Papers › MiniROAD: Minimal RNN Framework for Online Action Detection
MiniROAD: Minimal RNN Framework for Online Action Detection
Joungbin An, Hyolim Kang, Su Ho Han, Ming-Hsuan Yang, Seon Joo Kim
Online Action Detection (OAD) is the task of identifying actions in streaming videos without access to future frames. Much effort has been devoted to effectively capturing long-range dependencies, with transformers receiving the spotlight for their ability to capture long-range temporal structures. In contrast, RNNs have received less attention lately, due to their lower performance compared to recent methods that utilize transformers. In this paper, we investigate the underlying reasons for the inferior performance of RNNs compared to transformer-based algorithms. Our findings indicate that the discrepancy between training and inference is the primary hindrance to the effective training of RNNs. To address this, we propose applying non-uniform weights to the loss computed at each time step, which allows the RNN model to learn from the predictions made in an environment that better resembles the inference stage. Extensive experiments on three benchmark datasets, THUMOS, TVSeries, and FineAction demonstrate that a minimal RNN-based model trained with the proposed methodology performs equally or better than the existing best methods with a significant increase in efficiency. The code is available at https://github.com/jbistanbul/MiniROAD.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Online Action Detection | FineAction | MiniROAD | mAP | 37.1 | #1 of 1 | Archive leaderboard | report |
| Online Action Detection | THUMOS'14 | MiniROAD | MFLOPs per pred | 15.8 | #2 of 15 | Archive leaderboard | report |
| Online Action Detection | THUMOS'14 | MiniROAD | mAP | 71.8 | #2 of 15 | Archive leaderboard | report |
| Online Action Detection | TVSeries | MiniROAD | mCAP | 89.6 | #2 of 13 | 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