Papers › Harnessing Temporal Causality for Advanced Temporal Action Detection

Harnessing Temporal Causality for Advanced Temporal Action Detection

25 Jul 2024arXiv:2407.17792archive 2025-07-28

Shuming Liu, Lin Sui, Chen-Lin Zhang, Fangzhou Mu, Chen Zhao, Bernard Ghanem

As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries. Over the years, various networks, including convolutions, graphs, and transformers, have been explored for effective temporal modeling for TAD. However, these modules typically treat past and future information equally, overlooking the crucial fact that changes in action boundaries are essentially causal events. Inspired by this insight, we propose leveraging the temporal causality of actions to enhance TAD representation by restricting the model's access to only past or future context. We introduce CausalTAD, which combines causal attention and causal Mamba to achieve state-of-the-art performance on multiple benchmarks. Notably, with CausalTAD, we ranked 1st in the Action Recognition, Action Detection, and Audio-Based Interaction Detection tracks at the EPIC-Kitchens Challenge 2024, as well as 1st in the Moment Queries track at the Ego4D Challenge 2024. Our code is available at https://github.com/sming256/OpenTAD/.

PaperPDFCode

Code

sming256/OpenTAD officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Action DetectionAction RecognitionMambaMoment QueriesVideo Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionMambaSoftmax

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