16.7.4.6.3 Motion Flow, Motion Vectors for Human Action Recognition and Detection

Chapter Contents (Back)
Action Recognition. Human Actions. Flow. See also Spatio-Temporal Techniques for Human Action Recognition and Detection.

Bobick, A.F.[Aaron F.], Davis, J.W.[James W.],
The Recognition of Human Movement Using Temporal Templates,
PAMI(23), No. 3, March 2001, pp. 257-267.
IEEE DOI 0103
BibRef
Earlier:
Action Recognition Using Temporal Templates,
MBR97(Chapter 6). BibRef
Earlier:
Real-Time Recognition of Activity Using Temporal Templates,
WACV96(39-42).
IEEE DOI 9609
BibRef
And: Vismod-386, 1997.
HTML Version. BibRef
And: A2, A1:
The Representation and Recognition of Action Using Temporal Templates,
CVPR97(928-934).
IEEE DOI 9704
BibRef
And: Vismod--402, 1997.
HTML Version. BibRef
Earlier: A1, A2:
An Appearance-Based Representation of Action,
ICPR96(I: 307-312).
IEEE DOI 9608
Actions (human motion). Templates. A temporal template: a vector image where the value at each point is a funciton of the motion properties at the corresponding location in the image sequence. MIT BibRef

Davis, J.W.[James W.],
Sequential Reliable-Inference for Rapid Detection of Human Actions,
EventVideo04(111).
IEEE DOI 0502
BibRef
Earlier:
Hierarchical Motion History Images for Recognizing Human Motion,
EventVideo01(39-46).
IEEE DOI 0106
BibRef

Davis, J.W.[James W.],
Appearance-Based Motion Recognition of Human Actions,
Vismod-387, 1996, M.S. Thesis Index on the spatial distribution of motion energy.
HTML Version. BibRef 9600

Davis, J.W.[James W.], Tyagi, A.[Ambrish],
Minimal-latency human action recognition using reliable-inference,
IVC(24), No. 5, 1 May 2006, pp. 455-472.
Elsevier DOI 0606
BibRef
Earlier:
A reliable-inference framework for recognition of human actions,
AVSBS03(169-176).
IEEE DOI 0310
Action recognition; Reliable-inference; MAP; Video analysis Determine shortest video sequence, and extend if confusing or unreliable. BibRef

Davis, J.W.[James W.], Gao, H.[Hui],
An expressive three-mode principal components model of human action style,
IVC(21), No. 11, October 2003, pp. 1001-1016.
Elsevier DOI 0310
BibRef
Earlier:
Recognizing human action efforts: An adaptive three-mode PCA framework,
ICCV03(1463-1469).
IEEE DOI 0311
BibRef

Davis, J.W., Gao, H.[Hui], Kannappan, V.S.,
A three-mode expressive feature model of action effort,
Motion02(139-144).
IEEE DOI 0303
How much effort is required for the action. BibRef

Ahad, M.A.R.[M. Atiqur Rahman], Tan, J.K., Kim, H.S., Ishikawa, S.,
Temporal motion recognition and segmentation approach,
IJIST(19), No. 2, June 2009, pp. 91-99.
DOI Link 0905
BibRef

Ahad, M.A.R.[M. Atiqur Rahman], Tan, J.K., Kim, H.S., Ishikawa, S.,
Motion history image: Its variants and applications,
MVA(23), No. 2, March 2012, pp. 255-281.
WWW Link. 1202
BibRef
Earlier:
Action recognition by employing combined directional motion history and energy images,
CVCGI10(73-78).
IEEE DOI 1006
BibRef

Ahad, M.A.R.[M. Atiqur Rahman],
Computer Vision and Action Recognition: A Guide for Image Processing and Computer Vision Community for Action Understanding,
SpringerNew-York, 2012.

ISBN: 978-94-91216-19-0.
WWW Link. 1202
Action Datasets; Action Representation Approaches (Statistical or Structural); Shape Representation and Feature Vector Analysis (Tracking issues); and Challenges Ahead BibRef

Ahad, M.A.R.[M. Atiqur Rahman],
Motion History Images for Action Recognition and Understanding,

Springer2013. ISBN 978-1-4471-4729-9
WWW Link. 1304
Survey, Motion History Image. Motion history image (MHI) method. BibRef

Ahad, M.A.R.[M. Atiqur Rahman], Ogata, T., Tan, J.K., Kim, H.S., Ishikawa, S.,
Motion recognition approach to solve overwriting in complex actions,
FG08(1-6).
IEEE DOI 0809
BibRef

Ahad, M.A.R.[M. Atiqur Rahman],
Smart Approaches for Human Action Recognition,
PRL(34), No. 15, 2013, pp. 1769-1770.
Elsevier DOI 1309
BibRef

Mahbub, U.[Upal], Imtiaz, H.[Hafiz], Ahad, M.A.R.[M. Atiqur Rahman],
Action recognition based on statistical analysis from clustered flow vectors,
SIViP(8), No. 2, February 2014, pp. 243-253.
WWW Link. 1402
BibRef

Ballan, L.[Lamberto], Bertini, M.[Marco], del Bimbo, A.[Alberto], Seidenari, L.[Lorenzo], Serra, G.[Giuseppe],
Effective Codebooks for Human Action Representation and Classification in Unconstrained Videos,
MultMed(14), No. 4, 2012, pp. 1234-1245.
IEEE DOI 1208
BibRef
Earlier:
Effective Codebooks for human action categorization,
ObjectEvent09(506-513).
IEEE DOI 0910
BibRef
And:
Recognizing human actions by fusing spatio-temporal appearance and motion descriptors,
ICIP09(3569-3572).
IEEE DOI 0911
BibRef

Uricchio, T.[Tiberio], Ballan, L.[Lamberto], Seidenari, L.[Lorenzo], del Bimbo, A.[Alberto],
Automatic image annotation via label transfer in the semantic space,
PR(71), No. 1, 2017, pp. 144-157.
Elsevier DOI 1707
Automatic, image, annotation BibRef

Uricchio, T.[Tiberio], Bertini, M.[Marco], Seidenari, L.[Lorenzo], del Bimbo, A.[Alberto],
Fisher Encoded Convolutional Bag-of-Windows for Efficient Image Retrieval and Social Image Tagging,
WSM15(1020-1026)
IEEE DOI 1602
Aggregate a set of Deep Convolutional Neural Network (CNN) responses, extracted from a set of image windows. BibRef

Uricchio, T.[Tiberio], Ballan, L.[Lamberto],
Evaluating Temporal Information for Social Image Annotation and Retrieval,
CIAP13(I:722-732).
Springer DOI 1311
BibRef

Seidenari, L.[Lorenzo], Serra, G.[Giuseppe], Bagdanov, A.D., del Bimbo, A.[Alberto],
Local Pyramidal Descriptors for Image Recognition,
PAMI(36), No. 5, May 2014, pp. 1033-1040.
IEEE DOI 1405
Approximation methods BibRef

Costantini, L.[Luca], Seidenari, L.[Lorenzo], Serra, G.[Giuseppe], Capodiferro, L.[Licia], del Bimbo, A.[Alberto],
Space-Time Zernike Moments and Pyramid Kernel Descriptors for Action Classification,
CIAP11(II: 199-208).
Springer DOI 1109
BibRef

Kulkarni, K.[Kaustubh], Evangelidis, G.[Georgios], Cech, J.[Jan], Horaud, R.[Radu],
Continuous Action Recognition Based on Sequence Alignment,
IJCV(112), No. 1, March 2015, pp. 90-114.
Springer DOI 1503
BibRef
And: Erratum: IJCV(112), No. 1, March 2015, pp. 130.
Springer DOI 1503
See also Continuous Gesture Recognition from Articulated Poses. BibRef

Tsai, D.M.[Du-Ming], Chiu, W.Y.[Wei-Yao], Lee, M.H.[Men-Han],
Optical flow-motion history image (OF-MHI) for action recognition,
SIViP(9), No. 8, November 2015, pp. 1897-1906.
WWW Link. 1511
BibRef

Wang, X.F.[Xiao-Fang], Qi, C.[Chun],
Action recognition using edge trajectories and motion acceleration descriptor,
MVA(27), No. 5, August 2016, pp. 861-875.
WWW Link. 1609
BibRef

Wang, X.F.[Xiao-Fang], Qi, C.[Chun],
Saliency-based dense trajectories for action recognition using low-rank matrix decomposition,
JVCIR(41), No. 1, 2016, pp. 361-374.
Elsevier DOI 1612
Action recognition BibRef

Wang, X.F.[Xiao-Fang], Qi, C.[Chun], Lin, F.[Fei],
Combined trajectories for action recognition based on saliency detection and motion boundary,
SP:IC(57), No. 1, 2017, pp. 91-102.
Elsevier DOI 1709
Action recognition BibRef

Qin, J.[Jie], Liu, L.[Li], Yu, M.Y.[Meng-Yang], Wang, Y.H.[Yun-Hong], Shao, L.[Ling],
Fast Action Retrieval from Videos via Feature Disaggregation,
CVIU(156), No. 1, 2017, pp. 104-116.
Elsevier DOI 1702
BibRef
Earlier: BMVC15(xx-yy).
DOI Link 1601
Similarity search BibRef

Fernando, B.[Basura], Gavves, E.[Efstratios], Oramas Mogrovejo, J.A.[José Antonio], Ghodrati, A.[Amir], Tuytelaars, T.[Tinne],
Rank Pooling for Action Recognition,
PAMI(39), No. 4, April 2017, pp. 773-787.
IEEE DOI 1703
BibRef
Earlier:
Modeling video evolution for action recognition,
CVPR15(5378-5387)
IEEE DOI 1510
Data models BibRef

Seo, J.J.[Jeong-Jik], Kim, H.I.[Hyung-Il], de Neve, W.[Wesley], Ro, Y.M.[Yong Man],
Effective and efficient human action recognition using dynamic frame skipping and trajectory rejection,
IVC(58), No. 1, 2017, pp. 76-85.
Elsevier DOI 1703
Frame skipping BibRef

Seo, J.J.[Jeong-Jik], Son, J.[Jisoo], Kim, H.I.[Hyung-Il], de Neve, W.[Wesley], Ro, Y.M.[Yong Man],
Efficient and effective human action recognition in video through motion boundary description with a compact set of trajectories,
FG15(1-6)
IEEE DOI 1508
feature extraction BibRef

Matsui, K.[Kenji], Tamaki, T.[Toru], Raytchev, B.[Bisser], Kaneda, K.[Kazufumi],
Trajectory-Set Feature for Action Recognition,
IEICE(E100-D), No. 8, August 2017, pp. 1922-1924.
WWW Link. 1708
BibRef

Raytchev, B.[Bisser], Kawamoto, H., Tamaki, T.[Toru], Kaneda, K.[Kazufumi],
Higher-level representation of local spatio-temporal features for human action recognition using Subspace Matching Kernels,
ICPR16(3862-3867)
IEEE DOI 1705
Feature extraction, Histograms, Kernel, Manifolds, Measurement, Pattern recognition, Videos BibRef

Raytchev, B.[Bisser], Shigenaka, R.[Ryosuke], Tamaki, T.[Toru], Kaneda, K.[Kazufumi],
Action recognition by orthogonalized subspaces of local spatio-temporal features,
ICIP13(4387-4391)
IEEE DOI 1402
Action Recognition BibRef

Sultani, W.[Waqas], Zhang, D.[Dong], Shah, M.[Mubarak],
Unsupervised action proposal ranking through proposal recombination,
CVIU(161), No. 1, 2017, pp. 42-50.
Elsevier DOI 1708
Action proposal ranking BibRef

Sultani, W.[Waqas], Shah, M.[Mubarak],
Automatic action annotation in weakly labeled videos,
CVIU(161), No. 1, 2017, pp. 77-86.
Elsevier DOI 1708
BibRef
And:
What If We Do Not have Multiple Videos of the Same Action? Video Action Localization Using Web Images,
CVPR16(1077-1085)
IEEE DOI 1612
Weakly supervised. BibRef

Yeung, S.[Serena], Russakovsky, O.[Olga], Jin, N.[Ning], Andriluka, M.[Mykhaylo], Mori, G.[Greg], Fei-Fei, L.[Li],
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos,
IJCV(126), No. 2-4, April 2018, pp. 375-389.
Springer DOI 1804
Dense labels -- every frame. LSTM networks. BibRef

Varol, G.[Gül], Laptev, I.[Ivan], Schmid, C.[Cordelia],
Long-Term Temporal Convolutions for Action Recognition,
PAMI(40), No. 6, June 2018, pp. 1510-1517.
IEEE DOI 1805
Estimation, Network architecture, Neural networks, Optical filters, Optical imaging, Spatial resolution, Training, Action recognition, video analysis BibRef

El-Henawy, I.M.[Ibrahim M.], Ahmed, K.[Kareem], Mahmoud, H.A.[Hamdi A.],
Action recognition using fast HOG3D of integral videos and Smith-Waterman partial matching,
IET-IPR(12), No. 6, June 2018, pp. 896-908.
DOI Link 1805
BibRef
Earlier: A2, A1, A3:
Action recognition technique based on fast HOG3D of integral foreground snippets and random forest,
ISCV17(1-7)
IEEE DOI 1710
image recognition, image representation, input video file, random forest, videos representation, Trajectory, Action recognition, HOG3D, Random Forest, gesture, spatio-temporal BibRef

Carmona, J.M.[Josep Maria], Climent, J.[Joan],
Human action recognition by means of subtensor projections and dense trajectories,
PR(81), 2018, pp. 443-455.
Elsevier DOI 1806
Action recognition, Subtensors, Dense trajectories, Keypoint descriptors, Temporal template BibRef

Phan, H.H.[Hai-Hong], Vu, N.S.[Ngoc-Son], Nguyen, V.L.[Vu-Lam], Quoy, M.[Mathias],
Action recognition based on motion of oriented magnitude patterns and feature selection,
IET-CV(12), No. 5, August 2018, pp. 735-743.
DOI Link 1807
BibRef
Earlier:
Motion of Oriented Magnitudes Patterns for Human Action Recognition,
ISVC16(II: 168-177).
Springer DOI 1701
BibRef

Ghorbel, E.[Enjie], Boutteau, R.[Rémi], Boonaert, J.[Jacques], Savatier, X.[Xavier], Lecoeuche, S.[Stéphane],
Kinematic Spline Curves: A temporal invariant descriptor for fast action recognition,
IVC(77), 2018, pp. 60-71.
Elsevier DOI 1809
BibRef
Earlier:
A fast and accurate motion descriptor for human action recognition applications,
ICPR16(919-924)
IEEE DOI 1705
RBG-D cameras, Action recognition, Low computational latency, Temporal normalization. Acceleration, Interpolation, Kinematics, Kinetic energy, Skeleton, Splines (mathematics), Trajectory BibRef

Sabri, A.Q.M.[A.Q. Muhammad], Boonaert, J., Lecoeuche, S., Mouaddib, E.,
Human action classification using surf based spatio-temporal correlated descriptors,
ICIP12(1401-1404).
IEEE DOI 1302
BibRef

Blokus, A.[Adam], Krawczyk, H.[Henryk],
Systematic approach to binary classification of images in video streams using shifting time windows,
SIViP(13), No. 2, March 2019, pp. 341-348.
Springer DOI 1904
First initial classification of single frame. Then temporal analysis. BibRef

Wang, T.W.[Ting-Wei], Duan, P.[Peng], Ma, B.X.[Bing-Xian], Wu, P.[Peng], Lu, W.Z.[Wei-Zhi],
Action recognition using dynamic hierarchical trees,
JVCIR(61), 2019, pp. 315-325.
Elsevier DOI 1906
Action recognition, Hierarchical modeling, Evolution, Tree kernel BibRef

Edison, A.[Anitha], Jiji, C.V.,
Automated video analysis for action recognition using descriptors derived from optical acceleration,
SIViP(13), No. 5, July 2019, pp. 915-922.
Springer DOI 1906
Acceleration computed from Optical Flow for actions descriptions. BibRef

Li, C.K.[Chuan-Kun], Hou, Y.H.[Yong-Hong], Li, W.Q.[Wan-Qing], Wang, P.C.[Pi-Chao],
Learning attentive dynamic maps (ADMs) for Understanding Human Actions,
JVCIR(65), 2019, pp. 102640.
Elsevier DOI 1912
Human-robot/machine interaction, Deep learning, Human action recognition BibRef

Alwando, E.H.P.[Erick Hendra Putra], Chen, Y.T.[Yie-Tarng], Fang, W.H.[Wen-Hsien],
CNN-Based Multiple Path Search for Action Tube Detection in Videos,
CirSysVideo(30), No. 1, January 2020, pp. 104-116.
IEEE DOI 2002
BibRef
Earlier:
Multiple path search for action tube detection in videos,
ICIP17(4232-4236)
IEEE DOI 1803
convolutional neural nets, feature extraction, image motion analysis, object detection, video signal processing, object detection. Complexity theory, Message passing, Proposals, Radio frequency, Search problems, Videos, Action localization. BibRef

Song, S.J.[Si-Jie], Liu, J.Y.[Jia-Ying], Li, Y.H.[Yang-Hao], Guo, Z.M.[Zong-Ming],
Modality Compensation Network: Cross-Modal Adaptation for Action Recognition,
IP(29), 2020, pp. 3957-3969.
IEEE DOI 2002
Modality compensation, multi-modal, action recognition BibRef


Wang, L., Koniusz, P., Huynh, D.,
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition With CNNs,
ICCV19(8697-8707)
IEEE DOI 2004
convolutional neural nets, feature extraction, image colour analysis, image motion analysis, Training BibRef

Han, T.D.[Teng-Da], Xie, W.D.[Wei-Di], Zisserman, A.[Andrew],
Video Representation Learning by Dense Predictive Coding,
HVU19(1483-1492)
IEEE DOI 2004
image motion analysis, image representation, learning (artificial intelligence), video coding, video BibRef

Crasto, N.[Nieves], Weinzaepfel, P.[Philippe], Alahari, K.[Karteek], Schmid, C.[Cordelia],
MARS: Motion-Augmented RGB Stream for Action Recognition,
CVPR19(7874-7883).
IEEE DOI 2002
BibRef

Sevilla-Lara, L.[Laura], Liao, Y.[Yiyi], Güney, F.[Fatma], Jampani, V.[Varun], Geiger, A.[Andreas], Black, M.J.[Michael J.],
On the Integration of Optical Flow and Action Recognition,
GCPR18(281-297).
Springer DOI 1905
BibRef

Hommos, O.[Omar], Pintea, S.L.[Silvia L.], Mettes, P.S.M.[Pascal S. M.], van Gemert, J.C.[Jan C.],
Using Phase Instead of Optical Flow for Action Recognition,
OpticalFlow18(VI:678-691).
Springer DOI 1905
BibRef

Hiraoka, H.[Hiroki], Imiya, A.[Atsushi],
Topological Labelling of Scene using Background/Foreground Separation and Epipolar Geometry,
RSL-CV19(652-660)
IEEE DOI 2004
geometry, image segmentation, image sequences, principal component analysis, stereo image processing, Superpixels BibRef

Gotoh, I.[Itaru], Hiraoka, H.[Hiroki], Imiya, A.[Atsushi],
Event Extraction Using Transportation of Temporal Optical Flow Fields,
OpticalFlow18(VI:692-705).
Springer DOI 1905
BibRef

Yang, M.L.[Ming-Lei], Song, Y.[Yan], Shu, X.B.[Xiang-Bo], Tang, J.H.[Jin-Hui],
Temporal Action Localization Based on Temporal Evolution Model and Multiple Instance Learning,
MMMod19(II:341-351).
Springer DOI 1901
BibRef

Zhang, W.[Wei], Cen, J.P.[Jie-Peng], Zheng, H.C.[Hui-Cheng],
Temporal Inception Architecture for Action Recognition with Convolutional Neural Networks,
ICPR18(3216-3221)
IEEE DOI 1812
Kernel, Feature extraction, Videos, Streaming media, Computer architecture, Pattern recognition BibRef

Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.,
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition,
CVPR18(1390-1399)
IEEE DOI 1812
Feature extraction, Optical network units, Optical flow, Dynamics, Network architecture BibRef

Diba, A.[Ali], Sharma, V.[Vivek], Van Gool, L.J.[Luc J.], Stiefelhagen, R.,
DynamoNet: Dynamic Action and Motion Network,
ICCV19(6191-6200)
IEEE DOI 2004
convolutional neural nets, image classification, image filtering, image motion analysis, image representation, Convolution BibRef

Alwassel, H.[Humam], Heilbron, F.C.[Fabian Caba], Escorcia, V.[Victor], Ghanem, B.[Bernard],
Diagnosing Error in Temporal Action Detectors,
ECCV18(III: 264-280).
Springer DOI 1810
BibRef

Lee, M.G.[Myung-Gi], Lee, S.[Seungeui], Son, S.[Sungjoon], Park, G.[Gyutae], Kwak, N.[Nojun],
Motion Feature Network: Fixed Motion Filter for Action Recognition,
ECCV18(X: 392-408).
Springer DOI 1810
BibRef

Sun, C.[Chen], Shrivastava, A.[Abhinav], Vondrick, C.[Carl], Sukthankar, R.[Rahul], Murphy, K.[Kevin], Schmid, C.[Cordelia],
Relational Action Forecasting,
CVPR19(273-283).
IEEE DOI 2002
BibRef

Sun, C.[Chen], Shrivastava, A.[Abhinav], Vondrick, C.[Carl], Murphy, K.[Kevin], Sukthankar, R.[Rahul], Schmid, C.[Cordelia],
Actor-Centric Relation Network,
ECCV18(XI: 335-351).
Springer DOI 1810
BibRef

Liu, C., Xu, X., Zhang, Y.,
Temporal Attention Network for Action Proposal,
ICIP18(2281-2285)
IEEE DOI 1809
Temporal action proposal, temporal attention, untrimmed video analysis, neural network BibRef

Kwon, O.C., Kim, J., Yoo, C.D.,
Action Recognition: First-and Second-Order 3D Feature in Bi-Directional Attention Network,
ICIP18(3453-3457)
IEEE DOI 1809
Bidirectional control, Computer architecture, Convolutional neural networks, Visualization, Feeds, spatio-temporal bi-directional LSTM Attention BibRef

Yu, R., Wang, H., Davis, L.S.,
ReMotENet: Efficient Relevant Motion Event Detection for Large-Scale Home Surveillance Videos,
WACV18(1642-1651)
IEEE DOI 1806
image motion analysis, learning (artificial intelligence), neural nets, object detection, video surveillance, 3D ConvNets, Videos BibRef

Ng, J.Y.H., Davis, L.S.,
Temporal Difference Networks for Video Action Recognition,
WACV18(1587-1596)
IEEE DOI 1806
feedforward neural nets, image classification, image motion analysis, image recognition, image representation, BibRef

Ng, J.Y.H., Choi, J., Neumann, J., Davis, L.S.[Larry S.],
ActionFlowNet: Learning Motion Representation for Action Recognition,
WACV18(1616-1624)
IEEE DOI 1806
image motion analysis, image recognition, image representation, image sequences, learning (artificial intelligence), neural nets, Task analysis BibRef

Zhang, T.Y.[Tian-Yi], Niu, L.[Li], Cai, J.F.[Jian-Fei], Kot, A.C.[Alex C.],
Action proposals using hierarchical clustering of super-trajectories,
VCIP17(1-4)
IEEE DOI 1804
gesture recognition, sport, unsupervised learning, video signal processing, action localization task, Trajectory Grouping BibRef

Fang, H., Thiyagalingam, J., Bessis, N., Edirisinghe, E.,
Fast and reliable human action recognition in video sequences by sequential analysis,
ICIP17(3973-3977)
IEEE DOI 1803
Feature extraction, Reliability, Sequential analysis, Streaming media, Task analysis, Training, Video sequences, sequential probability ratio test(SPRT) BibRef

Liu, Z., Tian, Y., Wang, Z.,
Improving human action recognitionby temporal attention,
ICIP17(870-874)
IEEE DOI 1803
Adaptation models, Computer architecture, Feature extraction, Optical imaging, Recurrent neural networks, Training, Videos, temporal attention BibRef

Xiao, X., Hu, H., Wang, W.,
Trajectories-based motion neighborhood feature for human action recognition,
ICIP17(4147-4151)
IEEE DOI 1803
Computer vision, Handheld computers, Indexes, Pattern recognition, Support vector machines, Trajectory, linear SVM BibRef

Pu, J., Matsui, Y., Yang, F., Satoh, S.,
Energy based fast event retrieval in video with temporal match kernel,
ICIP17(885-889)
IEEE DOI 1803
Event retrieval, temporal match kernel BibRef

Hou, R.[Rui], Chen, C.[Chen], Shah, M.[Mubarak],
Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos,
ICCV17(5823-5832)
IEEE DOI 1802
convolution, feature extraction, image classification, image motion analysis, image recognition, Videos BibRef

Kalogeiton, V.[Vicky], Weinzaepfel, P.[Philippe], Ferrari, V.[Vittorio], Schmid, C.[Cordelia],
Action Tubelet Detector for Spatio-Temporal Action Localization,
ICCV17(4415-4423)
IEEE DOI 1802
convolution, feature extraction, image sequences, object detection, regression analysis, video signal processing, ACT-detector, Videos BibRef

Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.,
SST: Single-Stream Temporal Action Proposals,
CVPR17(6373-6382)
IEEE DOI 1711
Computational modeling, Computer architecture, Proposals, Training, Video sequences, Visualization BibRef

Sigurdsson, G.A., Divvala, S., Farhadi, A., Gupta, A.,
Asynchronous Temporal Fields for Action Recognition,
CVPR17(5650-5659)
IEEE DOI 1711
Cognition, Hidden Markov models, Semantics, Stochastic processes, Training, Videos BibRef

Lan, Z.Z.[Zhen-Zhong], Yu, S.I.[Shoou-I], Yao, D.Z.[De-Zhong], Lin, M.[Ming], Raj, B.[Bhiksha], Hauptmann, A.G.[Alexander G.],
The Best of Both Worlds: Combining Data-Independent and Data-Driven Approaches for Action Recognition,
Robust16(1196-1205)
IEEE DOI 1612
Video features. BibRef

Yuan, J.[Jun], Ni, B.B.[Bing-Bing], Yang, X.K.[Xiao-Kang], Kassim, A.A.[Ashraf A.],
Temporal Action Localization with Pyramid of Score Distribution Features,
CVPR16(3093-3102)
IEEE DOI 1612
BibRef

Alwassel, H.[Humam], Heilbron, F.C.[Fabian Caba], Ghanem, B.[Bernard],
Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization,
ECCV18(IX: 253-269).
Springer DOI 1810
BibRef

Heilbron, F.C.[Fabian Caba], Niebles, J.C.[Juan Carlos], Ghanem, B.[Bernard],
Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos,
CVPR16(1914-1923)
IEEE DOI 1612
BibRef

Li, Y.W.[Ying-Wei], Li, Y.[Yi], Vasconcelos, N.M.[Nuno M.],
RESOUND: Towards Action Recognition Without Representation Bias,
ECCV18(VI: 520-535).
Springer DOI 1810
BibRef

Li, Y.W.[Ying-Wei], Li, W.X.[Wei-Xin], Mahadevan, V.[Vijay], Vasconcelos, N.M.[Nuno M.],
VLAD3: Encoding Dynamics of Deep Features for Action Recognition,
CVPR16(1951-1960)
IEEE DOI 1612
BibRef

de Souza, C.R.[César Roberto], Gaidon, A.[Adrien], Vig, E.[Eleonora], López, A.M.[Antonio Manuel],
Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition,
ECCV16(VII: 697-716).
Springer DOI 1611
BibRef

Wang, L.M.[Li-Min], Xiong, Y.J.[Yuan-Jun], Lin, D.[Dahua], Van Gool, L.J.[Luc J.],
UntrimmedNets for Weakly Supervised Action Recognition and Detection,
CVPR17(6402-6411)
IEEE DOI 1711
Adaptation models, Feature extraction, Motion pictures, Proposals, Training, Videos, Visualization BibRef

Wang, L.M.[Li-Min], Xiong, Y.J.[Yuan-Jun], Wang, Z.[Zhe], Qiao, Y.[Yu], Lin, D.[Dahua], Tang, X.[Xiaoou], Van Gool, L.J.[Luc J.],
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition,
ECCV16(VIII: 20-36).
Springer DOI 1611
BibRef

Kim, T.S., Reiter, A.[Austin],
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks,
MotionRep17(1623-1631)
IEEE DOI 1709
Activity recognition, Computational modeling, Feature extraction, Skeleton, Solid modeling. BibRef

Leyva, R.[Roberto], Sanchez, V.[Victor], Li, C.T.[Chang-Tsun],
Fast Binary-Based Video Descriptors for Action Recognition,
DICTA16(1-8)
IEEE DOI 1701
BibRef
Earlier:
A fast binary pair-based video descriptor for action recognition,
ICIP16(4185-4189)
IEEE DOI 1610
Detectors. 3D Binary Pair Differences (3DBPD) for video action recognition. BibRef

Chen, Q.Q., Liu, F., Li, X., Liu, B.D., Zhang, Y.J.,
Saliency-context two-stream convnets for action recognition,
ICIP16(3076-3080)
IEEE DOI 1610
Adaptive optics BibRef

Li, Z., Wang, W., Li, N., Wang, J.,
Tube ConvNets: Better exploiting motion for action recognition,
ICIP16(3056-3060)
IEEE DOI 1610
Clustering algorithms BibRef

Wu, Z.X.[Zu-Xuan], Fu, Y.W.[Yan-Wei], Jiang, Y.G.[Yu-Gang], Sigal, L.[Leonid],
Harnessing Object and Scene Semantics for Large-Scale Video Understanding,
CVPR16(3112-3121)
IEEE DOI 1612
BibRef

Jia, C.C.[Cheng-Cheng], Pang, W.[Wei], Fu, Y.[Yun],
Mode-Driven Volume Analysis Based on Correlation of Time Series,
VECTaR14(818-833).
Springer DOI 1504
BibRef

Sun, X.[Xin], Huang, D.[Di], Wang, Y.H.[Yun-Hong], Qin, J.[Jie],
Action recognition based on kinematic representation of video data,
ICIP14(1530-1534)
IEEE DOI 1502
Acceleration BibRef

Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Sun, Q.R.[Qian-Ru],
Action classification by exploring directional co-occurrence of weighted stips,
ICIP14(1460-1464)
IEEE DOI 1502
Accuracy BibRef

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Spatio-Temporal Techniques for Human Action Recognition and Detection .


Last update:Nov 23, 2020 at 10:27:11