Library

Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019

This notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, dense-captioning events in videos, and spatio-temporal action localization.

cs.CVComputer Science
Source

Paper

Similar papers

CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)Xiang Wang, Baiteng Ma, Zhiwu Qing et al.2020 · arXiv (Cornell University) In Library
Temporal Activity Detection in Untrimmed Videos with Recurrent Neural NetworksAlberto Montes, Amaia Salvador, Santiago Pascual et al.2016 · Neural Information Processing Systems · 109 citations In Library
Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)Zhiwu Qing, Xiang Wang, Yongpeng Sang et al.2020 · arXiv (Cornell University) In Library
DstNet: deep spatial-temporal network for real-time action recognition and localisation in untrimmed videoZhi Liu, Junting Li, Xian Wang2022 · International Journal of Wireless and Mobile Computing In Library
Foreground-Action Consistency Network for Weakly Supervised Temporal Action LocalizationLinjiang Huang, Liang Wang, Hongsheng Li2021 · arXiv (Cornell University) · 93 citations In Library
PAND: Precise Action Recognition on Naturalistic DrivingHangyue Zhao, Yuchao Xiao, Yanyun Zhao2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 3 citations In Library
Multi-Instance Multi-Label Action Recognition and Localization Based on Spatio-Temporal Pre-Trimming for Untrimmed VideosXiaoyu Zhang, Haichao Shi, Changsheng Li et al.2020 · Proceedings of the AAAI Conference on Artificial Intelligence · 37 citations In Library
ActionBytes: Learning From Trimmed Videos to Localize ActionsMihir Jain, Amir Ghodrati, Cees G. M. Snoek2020 · Computer Vision and Pattern Recognition · 53 citations In Library
Foreground-Action Consistency Network for Weakly Supervised Temporal Action LocalizationLinjiang Huang, Liang Wang, Hongsheng Li2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) In Library
Improved Action Recognition with Separable Spatio-Temporal Attention Using Alternative Skeletal and Video Pre-ProcessingPau Climent-Pérez, Francisco Flórez‐Revuelta2021 · Sensors · 15 citations In Library
© 2026 NYSGPT2525 LLC