Papers › FASTER Recurrent Networks for Efficient Video Classification

FASTER Recurrent Networks for Efficient Video Classification

10 Jun 2019arXiv:1906.04226archive 2025-07-28

Linchao Zhu, Laura Sevilla-Lara, Du Tran, Matt Feiszli, Yi Yang, Heng Wang

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10x? while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.

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 ClassificationAction RecognitionClassificationGeneral ClassificationVideo Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 FASTER32 Acc@1 75.1 #157 of 207 Archive leaderboard report
Action Classification Kinetics-400 FASTER16 w/o sp Acc@1 71.7 #177 of 207 Archive leaderboard report
Action Recognition HMDB-51 FASTER32 (Kinetics pretrain) Average accuracy of 3 splits 75.7 #38 of 77 Archive leaderboard report
Action Recognition UCF101 FASTER32 3-fold Accuracy 96.9 #29 of 91 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