16.7.4.6.5 Human Action Recognition in Still Images, Single Images

Chapter Contents (Back)
Action Recognition. Human Actions. Single Image. See also Human Action Recognition and Detection Using Human Pose.

Khan, F.S.[Fahad Shahbaz], Anwer, R.M.[Rao Muhammad], van de Weijer, J.[Joost], Bagdanov, A.D.[Andrew D.], Lopez, A.M.[Antonio M.], Felsberg, M.[Michael],
Coloring Action Recognition in Still Images,
IJCV(105), No. 3, December 2013, pp. 205-221.
Springer DOI 1309
From static images. Shape cues and color. BibRef

Guo, G.D.[Guo-Dong], Lai, A.[Alice],
A survey on still image based human action recognition,
PR(47), No. 10, 2014, pp. 3343-3361.
Elsevier DOI 1406
Survey, Action Recognition. Action recognition BibRef

Cheema, M.S.[Muhammad Shahzad], Eweiwi, A.[Abdalrahman], Bauckhage, C.[Christian],
Human activity recognition by separating style and content,
PRL(50), No. 1, 2014, pp. 130-138.
Elsevier DOI 1410
BibRef
Earlier:
Who is doing what? Simultaneous recognition of actions and actors,
ICIP12(749-752).
IEEE DOI 1302
Action recognition BibRef

Cheema, M.S.[Muhammad Shahzad], Eweiwi, A.[Abdalrahman], Bauckhage, C.[Christian],
Gait recognition by learning distributed key poses,
ICIP12(1393-1396).
IEEE DOI 1302
BibRef

Eweiwi, A.[Abdalrahman], Cheema, M.S.[Muhammad Shahzad], Bauckhage, C.[Christian],
Action recognition in still images by learning spatial interest regions from videos,
PRL(51), No. 1, 2015, pp. 8-15.
Elsevier DOI 1412
BibRef
Earlier: A2, A1, A3:
A Stochastic Late Fusion Approach to Human Action Recognition in Unconstrained Images and Videos,
GCPR14(616-628).
Springer DOI 1411
BibRef
Earlier: A1, A2, A3:
Discriminative Joint Non-negative Matrix Factorization for Human Action Classification,
GCPR13(61-70).
Springer DOI 1311
Action recognition BibRef

Eweiwi, A.[Abdalrahman], Cheema, M.S.[Muhammed S.], Bauckhage, C.[Christian], Gall, J.[Juergen],
Efficient Pose-Based Action Recognition,
ACCV14(V: 428-443).
Springer DOI 1504
BibRef

Cheema, M.S.[Muhammad Shahzad], Eweiwi, A.[Abdalrahman], Thurau, C.[Christian], Bauckhage, C.[Christian],
Action recognition by learning discriminative key poses,
PEAction11(1302-1309).
IEEE DOI 1201
BibRef
And: A2, A1, A3, A4:
Temporal key poses for human action recognition,
PEAction11(1310-1317).
IEEE DOI 1201
BibRef

Zhang, Y., Cheng, L., Wu, J., Cai, J., Do, M.N., Lu, J.,
Action Recognition in Still Images With Minimum Annotation Efforts,
IP(25), No. 11, November 2016, pp. 5479-5490.
IEEE DOI 1610
Detectors BibRef

Zhang, L.[Lei], Li, C.X.[Chang-Xi], Peng, P.[Peipei], Xiang, X.Z.[Xue-Zhi], Song, J.[Jingkuan],
Towards optimal VLAD for human action recognition from still images,
IVC(55, Part 2), No. 1, 2016, pp. 53-63.
Elsevier DOI 1612
VLAD BibRef

Yan, S.Y.[Shi-Yang], Smith, J.S.[Jeremy S.], Zhang, B.L.[Bai-Ling],
Action Recognition from Still Images Based on Deep VLAD Spatial Pyramids,
SP:IC(54), No. 1, 2017, pp. 118-129.
Elsevier DOI 1704
BibRef
And:
Attributes and Action Recognition Based on Convolutional Neural Networks and Spatial Pyramid VLAD Encoding,
BEST16(III: 500-514).
Springer DOI 1704
Actions BibRef

Yan, S.Y.[Shi-Yang], Smith, J.S.[Jeremy S.], Lu, W.J.[Wen-Jin], Zhang, B.L.[Bai-Ling],
Hierarchical Multi-scale Attention Networks for action recognition,
SP:IC(61), No. 1, 2018, pp. 73-84.
Elsevier DOI 1801
Action recognition BibRef

Sharma, G.[Gaurav], Jurie, F.[Frederic], Schmid, C.[Cordelia],
Expanded Parts Model for Semantic Description of Humans in Still Images,
PAMI(39), No. 1, January 2017, pp. 87-101.
IEEE DOI 1612
BibRef
Earlier:
Expanded Parts Model for Human Attribute and Action Recognition in Still Images,
CVPR13(652-659)
IEEE DOI 1309
Analytical models. attributes See also EPML: Expanded Parts Based Metric Learning for Occlusion Robust Face Verification. BibRef

Zhao, Z.C.[Zhi-Chen], Ma, H.M.[Hui-Min], Chen, X.Z.[Xiao-Zhi],
Generalized symmetric pair model for action classification in still images,
PR(64), No. 1, 2017, pp. 347-360.
Elsevier DOI 1701
Generalized symmetry BibRef

Vieira, T.[Thales], Faugeroux, R.[Romain], Martínez, D.[Dimas], Lewiner, T.[Thomas],
Online human moves recognition through discriminative key poses and speed-aware action graphs,
MVA(28), No. 1-2, February 2017, pp. 185-200.
Springer DOI 1702
BibRef

Wang, J., Wang, G.,
Hierarchical Spatial Sum-Product Networks for Action Recognition in Still Images,
CirSysVideo(28), No. 1, January 2018, pp. 90-100.
IEEE DOI 1801
Computational modeling, Computer vision, Correlation, Feature extraction, Image recognition, Robustness, Videos, sum-product networks (SPNs) BibRef


Zhao, Z., Ma, H., You, S.,
Single Image Action Recognition Using Semantic Body Part Actions,
ICCV17(3411-3419)
IEEE DOI 1802
feature extraction, image recognition, image segmentation, semantic networks, PASCAL VOC 2012, Stanford-40, Torso BibRef

Roy, A.[Abhinaba], Banerjee, B.[Biplab], Murino, V.[Vittorio],
Discriminative Dictionary Design for Action Classification in Still Images,
CIAP17(II:160-170).
Springer DOI 1711
BibRef

Chao, Y.W., Yang, J., Price, B., Cohen, S., Deng, J.,
Forecasting Human Dynamics from Static Images,
CVPR17(3643-3651)
IEEE DOI 1711
Decoding, Forecasting, Heating systems, Pose estimation, Skeleton BibRef

Sharma, K., Kumar, A.C., Bhandarkar, S.M.[Suchendra M.],
Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions,
HAAHDC17(58-66)
IEEE DOI 1609
image motion analysis, natural language processing, object detection, NLP-based approaches, action detection, natural language descriptions, natural language processing, object-verb-object triplet models, still images, top object detection, training, verb detection, visual action detectors, word embeddings, word2vec, Context, Detectors, Feature extraction, Image recognition, Reliability, Training, Visualization, Object-Verb-Object triplet model, action recognition, natural language processing, word2vec, model BibRef

Favorskaya, M., Novikov, D., Savitskaya, Y.,
Human Action Poselets Estimation Via Color G-Surf in Still Images,
PTVSBB15(51-58).
DOI Link 1508
BibRef

Guan, N.Y.[Nai-Yang], Tao, D.C.[Da-Cheng], Lan, L.[Long], Luo, Z.G.[Zhi-Gang], Yang, X.J.[Xue-Jun],
Activity Recognition in Still Images with Transductive Non-negative Matrix Factorization,
VECTaR14(802-817).
Springer DOI 1504
BibRef

Zheng, Y.[Yin], Zhang, Y.J.[Yu-Jin], Li, X.[Xue], Liu, B.D.[Bao-Di],
Action recognition in still images using a combination of human pose and context information,
ICIP12(785-788).
IEEE DOI 1302
BibRef

Delaitre, V.[Vincent], Laptev, I.[Ivan], Sivic, J.[Josef],
Recognizing human actions in still images: A study of bag-of-features and part-based representations,
BMVC10(xx-yy).
HTML Version. 1009
BibRef

Ullah, M.M.[Muhammad Muneeb], Parizi, S.N.[Sobhan Naderi], Laptev, I.[Ivan],
Improving Bag-of-features Action Recognition with Non-local Cues,
BMVC10(xx-yy).
HTML Version. 1009
BibRef

Yang, W.L.[Wei-Long], Wang, Y.[Yang], Mori, G.[Greg],
Recognizing human actions from still images with latent poses,
CVPR10(2030-2037).
IEEE DOI 1006
BibRef
And:
Efficient Human Action Detection Using a Transferable Distance Function,
ACCV09(II: 417-426).
Springer DOI 0909
BibRef
Earlier:
Human action recognition from a single clip per action,
MLMotion09(482-489).
IEEE DOI 0910
BibRef

Thurau, C.[Christian], Hlavac, V.[Vaclav],
Pose primitive based human action recognition in videos or still images,
CVPR08(1-8).
IEEE DOI 0806
BibRef

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Human Action Recognition and Detection Using Human Pose .


Last update:Jun 23, 2018 at 14:58:54