Weakly supervised coarse-to-fine learning for human action segmentation in HCI videos
- 1 December 2022
- journal article
- research article
- Published by Springer Science and Business Media LLC in Multimedia Tools and Applications
- Vol. 82 (9), 12977-12993
- https://doi.org/10.1007/s11042-022-13792-1
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62076016, 61972016, 62176260)
- Beijing Nova Program of Science and Technology (Z191100001119106, Z211100002121147)
- Beijing Municipal Natural Science Foundation (4202065)
- Fundamental Research Funds for the Central Universities (2022YJSJD11, J210409)
This publication has 41 references indexed in Scilit:
- A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Unsupervised Learning from Narrated Instruction VideosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- End-to-End Learning of Action Detection from Frame Glimpses in VideosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data is Continuous and Weakly LabelledPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Temporal Action Detection Using a Statistical Language ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Weakly Supervised Action Labeling in Videos under Ordering ConstraintsLecture Notes in Computer Science, 2014
- Action Recognition with Improved TrajectoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- A survey on activity recognition and behavior understanding in video surveillanceThe Visual Computer, 2012
- An Efficient Viterbi DecoderInternational Journal of Computer Science, Engineering and Applications, 2012
- Improving the Fisher Kernel for Large-Scale Image ClassificationLecture Notes in Computer Science, 2010