17.1.4.1 Human Action Recognition with Occlusions

Chapter Contents (Back)
Action Recognition. Human Actions. Human Motion. Occlusions. 2602

See also Human Action Recognition, Part Models, Human Pose.
See also Object Recognition Using Human Interaction, Handling.

Emami, A.[Ali], Harandi, M.T.[Mehrtash T.], Dadgostar, F.[Farhad], Lovell, B.C.[Brian C.],
Novelty detection in human tracking based on spatiotemporal oriented energies,
PR(48), No. 3, 2015, pp. 812-826.
Elsevier DOI 1412
Occlusion modeling BibRef

Long, Y.[Yang], Zhu, F.[Fan], Shao, L.[Ling],
Recognising occluded multi-view actions using local nearest neighbour embedding,
CVIU(144), No. 1, 2016, pp. 36-45.
Elsevier DOI 1604
Occlusion BibRef

Haritaoglu, I.[Ismail], Harwood, D.[David], Davis, L.S.[Larry S.],
W4: Real-Time Surveillance of People and Their Activities,
PAMI(22), No. 8, August 2000, pp. 809-830.
IEEE DOI 0010
Human Motion. Real-Time System. Recognizes typical events between people. Creates models of people so that tracking can proceed with occlusions and interactions. Locate the parts to create the models. BibRef

Davis, L.S.[Larry S.], Harwood, D.[David], Haritaoglu, I.[Ismail],
Ghost: A Human Body Part Labeling System Using Silhouettes,
ICPR98(Vol I: 77-82).
IEEE DOI BibRef 9800
And: DARPA98(229-235).
See also Appearance-based Body Model for Multiple People Tracking, An. BibRef

Haritaoglu, I.[Ismail], Harwood, D.[David], Davis, L.S.[Larry S.],
Active outdoor surveillance,
CIAP99(1096-1099).
IEEE DOI 9909
BibRef
Earlier:
W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People,
AFGR98(222-227).
IEEE DOI BibRef
And:
W4S: A real-time system for detecting and tracking people in 2 1/2-D,
ECCV98(I: 877).
Springer DOI BibRef
And:
W4: A Real Time System for Detecting and Tracking People,
CVPR98(962-962).
IEEE DOI BibRef

Park, S.H.[Sang-Ho], Aggarwal, J.K.,
Simultaneous tracking of multiple body parts of interacting persons,
CVIU(102), No. 1, April 2006, pp. 1-21.
Elsevier DOI 0604
BibRef
Earlier:
Semantic-level Understanding of Human Actions and Interactions using Event Hierarchy,
Non-Rigid04(12).
IEEE DOI 0502
BibRef
And:
Event semantics in two-person interactions,
ICPR04(IV: 227-230).
IEEE DOI 0409
BibRef
Earlier:
Segmentation and tracking of interacting human body parts under occlusion and shadowing,
Motion02(105-111).
IEEE DOI 0303
BibRef
Earlier:
Recognition of Human Interaction Using Multiple Features in Grayscale Images,
ICPR00(Vol I: 51-54).
IEEE DOI Or:
PDF File. 0009
Tracking; Body part; Human interaction; Occlusion; ARG; MMT BibRef

Aggarwal, J.K., Park, S.H.[Sang-Ho],
Human motion: modeling and recognition of actions and interactions,
3DPVT04(640-647).
IEEE DOI 0412
BibRef

Madabhushi, A., Aggarwal, J.K.,
A Bayesian Approach to Human Activity Recognition,
VS99(xx-yy). BibRef 9900

Wang, Y.[Yang], Mori, G.[Greg],
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin,
PAMI(33), No. 7, July 2011, pp. 1310-1323.
IEEE DOI 1106
BibRef
Earlier:
Max-margin Latent Dirichlet Allocation for Image Classification and Annotation,
BMVC11(xx-yy).
HTML Version. 1110
BibRef
Earlier:
Max-margin hidden conditional random fields for human action recognition,
CVPR09(872-879).
IEEE DOI 0906
BibRef

Wang, Y.[Yang], Mori, G.[Greg],
Human Action Recognition by Semilatent Topic Models,
PAMI(31), No. 10, October 2009, pp. 1762-1774.
IEEE DOI 0909
BibRef
And:
A Discriminative Latent Model of Object Classes and Attributes,
ECCV10(V: 155-168).
Springer DOI 1009

See also Discriminative Latent Models for Recognizing Contextual Group Activities. BibRef

Wang, Y.[Yang], Sabzmeydani, P.[Payam], Mori, G.[Greg],
Semi-Latent Dirichlet Allocation: A Hierarchical Model for Human Action Recognition,
HUMO07(240-254).
Springer DOI 0710
BibRef

Huang, Z.F.[Zhi Feng], Yang, W.L.[Wei-Long], Wang, Y.[Yang], Mori, G.[Greg],
Latent Boosting for Action Recognition,
BMVC11(xx-yy).
HTML Version. 1110
BibRef

Angelini, F., Fu, Z., Long, Y., Shao, L., Naqvi, S.M.A.[Syed Moeen Ali],
2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling,
MultMed(22), No. 6, June 2020, pp. 1433-1446.
IEEE DOI 2005
Feature extraction, Target tracking, Detectors, Skeleton, CCTV BibRef

Zou, Y.L.[Yu-Liang], Choi, J.[Jinwoo], Wang, Q.T.[Qi-Tong], Huang, J.B.[Jia-Bin],
Learning representational invariances for data-efficient action recognition,
CVIU(227), 2023, pp. 103597.
Elsevier DOI 2301
3D human pose and shape estimation, Self-supervised learning, Occlusion handling BibRef

Chen, Y.[Yang], Wang, L.[Ling], Hu, D.[Dekun], Cheng, H.[Hong],
Multi-view graph convolution network for the recognition of human action with spatial and temporal occlusion problems,
JVCIR(97), 2023, pp. 103957.
Elsevier DOI 2312
Human action recognition, Spatial-temporal occlusion, Multi-view, Graph network BibRef

Cheltha, J.N.[Jeba Nega], Sharma, C.[Chirag], Prashar, D.[Deepak], Khan, A.A.[Arfat Ahmad], Kadry, S.[Seifedine],
Enhanced human motion detection with hybrid RDA-WOA-based RNN and multiple hypothesis tracking for occlusion handling,
IVC(150), 2024, pp. 105234.
Elsevier DOI 2409
Human motion detection, Adapted canny edge detection, Modified mask R-CNN, RNN, Multiple hypothesis tracking, Instance segmentation BibRef


Wang, G.Z.[Guang-Zhi], Guo, Y.Y.[Yang-Yang], Xu, Z.W.[Zi-Wei], Kankanhalli, M.[Mohan],
Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness,
CVPR24(27970-27980)
IEEE DOI 2410
Extrapolation, Adaptation models, Art, Semantics, Object detection, Detectors BibRef

Yang, D.[Di], Wang, Y.H.[Yao-Hui], Dantcheva, A.[Antitza], Garattoni, L.[Lorenzo], Francesca, G.[Gianpiero], Brémond, F.[François],
Self-Supervised Video Pose Representation Learning for Occlusion-Robust Action Recognition,
FG21(1-5)
IEEE DOI 2303
Training, Representation learning, Target recognition, Face recognition, Gesture recognition, Robustness, Data models BibRef

Hussain, S.M.[S. Muzamil], Liu, L.[Liu], Xu, W.Q.[Wen-Qiang], Lu, C.W.[Ce-Wu],
FPHA-Afford: A Domain-Specific Benchmark Dataset for Occluded Object Affordance Estimation in Human-Object-Robot Interaction,
ICIP20(1416-1420)
IEEE DOI 2011
Estimation, Videos, Robots, Semantics, Task analysis, Machine learning, Feature extraction, Human-Object-Robot Interaction, FPHA-Afford BibRef

Possegger, H.[Horst], Mauthner, T.[Thomas], Roth, P.M.[Peter M.], Bischof, H.[Horst],
Occlusion Geodesics for Online Multi-object Tracking,
CVPR14(1306-1313)
IEEE DOI 1409
Multi-Object Tracking; Occlusion Geodesics; Online Tracking BibRef

Jargalsaikhan, I.[Iveel], Direkoglu, C.[Cem], Little, S.[Suzanne], O'Connor, N.E.[Noel E.],
An Evaluation of Local Action Descriptors for Human Action Classification in the Presence of Occlusion,
MMMod14(II: 56-67).
Springer DOI 1405
BibRef
Earlier: A1, A3, A2, A4:
Action recognition based on sparse motion trajectories,
ICIP13(3982-3985)
IEEE DOI 1402
Action recognition; Feature extraction; Sparse trajectories BibRef

Chen, L.C.[Li-Chih], Hsieh, J.W.[Jun-Wei], Chuang, C.H.[Chi-Hung], Huang, C.Y.[Chang-Yu], Chen, D.Y.,
Occluded human action analysis using dynamic manifold model,
ICPR12(1245-1248).
WWW Link. 1302
BibRef

Chapter on Motion -- Human Motion, Surveillance, Tracking, Surveillance, Activities continues in
Action Localization, Action Localisation .


Last update:Feb 17, 2026 at 20:06:16