16.7.4.6.2 Action Segmentation

Shi, Q.F.[Qin-Feng], Cheng, L.[Li], Wang, L.[Li], Smola, A.J.[Alex J.],
Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models,
IJCV(93), No. 1, May 2011, pp. 22-32.
WWW Link. 1104
BibRef
Earlier: A1, A3, A2, A4:
Discriminative human action segmentation and recognition using semi-Markov model,
CVPR08(1-8).
IEEE DOI 0806
BibRef

Wu, C., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Krähenbühl, P.,
Compressed Video Action Recognition,
CVPR18(6026-6035)
IEEE DOI 1812
Image coding, Video compression, Training, Optical imaging, Streaming media BibRef

Samadani, A.A.[Ali-Akbar], Ghodsi, A.[Ali], Kulic, D.[Dana],
Discriminative functional analysis of human movements,
PRL(34), No. 15, 2013, pp. 1829-1839.
Elsevier DOI 1309
Human movement time-series analysis BibRef

Lin, J.F.S., Karg, M., Kulic, D.,
Movement Primitive Segmentation for Human Motion Modeling: A Framework for Analysis,
HMS(46), No. 3, June 2016, pp. 325-339.
IEEE DOI 1605
Algorithm design and analysis BibRef

Hoai, M.[Minh], de la Torre, F.[Fernando],
Max-Margin Early Event Detectors,
IJCV(107), No. 2, April 2014, pp. 191-202.
WWW Link. 1404
BibRef
Earlier: CVPR12(2863-2870).
IEEE DOI 1208
Award, CVPR, Student. BibRef

Wang, Y., Hoai, M.,
Pulling Actions out of Context: Explicit Separation for Effective Combination,
CVPR18(7044-7053)
IEEE DOI 1812
Training, Feature extraction, Context modeling, Cameras, Lighting, Loss measurement, Video sequences BibRef

Hoai, M.[Minh], Lan, Z.Z.[Zhen-Zhong], de la Torre, F.[Fernando],
Joint segmentation and classification of human actions in video,
CVPR11(3265-3272).
IEEE DOI 1106
BibRef

Wang, B.[Boyu], Hoai, M.[Minh],
Back to the beginning: Starting point detection for early recognition of ongoing human actions,
CVIU(175), 2018, pp. 24-31.
Elsevier DOI 1812
Action early recognition, Online action detection, Event detection BibRef

Taralova, E.[Ekaterina], de la Torre, F.[Fernando], Hebert, M.[Martial],
Source constrained clustering,
ICCV11(1927-1934).
IEEE DOI 1201
Quantizing data from different sources. Cluster actions, not cluster subjects. BibRef

Panagiotakis, C.[Costas], Papoutsakis, K.E.[Konstantinos E.], Argyros, A.A.[Antonis A.],
A graph-based approach for detecting common actions in motion capture data and videos,
PR(79), 2018, pp. 1-11.
Elsevier DOI 1804
Common action detection, Video co-segmentation, Temporal action co-segmentation, Dynamic Time Warping BibRef

Zeng, X.X.[Xun-Xun], Chen, F.[Fei], Wang, M.Q.[Mei-Qing],
Shape group Boltzmann machine for simultaneous object segmentation and action classification,
PRL(111), 2018, pp. 43-50.
Elsevier DOI 1808
Deep Boltzmann machine, Shape prior, Object segmentation, Classification, Transformation invariance BibRef

Yan, Y.[Yan], Xu, C.L.[Chen-Liang], Cai, D.[Dawen], Corso, J.J.[Jason J.],
A Weakly Supervised Multi-task Ranking Framework for Actor-Action Semantic Segmentation,
IJCV(128), No. 5, May 2020, pp. 1414-1432.
Springer DOI 2005
BibRef
Earlier:
Weakly Supervised Actor-Action Segmentation via Robust Multi-task Ranking,
CVPR17(1022-1031)
IEEE DOI 1711
Optimization, Robustness, Semantics, Support vector machines, Training, Videos BibRef

Xu, C.L.[Chen-Liang], Hsieh, S.H.[Shao-Hang], Xiong, C.M.[Cai-Ming], Corso, J.J.[Jason J.],
Can humans fly? Action understanding with multiple classes of actors,
CVPR15(2264-2273)
IEEE DOI 1510
BibRef

Chen, J.[Jie], Li, Z.H.[Zhi-Heng], Luo, J.B.[Jie-Bo], Xu, C.L.[Chen-Liang],
Learning a Weakly-Supervised Video Actor-Action Segmentation Model With a Wise Selection,
CVPR20(9898-9908)
IEEE DOI 2008
Training, Motion segmentation, Legged locomotion, Task analysis, Computational modeling, Proposals BibRef

Xu, C.L.[Chen-Liang], Ding, L.[Li],
Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment,
CVPR18(6508-6516)
IEEE DOI 1812
Videos, Hidden Markov models, Training, Task analysis, Decoding, Computational modeling, Recurrent neural networks BibRef

Qian, H.W.[Hang-Wei], Pan, S.J.L.[Sinno Jia-Lin], Miao, C.Y.[Chun-Yan],
Weakly-supervised sensor-based activity segmentation and recognition via learning from distributions,
AI(292), 2021, pp. 103429.
Elsevier DOI 2102
Human activity recognition, Sensor readings segmentation, Kernel mean embedding BibRef

Sun, X.[Xiao], Long, X.[Xiang], He, D.L.[Dong-Liang], Wen, S.L.[Shi-Lei], Lian, Z.H.[Zhou-Hui],
VSRNet: End-to-end video segment retrieval with text query,
PR(119), 2021, pp. 108027.
Elsevier DOI 2106
Video segment retrieval, Video retrieval, Description localization BibRef

Ji, L.[Lei], Wu, C.[Chenfei], Zhou, D.[Daisy], Yan, K.[Kun], Cui, E.[Edward], Chen, X.L.[Xi-Lin], Duan, N.[Nan],
Learning Temporal Video Procedure Segmentation from an Automatically Collected Large Dataset,
WACV22(2733-2742)
IEEE DOI 2202
Measurement, TV, Convolution, Annotations, Computational modeling, Transformers, Datasets, Evaluation and Comparison of Vision Algorithms Vision and Languages BibRef

Park, J.[Junyong], Kim, D.[Daekyum], Huh, S.[Sejoon], Jo, S.[Sungho],
Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction,
PR(129), 2022, pp. 108764.
Elsevier DOI 2206
Action segmentation, Temporal segmentation, Video understanding BibRef

Gao, H.B.[Hong-Bo], Lv, C.[Chen], Zhang, T.[Tong], Zhao, H.F.[Hong-Fei], Jiang, L.[Lei], Zhou, J.J.[Jun-Jie], Liu, Y.C.[Yu-Chao], Huang, Y.[Yi], Han, C.[Chao],
A Structure Constraint Matrix Factorization Framework for Human Behavior Segmentation,
Cyber(52), No. 12, December 2022, pp. 12978-12988.
IEEE DOI 2212
Clustering algorithms, Image segmentation, Principal component analysis, Motion segmentation, Optimization, structure constraint BibRef

Chen, Y.Z.[Yun-Ze], Chen, M.J.[Meng-Juan], Gu, Q.Y.[Qing-Yi],
Class-wise boundary regression by uncertainty in temporal action detection,
IET-IPR(16), No. 14, 2022, pp. 3854-3862.
DOI Link 2212
BibRef

Aziere, N.[Nicolas], Todorovic, S.[Sinisa],
Multistage temporal convolution transformer for action segmentation,
IVC(128), 2022, pp. 104567.
Elsevier DOI 2212
Action segmentation, Video understanding, Full supervision, Transformer network, Hybrid models, CNNs BibRef

Rahaman, R.[Rahul], Singhania, D.[Dipika], Thiery, A.[Alexandre], Yao, A.[Angela],
A Generalized and Robust Framework for Timestamp Supervision in Temporal Action Segmentation,
ECCV22(IV:279-296).
Springer DOI 2211
BibRef

Ding, G.D.[Guo-Dong], Yao, A.[Angela],
Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation,
ECCV22(XXXV:17-32).
Springer DOI 2211
BibRef

Behrmann, N.[Nadine], Golestaneh, S.A.[S. Alireza], Kolter, Z.[Zico], Gall, J.[Jürgen], Noroozi, M.[Mehdi],
Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation,
ECCV22(XXXV:52-68).
Springer DOI 2211
BibRef

Ishihara, K.[Kenta], Nakano, G.[Gaku], Inoshita, T.[Tetsuo],
MCFM: Mutual Cross Fusion Module for Intermediate Fusion-Based Action Segmentation,
ICIP22(1701-1705)
IEEE DOI 2211
Measurement, Image segmentation, Action segmentation, feature fusion, mutual cross fusion module, human-related feature BibRef

Sun, Z.N.[Zhao-Ning], Messikommer, N.[Nico], Gehrig, D.[Daniel], Scaramuzza, D.[Davide],
ESS: Learning Event-Based Semantic Segmentation from Still Images,
ECCV22(XXXIV:341-357).
Springer DOI 2211
BibRef

Li, C.C.[Cong-Cong], Wang, X.[Xinyao], Wen, L.Y.[Long-Yin], Hong, D.X.[De-Xiang], Luo, T.J.[Tie-Jian], Zhang, L.[Libo],
End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection,
CVPR22(13947-13956)
IEEE DOI 2210
Representation learning, Training, Annotations, Shape, Machine vision, Video sequences, Feature extraction, Vision applications and systems BibRef

Tang, J.Q.[Jia-Qi], Liu, Z.Y.[Zhao-Yang], Qian, C.[Chen], Wu, W.[Wayne], Wang, L.M.[Li-Min],
Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection,
CVPR22(3345-3354)
IEEE DOI 2210
Representation learning, Codes, Aggregates, Semantics, Benchmark testing, Pattern recognition, Action and event recognition BibRef

Du, Z.X.[Ze-Xing], Wang, X.[Xue], Zhou, G.Q.[Guo-Qing], Wang, Q.[Qing],
Fast and Unsupervised Action Boundary Detection for Action Segmentation,
CVPR22(3313-3322)
IEEE DOI 2210
Training, Clustering algorithms, Real-time systems, Pattern recognition, Proposals, Task analysis, Action and event recognition BibRef

Kang, H.[Hyolim], Kim, J.[Jinwoo], Kim, T.[Taehyun], Kim, S.J.[Seon Joo],
UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection,
CVPR22(20041-20050)
IEEE DOI 2210
Computational modeling, Semantics, Benchmark testing, Pattern recognition, Task analysis, Action and event recognition, Video analysis and understanding BibRef

Kumar, S.[Sateesh], Haresh, S.[Sanjay], Ahmed, A.[Awais], Konin, A.[Andrey], Zia, M.Z.[M. Zeeshan], Tran, Q.H.[Quoc-Huy],
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering,
CVPR22(20142-20153)
IEEE DOI 2210
Representation learning, Visualization, Video on demand, Memory management, Pattern recognition, Task analysis, Self- semi- meta- Video analysis and understanding BibRef

Dimiccoli, M.[Mariella], Garrido, L.[Lluís], Rodriguez-Corominas, G.[Guillem], Wendt, H.[Herwig],
Graph Constrained Data Representation Learning for Human Motion Segmentation,
ICCV21(1440-1449)
IEEE DOI 2203
Analytical models, Dictionaries, Computational modeling, Motion segmentation, Transfer learning, Benchmark testing, grouping and shape BibRef

Ahn, H.[Hyemin], Lee, D.[Dongheui],
Refining Action Segmentation with Hierarchical Video Representations,
ICCV21(16282-16290)
IEEE DOI 2203
Training, Codes, Computational modeling, Refining, Predictive models, Feature extraction, Action and behavior recognition, Video analysis and understanding BibRef

Lu, Z.J.[Zi-Jia], Elhamifar, E.[Ehsan],
Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency,
CVPR22(19871-19881)
IEEE DOI 2210
Training, Location awareness, Shape, Pattern recognition, Reliability, Task analysis, Action and event recognition, Video analysis and understanding BibRef

Lu, Z.J.[Zi-Jia], Elhamifar, E.[Ehsan],
Weakly-Supervised Action Segmentation and Alignment via Transcript-Aware Union-of-Subspaces Learning,
ICCV21(8065-8075)
IEEE DOI 2203
Training, Real-time systems, Inference algorithms, Videos, Video analysis and understanding, grouping and shape BibRef

Li, J.[Jun], Todorovic, S.[Sinisa],
Action Shuffle Alternating Learning for Unsupervised Action Segmentation,
CVPR21(12623-12631)
IEEE DOI 2111
Training, Viterbi algorithm, Computational modeling, Hidden Markov models, Videos BibRef

Shen, Y.[Yuhan], Wang, L.[Lu], Elhamifar, E.[Ehsan],
Learning to Segment Actions from Visual and Language Instructions via Differentiable Weak Sequence Alignment,
CVPR21(10151-10160)
IEEE DOI 2111
Location awareness, Visualization, Computational modeling, Prototypes, Linguistics, Feature extraction BibRef

Ishikawa, Y.[Yuchi], Kasai, S.[Seito], Aoki, Y.[Yoshimitsu], Kataoka, H.[Hirokatsu],
Alleviating Over-segmentation Errors by Detecting Action Boundaries,
WACV21(2321-2330)
IEEE DOI 2106
Segmenting actions. Smoothing methods, Refining, Feature extraction, Task analysis BibRef

Vignolo, A.[Alessia], Noceti, N.[Nicoletta], Sciutti, A.[Alessandra], Odone, F.[Francesca], Sandini, G.[Giulio],
Learning dictionaries of kinematic primitives for action classification,
ICPR21(5965-5972)
IEEE DOI 2105
Visualization, Dictionaries, Motion segmentation, Kinematics, Encoding, Synchronization BibRef

Li, J.[Jun], Todorovic, S.[Sinisa],
Anchor-Constrained Viterbi for Set-Supervised Action Segmentation,
CVPR21(9801-9810)
IEEE DOI 2111
BibRef
Earlier:
Set-Constrained Viterbi for Set-Supervised Action Segmentation,
CVPR20(10817-10826)
IEEE DOI 2008
Training, Shortest path problem, Monte Carlo methods, Viterbi algorithm, Hidden Markov models, Estimation, Benchmark testing. Neural networks, Feature extraction, TV, Task analysis BibRef

Huang, Y., Sugano, Y., Sato, Y.,
Improving Action Segmentation via Graph-Based Temporal Reasoning,
CVPR20(14021-14031)
IEEE DOI 2008
Task analysis, Convolution, Cognition, Predictive models, Cameras, Glass BibRef

Bai, R., Zhao, Q., Zhou, S., Li, Y., Zhao, X., Wang, J.,
Continuous Action Recognition and Segmentation in Untrimmed Videos,
ICPR18(2534-2539)
IEEE DOI 1812
Videos, Feature extraction, Motion segmentation, Hidden Markov models, Pattern recognition, Task analysis, Computer vision BibRef

Jain, H., Harit, G.,
Unsupervised Temporal Segmentation of Human Action Using Community Detection,
ICIP18(1892-1896)
IEEE DOI 1809
Videos, Motion segmentation, Training, Indexes, Hidden Markov models, Clustering algorithms, Shape, community detection, unsupervised action segmentation BibRef

Kuehne, H.[Hilde], Gall, J.[Juergen], Serre, T.[Thomas],
An end-to-end generative framework for video segmentation and recognition,
WACV16(1-8)
IEEE DOI 1606
Data models BibRef

Li, S., Li, K., Fu, Y.,
Temporal Subspace Clustering for Human Motion Segmentation,
ICCV15(4453-4461)
IEEE DOI 1602
Clustering methods BibRef

Lu, J.[Jiasen], Xu, R.[Ran], Corso, J.J.[Jason J.],
Human action segmentation with hierarchical supervoxel consistency,
CVPR15(3762-3771)
IEEE DOI 1510
BibRef

Kim, Y.[Yelin], Chen, J.X.[Ji-Xu], Chang, M.C.[Ming-Ching], Wang, X.[Xin], Provost, E.M., Lyu, S.W.[Si-Wei],
Modeling transition patterns between events for temporal human action segmentation and classification,
FG15(1-8)
IEEE DOI 1508
dynamic programming BibRef

Ghodrati, A.[Amir], Pedersoli, M.[Marco], Tuytelaars, T.[Tinne],
Coupling video segmentation and action recognition,
WACV14(618-625)
IEEE DOI 1406
BibRef

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Accumulation Methods, Motion Histograms for Human Action Recognition .