IEEE Trans Image Process - Relevance of a feed-forward model of visual attention for goal-oriented and free-viewing tasks.

Tópicos

{ motion(1329) object(1292) video(1091) }
{ model(3480) simul(1196) paramet(876) }
{ method(1219) similar(1157) match(930) }
{ chang(1828) time(1643) increas(1301) }
{ general(901) number(790) one(736) }
{ model(2341) predict(2261) use(1141) }
{ first(2504) two(1366) second(1323) }
{ imag(2675) segment(2577) method(1081) }
{ control(1307) perform(991) simul(935) }
{ featur(1941) imag(1645) propos(1176) }
{ perform(999) metric(946) measur(919) }
{ can(981) present(881) function(850) }
{ result(1111) use(1088) new(759) }
{ treatment(1704) effect(941) patient(846) }
{ error(1145) method(1030) estim(1020) }
{ research(1085) discuss(1038) issu(1018) }
{ import(1318) role(1303) understand(862) }
{ use(1733) differ(960) four(931) }
{ model(3404) distribut(989) bayesian(671) }
{ imag(1057) registr(996) error(939) }
{ take(945) account(800) differ(722) }
{ assess(1506) score(1403) qualiti(1306) }
{ search(2224) databas(1162) retriev(909) }
{ data(3963) clinic(1234) research(1004) }
{ studi(1410) differ(1259) use(1210) }
{ system(1050) medic(1026) inform(1018) }
{ studi(1119) effect(1106) posit(819) }
{ sampl(1606) size(1419) use(1276) }
{ data(3008) multipl(1320) sourc(1022) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ use(2086) technolog(871) perceiv(783) }
{ use(976) code(926) identifi(902) }
{ drug(1928) target(777) effect(648) }
{ can(774) often(719) complex(702) }
{ imag(1947) propos(1133) code(1026) }
{ data(1737) use(1416) pattern(1282) }
{ 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) }
{ featur(3375) classif(2383) classifi(1994) }
{ imag(2830) propos(1344) filter(1198) }
{ network(2748) neural(1063) input(814) }
{ patient(2315) diseas(1263) diabet(1191) }
{ studi(2440) review(1878) systemat(933) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ framework(1458) process(801) describ(734) }
{ problem(2511) optim(1539) algorithm(950) }
{ learn(2355) train(1041) set(1003) }
{ concept(1167) ontolog(924) domain(897) }
{ clinic(1479) use(1117) guidelin(835) }
{ algorithm(1844) comput(1787) effici(935) }
{ extract(1171) text(1153) clinic(932) }
{ method(1557) propos(1049) approach(1037) }
{ data(1714) softwar(1251) tool(1186) }
{ design(1359) user(1324) use(1319) }
{ model(2220) cell(1177) simul(1124) }
{ care(1570) inform(1187) nurs(1089) }
{ method(984) reconstruct(947) comput(926) }
{ case(1353) use(1143) diagnosi(1136) }
{ howev(809) still(633) remain(590) }
{ risk(3053) factor(974) diseas(938) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ perform(1367) use(1326) method(1137) }
{ blood(1257) pressur(1144) flow(957) }
{ spatial(1525) area(1432) region(1030) }
{ 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) }
{ signal(2180) analysi(812) frequenc(800) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ gene(2352) biolog(1181) express(1162) }
{ activ(1138) subject(705) human(624) }
{ patient(1821) servic(1111) care(1106) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ structur(1116) can(940) graph(676) }
{ high(1669) rate(1365) level(1280) }
{ cancer(2502) breast(956) screen(824) }
{ implement(1333) system(1263) develop(1122) }
{ survey(1388) particip(1329) question(1065) }
{ estim(2440) model(1874) function(577) }
{ decis(3086) make(1611) patient(1517) }
{ 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 purely bottom-up model of visual attention is proposed and compared to five state-of-the-art models. The role of the low-level visual features is examined in two contexts. Two datasets are used: one containing data coming from an eye tracking experiment obtained in a free-viewing task and a second containing 5000 hand-label pictures (observers had to enclose the most visually interesting objects in a rectangle). The relevancy of the bottom-up models, i.e. the ability of a model to predict where the salient areas are located, is evaluated. Whatever the metrics and the datasets, the degree of similarity between predictions and ground truth is significantly above chance. The proposed model, resting on a small number of features, is shown to be a good predictor of the human visual fixations but also a good predictor of the objects chosen as interesting by observers. This study suggests that the low-level of visual features have a significant role in a free-viewing task but also in a high-level visual task, such as the choice of the object of interest in a complex visual scene. Another outcome concerns the viewing duration used in eye tracking experiments. Results suggest that this parameter is finally not as critical as one would expect.

Resumo Limpo

pure bottomup model visual attent propos compar five stateoftheart model role lowlevel visual featur examin two context two dataset use one contain data come eye track experi obtain freeview task second contain handlabel pictur observ enclos visual interest object rectangl relev bottomup model ie abil model predict salient area locat evalu whatev metric dataset degre similar predict ground truth signific chanc propos model rest small number featur shown good predictor human visual fixat also good predictor object chosen interest observ studi suggest lowlevel visual featur signific role freeview task also highlevel visual task choic object interest complex visual scene anoth outcom concern view durat use eye track experi result suggest paramet final critic one expect

Resumos Similares

IEEE Trans Image Process - Activity recognition using a mixture of vector fields. ( 0,815888666821965 )
IEEE Trans Image Process - What are we tracking: a unified approach of tracking and recognition. ( 0,793823301994835 )
IEEE Trans Pattern Anal Mach Intell - Recognition Using Specular Highlights. ( 0,790495522368869 )
IEEE Trans Image Process - Common and Innovative Visuals: A sparsity modeling framework for video. ( 0,787621613222989 )
IEEE Trans Image Process - Robust spatiotemporal matching of electronic slides to presentation videos. ( 0,787452748799455 )
IEEE Trans Pattern Anal Mach Intell - Highly Non-Rigid Object Tracking via Patch-based Dynamic Appearance Modeling. ( 0,785752352194542 )
IEEE Trans Vis Comput Graph - Robust Relocalization and Its Evaluation For Online Environment Map Construction. ( 0,782262944519076 )
IEEE Trans Image Process - Maintaining temporal coherence in video retargeting using mosaic-guided scaling. ( 0,781115086086715 )
IEEE Trans Image Process - Detecting abandoned objects with a moving camera. ( 0,780633858978702 )
IEEE Trans Image Process - A particle filtering framework for joint video tracking and pose estimation. ( 0,779492858818584 )
IEEE Trans Image Process - Object tracking and target reacquisition based on 3-D range data for moving vehicles. ( 0,779392655086795 )
Int J Neural Syst - Unsupervised markerless 3-DOF motion tracking in real time using a single low-budget camera. ( 0,774218440814964 )
IEEE Trans Image Process - Motion-aware gradient domain video composition. ( 0,770359526453523 )
IEEE Trans Image Process - Online camera-gyroscope autocalibration for cell phones. ( 0,76969156826067 )
IEEE Trans Vis Comput Graph - Compact Video Synopsis via Global Spatiotemporal Optimization. ( 0,769651181879821 )
IEEE Trans Image Process - Removing motion blur with space-time processing. ( 0,763858478058189 )
Int J Med Robot - An integrated approach to endoscopic instrument tracking for augmented reality applications in surgical simulation training. ( 0,760356365616297 )
IEEE Trans Image Process - Human object inpainting using manifold learning-based posture sequence estimation. ( 0,759085024601568 )
Neural Comput - Variation in the local motion statistics of real-life optic flow scenes. ( 0,75369732217881 )
IEEE Trans Image Process - Locally oriented optical flow computation. ( 0,753111351854481 )
Neural Comput - A neural circuit for robust time-to-contact estimation based on primate MST. ( 0,752701300879492 )
IEEE Trans Vis Comput Graph - Lighting System for Visual Perception Enhancement in Volume Rendering. ( 0,750973963031322 )
IEEE Trans Image Process - Adaptive online performance evaluation of video trackers. ( 0,750302608333464 )
IEEE Trans Pattern Anal Mach Intell - Segmentation of Moving Objects by Long Term Video Analysis. ( 0,749260038357796 )
Comput Methods Programs Biomed - Cell tracking in microscopic video using matching and linking of bipartite graphs. ( 0,749258590496363 )
IEEE Trans Image Process - Behavior subtraction. ( 0,747515368797468 )
IEEE Trans Image Process - Pose estimation with segmentation consistency. ( 0,746655457186356 )
IEEE Trans Image Process - Cooperative object tracking and composite event detection with wireless embedded smart cameras. ( 0,746118622952877 )
IEEE Trans Image Process - Robust online multiobject tracking with data association and track management. ( 0,744855256731662 )
IEEE Trans Neural Netw Learn Syst - Asynchronous Event-Based Multikernel Algorithm for High-Speed Visual Features Tracking. ( 0,74452775122351 )
IEEE Trans Pattern Anal Mach Intell - Animated Pose Templates for Modelling and Detecting Human Actions. ( 0,741049249743416 )
IEEE Trans Image Process - A semitransparency-based optical-flow method with a point trajectory model for particle-like video. ( 0,739597441288487 )
IEEE Trans Image Process - Joint random field model for all-weather moving vehicle detection. ( 0,737976351622747 )
IEEE Trans Image Process - A novel approach to FRUC using discriminant saliency and frame segmentation. ( 0,735737540006356 )
J Digit Imaging - Performing real-time interactive fiber tracking. ( 0,734053779675788 )
IEEE Trans Vis Comput Graph - 6-DoF Pose Estimation Using a Projected Dense Dot Pattern. ( 0,733522907077863 )
IEEE Trans Pattern Anal Mach Intell - Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion. ( 0,732058896395823 )
IEEE Trans Pattern Anal Mach Intell - A Prism-Mask System for Multispectral Video Acquisition. ( 0,731984023274724 )
IEEE Trans Image Process - Learning adaptive metric for robust visual tracking. ( 0,728982731830298 )
Neural Comput - Visual motion priors differ for infants and mothers. ( 0,728574903523784 )
IEEE Trans Image Process - Three-dimensional deformable-model-based localization and recognition of road vehicles. ( 0,727633415694492 )
IEEE Trans Image Process - Patchwise joint sparse tracking with occlusion detection. ( 0,727459347860302 )
IEEE Trans Image Process - Temporal frequency of flickering-distortion optimized video halftoning for electronic paper. ( 0,726710410911468 )
Int J Med Robot - Hand-eye and radial distortion calibration for rigid endoscopes. ( 0,726308243423221 )
IEEE Trans Image Process - Particle filter with a mode tracker for visual tracking across illumination changes. ( 0,726244556137911 )
IEEE Trans Vis Comput Graph - Content-Aware Video Retargeting Using Object-preserving Warping. ( 0,725133240175243 )
IEEE Trans Image Process - Collaborative sensing in a distributed PTZ camera network. ( 0,720912200024128 )
IEEE Trans Image Process - Camera constraint-free view-based 3-D object retrieval. ( 0,720877583280592 )
IEEE Trans Image Process - Novel true-motion estimation algorithm and its application to motion-compensated temporal frame interpolation. ( 0,720032361732268 )
IEEE Trans Image Process - Segmentation and tracking multiple objects under occlusion from multiview video. ( 0,715707728899691 )
IEEE Trans Vis Comput Graph - Handling Motion-Blur in 3D Tracking and Rendering for Augmented Reality. ( 0,715121887589148 )
Int J Comput Assist Radiol Surg - Simulation of spatiotemporal CT data sets using a 4D MRI-based lung motion model. ( 0,714465512620837 )
IEEE Trans Image Process - Video object tracking in the compressed domain using spatio-temporal Markov random fields. ( 0,713112305480833 )
IEEE Trans Image Process - Optical flow estimation for flame detection in videos. ( 0,712716962288348 )
IEEE Trans Pattern Anal Mach Intell - Multiple Hypothesis Tracking for Cluttered Biological Image Sequences. ( 0,712173378347522 )
IEEE Trans Vis Comput Graph - Summarization-Based Image Resizing by Intelligent Object Carving. ( 0,711018881752126 )
IEEE Trans Image Process - Object tracking via partial least squares analysis. ( 0,710994924070742 )
IEEE Trans Image Process - Exploring visual and motion saliency for automatic video object extraction. ( 0,710958434262119 )
IEEE Trans Image Process - Integrating graph partitioning and matching for trajectory analysis in video surveillance. ( 0,70980143385646 )
IEEE Trans Image Process - 3-D target-based distributed smart camera network localization. ( 0,708172482208526 )
IEEE Trans Image Process - Fast edge-preserving PatchMatch for large displacement optical flow. ( 0,707665155934362 )
IEEE Trans Image Process - Cluster-based distributed face tracking in camera networks. ( 0,706178705905359 )
IEEE Trans Image Process - A novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. ( 0,705501618122977 )
Int J Comput Assist Radiol Surg - A robust method to track colonoscopy videos with non-informative images. ( 0,704255159793443 )
IEEE Trans Image Process - Robust video hashing via multilinear subspace projections. ( 0,70117634364469 )
Neural Comput - A model of motion transparency processing with local center-surround interactions and feedback. ( 0,70002010878882 )
Comput Math Methods Med - The research and application of visual saliency and adaptive support vector machine in target tracking field. ( 0,700018647987602 )
Comput Math Methods Med - Robust myocardial motion tracking for echocardiography: variational framework integrating local-to-global deformation. ( 0,69970521766478 )
IEEE Trans Pattern Anal Mach Intell - Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera. ( 0,698817660972736 )
IEEE Trans Pattern Anal Mach Intell - 3D Traffic Scene Understanding from Movable Platforms. ( 0,698412556542074 )
IEEE Trans Image Process - Fusing inertial sensor data in an extended Kalman filter for 3D camera tracking. ( 0,697251955435381 )
Comput Math Methods Med - Image tracking for the high similarity drug tablets based on light intensity reflective energy and artificial neural network. ( 0,696221478518532 )
IEEE Trans Image Process - Multi-frame super-resolution reconstruction of small moving objects. ( 0,695208468358589 )
IEEE Trans Image Process - Video super-resolution using simultaneous motion and intensity calculations. ( 0,693868087284664 )
Comput. Biol. Med. - Serial slice image segmentation of digital human based on adaptive geometric active contour tracking. ( 0,693579340746557 )
IEEE Trans Image Process - Video alignment for change detection. ( 0,69295486315738 )
IEEE Trans Pattern Anal Mach Intell - Efficient Subframe Video Alignment using Short Descriptors. ( 0,692556634304207 )
IEEE Trans Image Process - Discriminative metric preservation for tracking low-resolution targets. ( 0,69006672348831 )
IEEE Trans Image Process - Video deblurring algorithm using accurate blur kernel estimation and residual deconvolution based on a blurred-unblurred frame pair. ( 0,685816461517153 )
Comput Math Methods Med - 3D human motion editing and synthesis: a survey. ( 0,684696681321957 )
IEEE Trans Vis Comput Graph - Visuo-Haptic Mixed Reality with Unobstructed Tool-Hand Integration. ( 0,684153201744154 )
IEEE Trans Image Process - Active contour-based visual tracking by integrating colors, shapes, and motions. ( 0,683414391754797 )
Med Biol Eng Comput - Video analysis of Hammersmith lateral tilting examination using Kalman filter guided multi-path tracking. ( 0,681402355409702 )
Comput Methods Programs Biomed - Simulation of the human TMJ behavior based on interdependent joints topology. ( 0,681144173178512 )
IEEE Trans Pattern Anal Mach Intell - A Geometric Particle Filter for Template-Based Visual Tracking. ( 0,680679284667052 )
IEEE Trans Image Process - Distributed consensus on camera pose. ( 0,680556084768778 )
IEEE Trans Image Process - LCD motion blur: modeling, analysis, and algorithm. ( 0,67804089569985 )
Med Biol Eng Comput - Automatic detection of motion blur in intravital video microscopy image sequences via directional statistics of log-Gabor energy maps. ( 0,676576257542337 )
IEEE Trans Pattern Anal Mach Intell - Trajectory Space: A Dual Representation for Nonrigid Structure from Motion. ( 0,67598313910625 )
IEEE Trans Image Process - Occlusion-aware motion layer extraction under large interframe motions. ( 0,675851214883349 )
IEEE J Biomed Health Inform - Red blood cell tracking using optical flow methods. ( 0,675404491920011 )
IEEE J Biomed Health Inform - Fall detection based on body part tracking using a depth camera. ( 0,675039487520884 )
IEEE Trans Pattern Anal Mach Intell - Multimodal Speaker Diarization. ( 0,674886773096155 )
IEEE Trans Vis Comput Graph - Natural Interaction Metaphors for Functional Validations of Virtual Car Models. ( 0,674460261406877 )
IEEE Trans Image Process - Multiple player tracking in sports video: a dual-mode two-way bayesian inference approach with progressive observation modeling. ( 0,674299942994421 )
IEEE Trans Pattern Anal Mach Intell - Tracking-Learning-Detection. ( 0,671197494937491 )
IEEE Trans Pattern Anal Mach Intell - Contextualized Trajectory Parsing with Spatio-Temporal Graph. ( 0,669993794706293 )
Int J Comput Assist Radiol Surg - Robust bronchoscope motion tracking using sequential Monte Carlo methods in navigated bronchoscopy: dynamic phantom and patient validation. ( 0,669812264852167 )
IEEE Trans Image Process - Alleviating dirty-window effect in medium frame-rate binary video halftones. ( 0,666978765739202 )
IEEE Trans Vis Comput Graph - Model Estimation and Selection towards Unconstrained Real-Time Tracking and Mapping. ( 0,666119900914919 )