IEEE Trans Neural Netw Learn Syst - Learning a Probabilistic Topology Discovering Model for Scene Categorization.

Tópicos

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

Resumo

A recent advance in scene categorization prefers a topological based modeling to capture the existence and relationships among different scene components. To that effect, local features are typically used to handle photographing variances such as occlusions and clutters. However, in many cases, the local features alone cannot well capture the scene semantics since they are extracted from tiny regions (e.g., 4?4 patches) within an image. In this paper, we mine a discriminative topology and a low-redundant topology from the local descriptors under a probabilistic perspective, which are further integrated into a boosting framework for scene categorization. In particular, by decomposing a scene image into basic components, a graphlet model is used to describe their spatial interactions. Accordingly, scene categorization is formulated as an intergraphlet matching problem. The above procedure is further accelerated by introducing a probabilistic based representative topology selection scheme that makes the pairwise graphlet comparison trackable despite their exponentially increasing volumes. The selected graphlets are highly discriminative and independent, characterizing the topological characteristics of scene images. A weak learner is subsequently trained for each topology, which are boosted together to jointly describe the scene image. In our experiment, the visualized graphlets demonstrate that the mined topological patterns are representative to scene categories, and our proposed method beats state-of-the-art models on five popular scene data sets.

Resumo Limpo

recent advanc scene categor prefer topolog base model captur exist relationship among differ scene compon effect local featur typic use handl photograph varianc occlus clutter howev mani case local featur alon well captur scene semant sinc extract tini region eg patch within imag paper mine discrimin topolog lowredund topolog local descriptor probabilist perspect integr boost framework scene categor particular decompos scene imag basic compon graphlet model use describ spatial interact accord scene categor formul intergraphlet match problem procedur acceler introduc probabilist base repres topolog select scheme make pairwis graphlet comparison trackabl despit exponenti increas volum select graphlet high discrimin independ character topolog characterist scene imag weak learner subsequ train topolog boost togeth joint describ scene imag experi visual graphlet demonstr mine topolog pattern repres scene categori propos method beat stateoftheart model five popular scene data set

Resumos Similares

IEEE J Biomed Health Inform - Local object patterns for the representation and classification of colon tissue images. ( 0,771043310650635 )
IEEE Trans Image Process - Discovering thematic objects in image collections and videos. ( 0,768357742545219 )
IEEE Trans Image Process - Discovering discriminative graphlets for aerial image categories recognition. ( 0,760707389526407 )
IEEE Trans Image Process - Scale- and rotation-invariant local binary pattern using scale-adaptive texton and subuniform-based circular shift. ( 0,75471046458585 )
IEEE Trans Pattern Anal Mach Intell - CENTRIST: A Visual Descriptor for Scene Categorization. ( 0,74860510295112 )
IEEE Trans Pattern Anal Mach Intell - Spatially-Constrained Similarity Measure for Large-Scale Object Retrieval. ( 0,746345261926409 )
IEEE Trans Image Process - Human gait recognition using patch distribution feature and locality-constrained group sparse representation. ( 0,74145877768032 )
IEEE Trans Image Process - A probabilistic approach to realistic face synthesis with a single uncalibrated image. ( 0,739719848226533 )
IEEE Trans Image Process - Color texture classification using shortest paths in graphs. ( 0,726963329960365 )
IEEE Trans Image Process - Anisotropic morphological filters with spatially-variant structuring elements based on image-dependent gradient fields. ( 0,722530061271497 )
IEEE Trans Image Process - Combining LBP difference and feature correlation for texture description. ( 0,719639952110375 )
IEEE Trans Image Process - Toward a unified color space for perception-based image processing. ( 0,718488252832381 )
IEEE Trans Image Process - Low-resolution face tracker robust to illumination variations. ( 0,717839959893335 )
IEEE Trans Pattern Anal Mach Intell - LDAHash: Improved Matching with Smaller Descriptors. ( 0,716543032461885 )
IEEE Trans Image Process - Multilinear supervised neighborhood embedding of a local descriptor tensor for scene/object recognition. ( 0,71415139943638 )
IEEE Trans Image Process - Representing and retrieving video shots in human-centric brain imaging space. ( 0,712734064420076 )
IEEE Trans Image Process - A new hybrid method for image approximation using the easy path wavelet transform. ( 0,712138614268702 )
IEEE Trans Image Process - Sparse representation with kernels. ( 0,709954027747657 )
IEEE Trans Image Process - An attribute-assisted reranking model for web image search. ( 0,708948264726999 )
IEEE Trans Pattern Anal Mach Intell - Pose-Robust Recognition of Low-Resolution Face Images. ( 0,70647347891168 )
IEEE Trans Image Process - High-order local spatial context modeling by spatialized random forest. ( 0,704673879060255 )
Comput. Biol. Med. - Texture feature extraction based on a uniformity estimation method for local brightness and structure in chest CT images. ( 0,702646485020762 )
IEEE Trans Image Process - Robust face representation using hybrid spatial feature interdependence matrix. ( 0,702618160650472 )
IEEE Trans Image Process - Adaptive dictionary learning in sparse gradient domain for image recovery. ( 0,702495215222288 )
IEEE Trans Pattern Anal Mach Intell - From Bits to Images: Inversion of Local Binary Descriptors. ( 0,702156417502856 )
IEEE Trans Image Process - Fusing local patterns of Gabor magnitude and phase for face recognition. ( 0,701821184597237 )
IEEE Trans Image Process - Hyperspectral image segmentation using a new spectral unmixing-based binary partition tree representation. ( 0,699489145434495 )
IEEE Trans Image Process - Image editing with spatiograms transfer. ( 0,698531189003662 )
IEEE Trans Image Process - A novel local pattern descriptor--local vector pattern in high-order derivative space for face recognition. ( 0,698387051753949 )
IEEE Trans Image Process - Multilayer surface albedo for face recognition with reference images in bad lighting conditions. ( 0,696473115998761 )
IEEE Trans Image Process - USB: ultrashort binary descriptor for fast visual matching and retrieval. ( 0,695938215848597 )
IEEE Trans Image Process - Steganography using reversible texture synthesis. ( 0,695402261578341 )
IEEE Trans Image Process - Occlusion-aware motion layer extraction under large interframe motions. ( 0,694924821050768 )
IEEE Trans Image Process - Wavelet domain multifractal analysis for static and dynamic texture classification. ( 0,69398282042399 )
IEEE Trans Image Process - An affine symmetric image model and its applications. ( 0,692029476353995 )
IEEE Trans Image Process - Face recognition by exploring information jointly in space, scale and orientation. ( 0,691166572953419 )
IEEE Trans Image Process - Color local texture features for color face recognition. ( 0,687933452879514 )
IEEE Trans Image Process - Adaptive color feature extraction based on image color distributions. ( 0,687715920577242 )
IEEE Trans Pattern Anal Mach Intell - Local Difference Binary for Ultra-fast and Distinctive Feature Description. ( 0,684563402284917 )
IEEE Trans Image Process - Subspace-based discrete transform encoded local binary patterns representations for robust periocular matching on NIST's face recognition grand challenge. ( 0,68442314604801 )
IEEE Trans Image Process - HSOG: a novel local image descriptor based on histograms of the second-order gradients. ( 0,683466791101838 )
IEEE Trans Image Process - Video tonal stabilization via color states smoothing. ( 0,682866655919714 )
Neural Comput - Learning a generative model of images by factoring appearance and shape. ( 0,682592424808671 )
IEEE Trans Image Process - Image classification via object-aware holistic superpixel selection. ( 0,680828780311055 )
IEEE Trans Pattern Anal Mach Intell - Scalable Face Image Retrieval with Identity-Based Quantization and Multireference Reranking. ( 0,678813890134892 )
IEEE Trans Image Process - Scale- and affine-invariant fan feature. ( 0,678796182295608 )
IEEE Trans Vis Comput Graph - Reconstructing the Curve-Skeletons of 3D Shapes Using the Visual Hull. ( 0,67683466239744 )
IEEE Trans Image Process - Very low resolution face recognition problem. ( 0,676016108153512 )
IEEE Trans Image Process - Scale-invariant features for 3-D mesh models. ( 0,675093229923841 )
IEEE Trans Image Process - Local color vector binary patterns from multichannel face images for face recognition. ( 0,674946782380482 )
IEEE Trans Pattern Anal Mach Intell - The Applicability of Spatiotemporal Oriented Energy Features to Region Tracking. ( 0,674678921856355 )
IEEE Trans Pattern Anal Mach Intell - Learning Discriminant Face Descriptor. ( 0,674458101434079 )
Comput Math Methods Med - A machine learning approach for specification of spinal cord injuries using fractional anisotropy values obtained from diffusion tensor images. ( 0,674123267623727 )
IEEE Trans Image Process - Geodesic invariant feature: a local descriptor in depth. ( 0,673886843810494 )
IEEE Trans Image Process - Non-uniform deblurring in HDR image reconstruction. ( 0,672789136434585 )
IEEE Trans Image Process - Common feature discriminant analysis for matching infrared face images to optical face images. ( 0,672216084062832 )
IEEE Trans Image Process - Edge-SIFT: discriminative binary descriptor for scalable partial-duplicate mobile search. ( 0,671179557808188 )
IEEE Trans Image Process - Color constancy by category correlation. ( 0,67105525954471 )
IEEE Trans Image Process - Halftone-image security improving using overall minimal-error searching. ( 0,670048139481531 )
IEEE Trans Image Process - Efficient texture image retrieval using copulas in a Bayesian framework. ( 0,669736863532781 )
IEEE Trans Image Process - Local energy pattern for texture classification using self-adaptive quantization thresholds. ( 0,669587553652185 )
IEEE Trans Image Process - Tensor discriminant color space for face recognition. ( 0,668421110806913 )
IEEE Trans Image Process - Sparse texture active contour. ( 0,668418265712258 )
IEEE Trans Pattern Anal Mach Intell - Transform-Invariant PCA: A Unified Approach to Fully Automatic Face Alignment, Representation, and Recognition. ( 0,668392925241556 )
IEEE Trans Pattern Anal Mach Intell - Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin. ( 0,668224829659672 )
IEEE Trans Pattern Anal Mach Intell - A Two-Stage Framework for 3D Face Reconstruction From RGBD Images. ( 0,667075024616684 )
IEEE Trans Image Process - Robust face recognition with structurally incoherent low-rank matrix decomposition. ( 0,66649573964115 )
IEEE Trans Image Process - Combined invariants to similarity transformation and to blur using orthogonal Zernike moments. ( 0,665973022644035 )
IEEE Trans Image Process - Face recognition system using multiple face model of hybrid Fourier feature under uncontrolled illumination variation. ( 0,66537628953353 )
IEEE Trans Pattern Anal Mach Intell - Intrinsic Image Decomposition Using a Sparse Representation of Reflectance. ( 0,664511916338994 )
IEEE Trans Image Process - Coupled binary embedding for large-scale image retrieval. ( 0,663918438575841 )
IEEE Trans Image Process - Normalization of face illumination based on large-and small-scale features. ( 0,663678709878522 )
IEEE Trans Image Process - Enhanced local texture feature sets for face recognition under difficult lighting conditions. ( 0,663218595898863 )
IEEE Trans Image Process - Semantic pyramids for gender and action recognition. ( 0,662319604045845 )
IEEE Trans Image Process - Shape vocabulary: a robust and efficient shape representation for shape matching. ( 0,662066359100514 )
IEEE Trans Pattern Anal Mach Intell - Learning Hybrid Image Templates (HIT) by Information Projection. ( 0,661812350067531 )
IEEE Trans Pattern Anal Mach Intell - What Makes a Photograph Memorable? ( 0,661639730807077 )
IEEE Trans Image Process - Color constancy for multiple light sources. ( 0,660688560731237 )
IEEE Trans Vis Comput Graph - Lagrangian Texture Advection: Preserving both Spectrum and Velocity Field. ( 0,659478702268851 )
IEEE Trans Image Process - Structured sparse error coding for face recognition with occlusion. ( 0,658866470090392 )
IEEE Trans Image Process - Hierarchical colorant-based direct binary search halftoning. ( 0,658660756455751 )
IEEE Trans Image Process - Completed local binary count for rotation invariant texture classification. ( 0,658608767016888 )
IEEE Trans Pattern Anal Mach Intell - Statistical 3D Shape Analysis by Local Generative Descriptors. ( 0,657738178259368 )
IEEE Trans Image Process - Large-margin Learning of Compact Binary Image Encodings. ( 0,657704789687136 )
IEEE Trans Image Process - Rigid-motion-invariant classification of 3-D textures. ( 0,657650500343463 )
J Med Syst - Comparison of several texture features for tumor detection in CE images. ( 0,657391973406216 )
IEEE Trans Image Process - A consensus-driven approach for structure and texture aware depth map upsampling. ( 0,656890587376512 )
IEEE Trans Image Process - Angular pattern and binary angular pattern for shape retrieval. ( 0,656640514544095 )
IEEE Trans Image Process - Scale-invariant features and polar descriptors in omnidirectional imaging. ( 0,656449727548418 )
Comput Methods Programs Biomed - Tensor based sparse decomposition of 3D shape for visual detection of mirror symmetry. ( 0,654629342731949 )
IEEE Trans Image Process - Boosting color feature selection for color face recognition. ( 0,653642023111595 )
IEEE Trans Pattern Anal Mach Intell - Efficient Subframe Video Alignment using Short Descriptors. ( 0,651168436018651 )
IEEE Trans Image Process - Face recognition using ensemble string matching. ( 0,650505414535734 )
IEEE Trans Image Process - Extracting multiple features in the CID color space for face recognition. ( 0,650310946882293 )
IEEE Trans Image Process - From local pixel structure to global image super-resolution: a new face hallucination framework. ( 0,650269008671785 )
IEEE Trans Image Process - Fast localization of the optic disc using projection of image features. ( 0,649934226531837 )
IEEE Trans Image Process - Content-based image retrieval using features extracted from halftoning-based block truncation coding. ( 0,64935673394217 )
IEEE Trans Image Process - Depth estimation of face images using the nonlinear least-squares model. ( 0,647923194501891 )
IEEE Trans Image Process - Depth from motion and optical blur with an unscented Kalman filter. ( 0,647579065804803 )
IEEE Trans Pattern Anal Mach Intell - Detailed 3D Representations for Object Recognition and Modeling. ( 0,647498770952573 )