AI Paper Atlas

Research map / Video / Action recognition

Listen to Look: Action Recognition by Previewing Audio

Ruohan Gao, Tae-Hyun Oh, Kristen Grauman, Lorenzo Torresani

CVPR 2020 · Video › Action recognition · approach: Disentangled action recognition · 269 citations (OpenAlex)

Check 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
Use iterative attention-based moment selection instead of dense prediction aggregationImgAud-Skimming · ActivityNetaccuracy (%): 66.3 -> 70.3Improved
Use iterative attention-based moment selection instead of dense prediction aggregationImgAud-Skimming · Mini-Sports1Maccuracy (%): 37.3 -> 39.2Improved
Use context-aware moment selection instead of selecting the top confidence clipsImgAud-Skimming · ActivityNetaccuracy (%): 69.1 -> 70.3Improved
Use context-aware moment selection instead of selecting the top confidence clipsImgAud-Skimming · Mini-Sports1Maccuracy (%): 38.4 -> 39.2Improved
Replace recurrent iterative queries with a single query (ablation)ImgAud-Skimming · ActivityNetaccuracy (%): 70.3 -> 67.5Hurt
Replace recurrent iterative queries with a single query (ablation)ImgAud-Skimming · Mini-Sports1Maccuracy (%): 39.2 -> 38.0Hurt
Process all image-audio features sequentially rather than selecting useful moments (ablation)ImgAud-Skimming · ActivityNetaccuracy (%): 70.3 -> 63.5Hurt
Process all image-audio features sequentially rather than selecting useful moments (ablation)ImgAud-Skimming · Mini-Sports1Maccuracy (%): 39.2 -> 34.1Hurt
Use image-audio indexing with R(2+1)D-152 recognition instead of dense evaluationImgAud-Skimming · ActivityNetmAP: 88.9 -> 88.5Hurt
Use image-audio indexing with R(2+1)D-152 recognition instead of dense evaluationImgAud-Skimming · ActivityNetTFLOPs: 25.9 -> 1.31Improved
Use R(2+1)D-152 features for both indexing and recognition instead of dense evaluationImgAud-Skimming · ActivityNetmAP: 88.9 -> 89.9Improved
Use R(2+1)D-152 features for both indexing and recognition instead of dense evaluationImgAud-Skimming · ActivityNetTFLOPs: 25.9 -> 2.64Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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