Papers › Temporal Attentive Alignment for Video Domain Adaptation

Temporal Attentive Alignment for Video Domain Adaptation

26 May 2019arXiv:1905.10861archive 2025-07-28

Min-Hung Chen, Zsolt Kira, Ghassan AlRegib

Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose a larger-scale dataset with larger domain discrepancy: UCF-HMDB_full. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets. The code and data are released at http://github.com/cmhungsteve/TA3N.

PaperPDFCode

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

Code

cmhungsteve/TA3N officialmentioned in papermentioned on GitHubpytorchMIT report
jonmun/EPIC-KITCHENS-100_UDA_TA3N mentioned on GitHubpytorchMIT report
mustafa1728/TA3N-Lightning mentioned on GitHubpytorchMIT report
olivesgatech/TA3N mentioned on GitHubpytorchMIT 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

Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation HMDBfull-to-UCF TA3N Accuracy 81.79 #2 of 5 Archive leaderboard report
Domain Adaptation HMDBsmall-to-UCF TA3N Accuracy 99.47 #1 of 3 Archive leaderboard report
Domain Adaptation Olympic-to-HMDBsmall TA3N Accuracy 92.92 #1 of 3 Archive leaderboard report
Domain Adaptation UCF-to-HMDBfull TA3N Accuracy 78.33 #2 of 5 Archive leaderboard report
Domain Adaptation UCF-to-HMDBsmall TA3N Accuracy 99.33 #1 of 3 Archive leaderboard report
Domain Adaptation UCF-to-Olympic TA3N Accuracy 98.15 #1 of 3 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