Papers › Relation Modeling in Spatio-Temporal Action Localization

Relation Modeling in Spatio-Temporal Action Localization

15 Jun 2021arXiv:2106.08061archive 2025-07-28

Yutong Feng, Jianwen Jiang, Ziyuan Huang, Zhiwu Qing, Xiang Wang, Shiwei Zhang, Mingqian Tang, Yue Gao

This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action DetectionAction LocalizationSpatio-Temporal Action LocalizationTemporal Action Localization

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Spatio-Temporal Action Localization AVA-Kinetics RM (multi-scale, ensemble) val mAP 40.52 #4 of 7 Archive leaderboard report
Spatio-Temporal Action Localization AVA-Kinetics RM (multi-scale, ir-CSN-152) val mAP 37.95 #6 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections