Papers › DCAN: Improving Temporal Action Detection via Dual Context Aggregation

DCAN: Improving Temporal Action Detection via Dual Context Aggregation

7 Dec 2021arXiv:2112.03612archive 2025-07-28

Guo Chen, Yin-Dong Zheng, LiMin Wang, Tong Lu

Temporal action detection aims to locate the boundaries of action in the video. The current method based on boundary matching enumerates and calculates all possible boundary matchings to generate proposals. However, these methods neglect the long-range context aggregation in boundary prediction. At the same time, due to the similar semantics of adjacent matchings, local semantic aggregation of densely-generated matchings cannot improve semantic richness and discrimination. In this paper, we propose the end-to-end proposal generation method named Dual Context Aggregation Network (DCAN) to aggregate context on two levels, namely, boundary level and proposal level, for generating high-quality action proposals, thereby improving the performance of temporal action detection. Specifically, we design the Multi-Path Temporal Context Aggregation (MTCA) to achieve smooth context aggregation on boundary level and precise evaluation of boundaries. For matching evaluation, Coarse-to-fine Matching (CFM) is designed to aggregate context on the proposal level and refine the matching map from coarse to fine. We conduct extensive experiments on ActivityNet v1.3 and THUMOS-14. DCAN obtains an average mAP of 35.39% on ActivityNet v1.3 and reaches mAP 54.14% at IoU@0.5 on THUMOS-14, which demonstrates DCAN can generate high-quality proposals and achieve state-of-the-art performance. We release the code at https://github.com/cg1177/DCAN.

PaperPDFCode

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

Code

cg1177/dcan officialmentioned in papermentioned on GitHubpytorchApache-2.0 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 DetectionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization ActivityNet-1.3 DCAN (TSN features) mAP 35.39 #20 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 DCAN (TSN features) mAP IOU@0.5 51.78 #20 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 DCAN (TSN features) mAP IOU@0.75 35.98 #20 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 DCAN (TSN features) mAP IOU@0.95 9.45 #20 of 33 Archive leaderboard report
Temporal Action Localization THUMOS’14 DCAN (TSN features) Avg mAP (0.3:0.7) 52.3 #24 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DCAN (TSN features) mAP IOU@0.3 68.2 #24 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DCAN (TSN features) mAP IOU@0.4 62.7 #24 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DCAN (TSN features) mAP IOU@0.5 54.1 #24 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DCAN (TSN features) mAP IOU@0.6 43.9 #24 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 DCAN (TSN features) mAP IOU@0.7 32.6 #24 of 42 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