</> Code with Papers by Syntology

Papers › Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization

Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization

27 Jun 2021arXiv:2106.14118archive 2025-07-28

Anurag Bagchi, Jazib Mahmood, Dolton Fernandes, Ravi Kiran Sarvadevabhatla

State of the art architectures for untrimmed video Temporal Action Localization (TAL) have only considered RGB and Flow modalities, leaving the information-rich audio modality totally unexploited. Audio fusion has been explored for the related but arguably easier problem of trimmed (clip-level) action recognition. However, TAL poses a unique set of challenges. In this paper, we propose simple but effective fusion-based approaches for TAL. To the best of our knowledge, our work is the first to jointly consider audio and video modalities for supervised TAL. We experimentally show that our schemes consistently improve performance for state of the art video-only TAL approaches. Specifically, they help achieve new state of the art performance on large-scale benchmark datasets - ActivityNet-1.3 (54.34 mAP@0.5) and THUMOS14 (57.18 mAP@0.5). Our experiments include ablations involving multiple fusion schemes, modality combinations and TAL architectures. Our code, models and associated data are available at https://github.com/skelemoa/tal-hmo.

PaperPDFCode

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

Code

skelemoa/tal-hmo officialmentioned in papermentioned on GitHubpytorch 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 LocalizationAction RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization ActivityNet-1.3 AVFusion mAP 36.82 #12 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 AVFusion mAP IOU@0.5 54.34 #12 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 AVFusion mAP IOU@0.75 37.66 #12 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 AVFusion mAP IOU@0.95 8.93 #12 of 33 Archive leaderboard report
Temporal Action Localization THUMOS'14 AVFusion mAP IOU@0.5 57.18 #1 of 1 Archive leaderboard report
Temporal Action Localization THUMOS’14 AVFusion Avg mAP (0.3:0.7) 53.3 #22 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 AVFusion mAP IOU@0.3 70.1 #22 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 AVFusion mAP IOU@0.4 64.9 #22 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 AVFusion mAP IOU@0.5 57.1 #22 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 AVFusion mAP IOU@0.6 45.4 #22 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 AVFusion mAP IOU@0.7 28.8 #22 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