-
Shuai Li, Duc Manh Vu, Juergen Gall, Learning Probabilistic Embeddings for Unsupervised Action Segmentation, ECCV2026. [code]
$\color{red} \text{Unsupervised}$ -
Linxiang Peng, Xinyao Qin, Jinhan Li, Di Yang, Jiangtao Wang, FIS-OT: Feature-Induced Optimal Transport for Unsupervised Action Segmentation, ICME2026. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Junxian Huang, Ruichu Cai, Hao Zhu, Juntao Fang, Boyan Xu, Weilin Chen, Zijian Li, Shenghua Gao, Hierarchical Action Learning for Weakly-Supervised Action Segmentation, CVPR2026. [pdf] [code]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Tieqiao Wang, Sinisa Todorovic, Timestamp Query Transformer for Temporal Action Segmentation, WACV2026. [pdf] [code]
$\color{magenta} \text{Timestep\ supervised}$
-
Ali Shah Ali, Syed Ahmed Mahmood, Mubin Saeed Andrey Konin, M. Zeeshan Zia, Quoc-Huy Tran, Joint Self-Supervised Video Alignment and Action Segmentation, ICCV2025. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Elena Bueno-Benito, Mariella Dimiccoli, CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation, ICCV2025. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Federico Spurio, Emad Bahrami, Gianpiero Francesca, Juergen Gall, Hierarchical Vector Quantization for Unsupervised Action Segmentation, AAAI2025. [pdf] [code]
$\color{red} \text{Unsupervised}$
-
Anchi Xu, Weishi Zheng, Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment, CVPR2024. [pdf] [code]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Ming Xu, Stephen Gould, Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation, CVPR2024. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Quoc-Huy Tran, Ahmed Mehmood, Muhammad Ahmed, Muhammad Naufil, Anas Zafar, Andrey Konin, M. Zeeshan Zia, Permutation-Aware Activity Segmentation via Unsupervised Frame-to-Segment Alignment, WACV2024. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Roy Hirsch, Regev Cohen, Tomer Golany, Daniel Freedman, Ehud Rivlin, Random Walks for Temporal Action Segmentation with Timestamp Supervision, WACV2024. [pdf] [code]
$\color{magenta} \text{Timestep\ supervised}$
- Fan Yang, Shigeyuki Odashima, Shoichi Masui, Shan Jiang, Is Weakly-supervised Action Segmentation Ready For Human Robot Interaction?No, Let's Improve it With Action-Union Learning, IROS2023.
[pdf]
$\color{magenta} \text{Timestep\ supervised}$
-
Yaser Souri, Yazan Abu Farha, Emad Bahrami, Gianpiero Francesca, Juergen Gall, Robust Action Segmentation from Timestamp Supervision, BMVC2022. [pdf] [code]
$\color{magenta} \text{Timestep\ supervised}$ -
Nadine Behrmann, S. Alireza Golestaneh, Zico Kolter, Juergen Gall, Mehdi Norooz, Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation, ECCV2022. [pdf] [code]
$\color{magenta} \text{Timestep\ supervised}$ -
Rahul Rahaman, Dipika Singhania, Alexandre Thiery, Angela Yao, A Generalized and Robust Framework for Timestamp Supervision in Temporal Action Segmentation, ECCV2022. [pdf]
$\color{magenta} \text{Timestep\ supervised}$ -
Zijia Lu, Ehsan Elhamifar. Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency, CVPR2022. [pdf] [code]
$\color{green} \text{Unordered\ transcript\ supervised}$ -
Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Chiho Choi, Behzad Dariush, Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos, CVPR2022. [pdf]
-
Sateesh Kumar, Sanjay Haresh, Awais Ahmed, Andrey Konin, M. Zeeshan Zia, Quoc-Huy Tran. Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering, CVPR2022. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Zexing Du, Xue Wang, Guoqing Zhou, Qing Wang. Fast and Unsupervised Action Boundary Detection for Action Segmentation, CVPR2022. [pdf]
-
Zhe Wang, Hao Chen, Xinyu Li, Chunhui Liu, Yuanjun Xiong, Joseph Tighe, Charless Fowlkes, SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation, WACV2022. [pdf]
$\color{red} \text{Unsupervised}$ -
Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos. Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos, WACV2022. [pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$
-
Nikita Dvornik, Isma Hadji, Konstantinos G. Derpanis, Animesh Garg, Allan D. Jepson. Drop-dtw: Aligning common signal between sequences while dropping outliers, NeuriPS2021. [pdf] [code]
-
AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo, Irfan Essa. Unsupervised Discovery of Actions in Instructional Videos, BMVC2021. [pdf]
$\color{red} \text{Unsupervised}$ -
Sirnam Swetha, Hilde Kuehne, Yogesh S Rawat, Mubarak Shah. Unsupervised discriminative embedding for sub-action learning in complex activitie, ICIP2021. [pdf]
$\color{red} \text{Unsupervised}$ -
JRosaura G. VidalMata, Walter J. Scheirer, Anna Kukleva, David Cox, Hilde Kuehne. Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences, WACV2021. [pdf]
$\color{red} \text{Unsupervised}$ -
M. Saquib Sarfraz, Naila Murray, Vivek Sharma, Ali Diba, Luc Van Gool, Rainer Stiefelhagen. Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation, CVPR2021. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Zhe Li, Yazan Arbu Farha, Juergen Gall. Temporal Action Segmentation from Timestamp Supervision, CVPR2021. [pdf] [code]
$\color{magenta} \text{Timestep\ supervised}$ -
Zijia Lu, Ehsan Elhamifar. Weakly-supervised action segmentation and alignment via transcript-aware union-of-subspaces learning, ICCV2021. [pdf] [code]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Xiaobin Chang, Frederick Tung, Greg Mori. Learning discriminative prototypes with dynamic time warping, CVPR2021. [pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Jun Li, Sinisa Todorovic. Action Shuffle Alternating Learning for Unsupervised Action Segmentation, CVPR2021. [pdf]
$\color{red} \text{Unsupervised}$ -
Jun Li, Sinisa Todorovic. Anchor-Constrained Viterbi for Set-Supervised Action Segmentation, CVPR2021. [pdf]
$\color{green} \text{Unordered\ transcript\ supervised}$ -
Yaser Souri, Yazan Abu Farha, Fabien Despinoy, Gianpiero Francesca, Juergen Gall. FIFA: Fast Inference Approximation for Action Segmentation, GCPR2021. [pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Yaser Souri, Mohsen Fayyaz, Luca Minciullo, Gianpiero Francesca, Juergen Gall. Fast Weakly Supervised Action Segmentation Using Mutual Consistency, PAMI2021. [pdf] [code]
$\color{blue} \text{Ordered\ transcript\ supervised}$
-
Jun Li, Sinisa Todorovic. Set-Constrained Viterbi for Set-Supervised Action Segmentation, CVPR2020. [pdf]
$\color{green} \text{Unordered\ transcript\ supervised}$ -
Mohsen Fayyaz, Jurgen Gall. Sct: Set constrained temporal transformer for set supervised action segmentation, CVPR2020. [pdf] [code]
$\color{green} \text{Unordered\ transcript\ supervised}$ -
Daniel Fried, Jean-Baptiste Alayrac,Phil Blunsom, Chris Dyer, Stephen Clark, Aida Nematzadeh. Learning to Segment Actions from Observation and Narration, ACL2020. [pdf] [code]
-
Jun Li, Sinisa Todorovic. Weakly Supervised Energy-Based Learning for Action Segmentation, ICCV2019. [pdf] [code]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Sathyanarayanan N. Aakur, Sudeep Sarkar. A perceptual prediction framework for self supervised event segmentation, CVPR2019. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Anna Kukleva, Hilde Kuehne, Fadime Sener, Juergen Gall. Unsupervised learning of action classes with continuous temporal embedding, CVPR2019. [pdf] [code]
$\color{red} \text{Unsupervised}$ -
Chien-Yi Chang, De-An Huang, Yanan Sui, Li Fei-Fei, Juan Carlos Niebles. D3tw: Discriminative differentiable dynamic time warping for weakly supervised action alignment and segmentation, CVPR2019. [pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Ehsan Elhamifar, Zwe Naing. Unsupervised Procedure Learning via Joint Dynamic Summarization, ICCV2019. [pdf]
$\color{red} \text{Unsupervised}$
-
Fadime Sener, Angela Yao. Unsupervised learning and segmentation of complex activities from video, CVPR2018. [pdf][code]
$\color{red} \text{Unsupervised}$ -
Alexander Richard, Hilde Kuehne, Ahsan Iqbal, Juergen Gall. Neuralnetwork-viterbi: A framework for weakly supervised video learning, CVPR2018. [pdf][code]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Alexander Richard, Hilde Kuehne, Juergen Gall. Action sets: Weakly supervised action segmentation without ordering constraints, CVPR2018. [pdf][code]
$\color{green} \text{Unordered\ transcript\ supervised}$ -
Li Ding, Chenliang Xu. Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment, CVPR2018. [pdf] [code]
$\color{blue} \text{Ordered\ transcript\ supervised}$
- Alexander Richard, Hilde Kuehne, Juergen Gall. Weakly supervised action learning with rnn based fine-to-coarse modeling, CVPR2017.
[pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$
-
Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal, Josef Sivic, Ivan Laptev, and Simon Lacoste-Julien. Unsupervised learning from narrated instruction videos, CVPR2016. [pdf]
$\color{red} \text{Unsupervised}$ -
De-An Huang, Feifei Li, Juan Carlos Niebles. Connectionist temporal modeling for weakly supervised action labeling, ECCV2016. [pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$
-
Ozan Sener, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena. Unsupervised Semantic Parsing of Video Collections, ICCV2015. [pdf]
$\color{red} \text{Unsupervised}$ -
Piotr Bojanowski, R. Lajugie, E Grave, Francois Bach, Ivan Laptev, Jean Ponce, Cordelia Schimid. Weakly-Supervised Alignment of Video With Text, ICCV2015. [pdf]
-
Piotr Bojanowski, R. Lajugie, Francois Bach, Ivan Laptev. Weakly supervised action labeling in videos under ordering constraints, ECCV2014. [pdf]
$\color{blue} \text{Ordered\ transcript\ supervised}$ -
Hamed Pirsiavash, Deva Ramanan. Parsing videos of actions with segmental grammars, CVPR2014. [pdf]
-
Nam N. Vo, Aaron F. Bobick. From Stochastic Grammar to Bayes Network: Probabilistic Parsing of Complex Activity, CVPR2014. [pdf][code]
- Hilde Kuehne, Ali Arslan, Thomas Serre. The language of actions: Recovering the syntax and semantics of goaldirected human activities, CVPR2014. [pdf]
- Sebastian Stein, Stephen J McKenna. Combining embedded accelerometers with computer vision for recognizing food preparation activities, In Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing. [pdf]
- Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal, Josef Sivic, Ivan Laptev, Simon Lacoste-Julien. Unsupervised learning from narrated instruction videos, CVPR2016. [pdf]
- Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis, David Fouhey, Ivan Laptev, Josef Sivic. Cross-task weakly supervised learning from instructional videos, CVPR2019. [pdf]