Papers › Dance with Flow: Two-in-One Stream Action Detection

Dance with Flow: Two-in-One Stream Action Detection

1 Apr 2019CVPR 2019 6arXiv:1904.00696archive 2025-07-28

Jiaojiao Zhao, Cees G. M. Snoek

The goal of this paper is to detect the spatio-temporal extent of an action. The two-stream detection network based on RGB and flow provides state-of-the-art accuracy at the expense of a large model-size and heavy computation. We propose to embed RGB and optical-flow into a single two-in-one stream network with new layers. A motion condition layer extracts motion information from flow images, which is leveraged by the motion modulation layer to generate transformation parameters for modulating the low-level RGB features. The method is easily embedded in existing appearance- or two-stream action detection networks, and trained end-to-end. Experiments demonstrate that leveraging the motion condition to modulate RGB features improves detection accuracy. With only half the computation and parameters of the state-of-the-art two-stream methods, our two-in-one stream still achieves impressive results on UCF101-24, UCFSports and J-HMDB.

PaperPDFConference PDFCode

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

Code

jiaozizhao/Two-in-One-ActionDetection 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 DetectionOptical Flow EstimationVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection J-HMDB Two-in-one Two Stream Video-mAP 0.5 74.74 #16 of 18 Archive leaderboard report
Action Detection J-HMDB Two-in-one Video-mAP 0.5 57.96 #17 of 18 Archive leaderboard report
Action Detection UCF Sports Two-in-one Two Stream Video-mAP 0.5 96.52 #6 of 7 Archive leaderboard report
Action Detection UCF Sports Two-in-one Video-mAP 0.5 92.74 #7 of 7 Archive leaderboard report
Action Detection UCF101-24 Two-in-one Two Stream Video-mAP 0.2 78.48 #17 of 19 Archive leaderboard report
Action Detection UCF101-24 Two-in-one Two Stream Video-mAP 0.5 50.30 #17 of 19 Archive leaderboard report
Action Detection UCF101-24 Two-in-one Video-mAP 0.2 75.48 #18 of 19 Archive leaderboard report
Action Detection UCF101-24 Two-in-one Video-mAP 0.5 48.31 #18 of 19 Archive leaderboard report
Action Recognition UCF101 two-in-one two stream 3-fold Accuracy 92 #65 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