraction under large interframe motions. ( 0,660638580649473 )
IEEE Trans Image Process - Non-uniform deblurring in HDR image reconstruction. ( 0,657596874507821 )
IEEE Trans Pattern Anal Mach Intell - Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition. ( 0,657541227394439 )
IEEE Trans Pattern Anal Mach Intell - Layered Graphical Models for Tracking Partially Occluded Objects. ( 0,657174427862783 )
IEEE Trans Image Process - Transferring visual prior for online object tracking. ( 0,651556112490092 )
Neural Comput - A model of motion transparency processing with local center-surround interactions and feedback. ( 0,645040933304135 )
IEEE Trans Image Process - Video tonal stabilization via color states smoothing. ( 0,644163804298107 )
IEEE Trans Pattern Anal Mach Intell - Scene-Specific Pedestrian Detection for Static Video Surveillance. ( 0,643199938269551 )
IEEE Trans Pattern Anal Mach Intell - The Applicability of Spatiotemporal Oriented Energy Features to Region Tracking. ( 0,64237100318238 )
IEEE Trans Image Process - Real-time probabilistic covariance tracking with efficient model update. ( 0,641310295791145 )
IEEE Trans Image Process - Discovering thematic objects in image collections and videos. ( 0,630039802383658 )
IEEE Trans Image Process - Object tracking via partial least squares analysis. ( 0,628351951375889 )
IEEE Trans Pattern Anal Mach Intell - A Bag-of-Features Framework to Classify Time Series. ( 0,626646479793143 )
IEEE Trans Image Process - Fine-tuning regression forests votes for object alignment in the wild. ( 0,624737904520916 )
IEEE Trans Pattern Anal Mach Intell - Automatic Upright Adjustment of Photographs with Robust Camera Calibration. ( 0,624323057539112 )
IEEE Trans Image Process - Exploring visual and motion saliency for automatic video object extraction. ( 0,624305005130629 )
IEEE Trans Image Process - Pose-invariant face recognition using Markov random fields. ( 0,623387735828762 )
IEEE Trans Pattern Anal Mach Intell - 3D Traffic Scene Understanding from Movable Platforms. ( 0,622548427370995 )
IEEE Trans Pattern Anal Mach Intell - Camera Localization using Trajectories and Maps. ( 0,621630642141625 )
IEEE Trans Pattern Anal Mach Intell - Semi-Supervised Video Segmentation Using Tree Structured Graphical Models. ( 0,619828949181951 )
IEEE Trans Image Process - Scale Adaptive Dictionary Learning. ( 0,619684038339534 )
IEEE Trans Pattern Anal Mach Intell - Unconstrained Pose-Invariant Face Recognition Using 3D Generic Elastic Models. ( 0,615653835125118 )
Comput Math Methods Med - The research and application of visual saliency and adaptive support vector machine in target tracking field. ( 0,61384049143706 )
IEEE Trans Image Process - Low-resolution face tracker robust to illumination variations. ( 0,613587979332625 )
IEEE Trans Pattern Anal Mach Intell - Spatially-Constrained Similarity Measure for Large-Scale Object Retrieval. ( 0,611832023474512 )
IEEE Trans Image Process - Representing and retrieving video shots in human-centric brain imaging space. ( 0,609450843570601 )
IEEE Trans Image Process - Track creation and deletion framework for long-term online multiface tracking. ( 0,609435591638429 )
IEEE Trans Pattern Anal Mach Intell - Robust Object Tracking with Online Multiple Instance Learning. ( 0,607652891122057 )
IEEE Trans Image Process - Object tracking and target reacquisition based on 3-D range data for moving vehicles. ( 0,606248359985099 )
IEEE Trans Vis Comput Graph - Live Speech Driven Head-and-Eye Motion Generators. ( 0,604217199931482 )
IEEE Trans Image Process - Cluster-based distributed face tracking in camera networks. ( 0,602069256680277 )
IEEE Trans Image Process - Human gait recognition using patch distribution feature and locality-constrained group sparse representation. ( 0,601217405688417 )
IEEE Trans Image Process - Multilayer surface albedo for face recognition with reference images in bad lighting conditions. ( 0,599915346450785 )
IEEE Trans Pattern Anal Mach Intell - Pose-Robust Recognition of Low-Resolution Face Images. ( 0,598838024550667 )
IEEE Trans Image Process - Task-dependent visual-codebook compression. ( 0,597944421002318 )
IEEE Trans Pattern Anal Mach Intell - Multiple Hypothesis Tracking for Cluttered Biological Image Sequences. ( 0,597908920679116 )
IEEE Trans Vis Comput Graph - Lagrangian Texture Advection: Preserving both Spectrum and Velocity Field. ( 0,59767635900563 )
J Am Med Inform Assoc - Coreference analysis in clinical notes: a multi-pass sieve with alternate anaphora resolution modules. ( 0,596968292802015 )
IEEE Trans Image Process - Integrating graph partitioning and matching for trajectory analysis in video surveillance. ( 0,595599644351497 )
IEEE Trans Image Process - Hierarchical colorant-based direct binary search halftoning. ( 0,594518074046221 )
IEEE Trans Vis Comput Graph - Video-based Crowd Synthesis. ( 0,59382736635551 )
IEEE Trans Pattern Anal Mach Intell - Structured Time Series Analysis for Human Action Segmentation and Recognition. ( 0,591476411039766 )
IEEE Trans Pattern Anal Mach Intell - Highly Non-Rigid Object Tracking via Patch-based Dynamic Appearance Modeling. ( 0,590649346970691 )
IEEE Trans Neural Netw Learn Syst - Learning a Probabilistic Topology Discovering Model for Scene Categorization. ( 0,589638626511217 )
IEEE Trans Neural Netw Learn Syst - Asynchronous Event-Based Multikernel Algorithm for High-Speed Visual Features Tracking. ( 0,588636923367111 )
Neural Comput - Learning invariance from natural images inspired by observations in the primary visual cortex. ( 0,588460938753594 )
Neural Comput - Invariant object recognition and pose estimation with slow feature analysis. ( 0,587554207313959 )
Med Biol Eng Comput - 3D spinal motion analysis during staircase walking using an ambulatory inertial and magnetic sensing system. ( 0,587442591543911 )
Int J Med Robot - Hand-eye and radial distortion calibration for rigid endoscopes. ( 0,585836867145588 )
IEEE Trans Image Process - Computational cameras: convergence of optics and processing. ( 0,585237118252225 )
IEEE Trans Image Process - Toward naturalistic 2D-to-3D conversion. ( 0,584972698543393 )
Comput Math Methods Med - Image tracking for the high similarity drug tablets based on light intensity reflective energy and artificial neural network. ( 0,584942409914727 )
J Am Med Inform Assoc - Automatic lymphoma classification with sentence subgraph mining from pathology reports. ( 0,58353001876991 )
IEEE Trans Image Process - Video object tracking in the compressed domain using spatio-temporal Markov random fields. ( 0,58274516589756 )
IEEE Trans Pattern Anal Mach Intell - Meta-Recognition: The Theory and Practice of Recognition Score Analysis. ( 0,582182383427612 )
IEEE Trans Pattern Anal Mach Intell - Combining Multiple Dynamic Models and Deep Learning Architectures for Tracking the Left Ventricle Endocardium in Ultrasound Data. ( 0,580506484525852 )
IEEE Trans Image Process - Blur and illumination robust face recognition via set-theoretic characterization. ( 0,578956668977412 )
IEEE Trans Image Process - Weighted color and texture sample selection for image matting. ( 0,577942917763185 )
IEEE Trans Image Process - Geodesic propagation for semantic labeling. ( 0,576741971621339 )
IEEE Trans Image Process - Robust video hashing via multilinear subspace projections. ( 0,576637931934045 )
IEEE Trans Pattern Anal Mach Intell - Richardson-Lucy Deblurring for Scenes under a Projective Motion Path. ( 0,576174327461487 )
IEEE Trans Vis Comput Graph - 6-DoF Pose Estimation Using a Projected Dense Dot Pattern. ( 0,575558256848647 )
IEEE Trans Image Process - Sparse representation with kernels. ( 0,575362914058022 )
IEEE Trans Image Process - Interframe coding of feature descriptors for mobile augmented reality. ( 0,575032184234068 )
IEEE Trans Image Process - Removing motion blur with space-time processing. ( 0,573818460990544 )
IEEE Trans Vis Comput Graph - Animating Wrinkles by Example on Non-Skinned Cloth. ( 0,573628664064794 )
Methods Inf Med - Censoring weighted separate-and-conquer rule induction from survival data. ( 0,573511186398425 )
IEEE Trans Pattern Anal Mach Intell - Describable Visual Attributes for Face Verification and Image Search. ( 0,57260567519427 )
IEEE Trans Image Process - Depth from motion and optical blur with an unscented Kalman filter. ( 0,572261654927188 )
IEEE Trans Pattern Anal Mach Intell - CENTRIST: A Visual Descriptor for Scene Categorization. ( 0,57188609511892 )
Comput Math Methods Med - A biological hierarchical model based underwater moving object detection. ( 0,571602796812166 )
Med Biol Eng Comput - Development and validation of a machine learning algorithm and hybrid system to predict the need for life-saving interventions in trauma patients. ( 0,571436446798616 )
IEEE Trans Image Process - Estimation of sunlight direction using 3D object models. ( 0,570004573527618 )
IEEE Trans Neural Netw Learn Syst - On Equivalence of FIS and ELM for Interpretable Rule-Based Knowledge Representation. ( 0,569500957581707 )
IEEE Trans Pattern Anal Mach Intell - Robust Facial Feature Tracking Using Shape-Constrained Multiresolution-Selected Linear Predictors. ( 0,569264630858294 )
Comput. Biol. Med. - Serial slice image segmentation of digital human based on adaptive geometric active contour tracking. ( 0,569123830368093 )
IEEE Trans Image Process - Unequal protection of video data according to slice relevance. ( 0,56832387537836 )
IEEE Trans Pattern Anal Mach Intell - Modeling Bidirectional Texture Functions with Multivariate Spherical Radial Basis Functions. ( 0,567914308994193 )
IEEE Trans Pattern Anal Mach Intell - Trainable Convolution Filters and Their Application to Face Recognition. ( 0,565097699673722 )
IEEE Trans Image Process - Temporal frequency of flickering-distortion optimized video halftoning for electronic paper. ( 0,564695348286799 )
IEEE Trans Image Process - Cooperative sparse representation in two opposite directions for semi-supervised image annotation. ( 0,562533350058263 )
IEEE Trans Image Process - A unified framework for multioriented text detection and recognition. ( 0,562429713548567 )
IEEE Trans Image Process - Semisupervised multiview distance metric learning for cartoon synthesis. ( 0,562158070476713 )
Comput. Biol. Med. - Computer-aided diagnosis system based on fuzzy logic for breast cancer categorization. ( 0,561986097432832 )
IEEE Trans Image Process - A novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. ( 0,559984963568594 )
IEEE Trans Pattern Anal Mach Intell - Facial Age Estimation by Learning from Label Distributions. ( 0,559937362320788 )
IEEE Trans Pattern Anal Mach Intell - Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation. ( 0,559604623091493 )
IEEE Trans Pattern Anal Mach Intell - Multi-Commodity Network Flow for Tracking Multiple People. ( 0,558811185579863 )
IEEE Trans Image Process - Segmentation and estimation of spatially varying illumination. ( 0,558182873901701 )
IEEE Trans Image Process - Online object tracking with sparse prototypes. ( 0,557568768519306 )
IEEE Trans Image Process - Maintaining temporal coherence in video retargeting using mosaic-guided scaling. ( 0,557201716645348 )
IEEE Trans Image Process - Camera constraint-free view-based 3-D object retrieval. ( 0,555509663236514 )
IEEE Trans Image Process - Coupled kernel embedding for low resolution face image recognition. ( 0,554005636166224 )