AI Paper Atlas

Research map / Video / Video segmentation and tracking

EPIC-SOUNDS: A Large-Scale Dataset of Actions That Sound

Jaesung Huh, Jacob Chalk, Evangelos Kazakos, Dima Damen, Andrew Zisserman

TPAMI 2025 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 34 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune backbone instead of linear probe (ablation)SSAST · EPIC-SOUNDS recognition (validation)top-1 accuracy: 28.74 -> 53.47Improved
fine-tune backbone instead of linear probe (ablation)ASF · EPIC-SOUNDS recognition (validation)top-1 accuracy: 45.53 -> 53.75Improved
add visual modality (TIM)ASF audio-only · EPIC-SOUNDS recognition (validation)top-1 accuracy: 53.75 -> 58.49Improved
add visual modality (MTCN)ASF audio-only · EPIC-SOUNDS recognition (entire test)top-1 accuracy: 54.86 -> 57.96Improved
add visual modality to ActionFormerActionFormer · EPIC-SOUNDS detection (validation)average mAP: 13.5 -> 14.5Improved
add visual modality to TriDetTriDet · EPIC-SOUNDS detection (validation)average mAP: 13.3 -> 14.8Improved
add visual modality to TriDetTriDet · EPIC-SOUNDS detection (detection test)average mAP: 12.6 -> 13.0Improved
add visual modality to ActionFormerActionFormer · EPIC-SOUNDS detection (entire test)average mAP: 11.5 -> 12.5Improved
use TriDet instead of ActionFormer, audio-onlydetection · EPIC-SOUNDS detection (validation)average mAP: 13.5 -> 13.3Mixed
use ActionFormer-AV instead of TriDet-AVaudio-visual detection · EPIC-SOUNDS detection (detection test)average mAP: 13.0 -> 13.6Mixed
fusion weight alpha 0.8 (ActionFormer) / 0.7 (TriDet), audio-dominant (ablation)audio-visual detection · EPIC-SOUNDS detectionaverage mAPImproved
human annotators vs ASF on audio-only recognitionaudio recognition · EPIC-SOUNDS recognition (validation subset, 412 clips)accuracy: 20.8% vs 21.1%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy