AI Paper Atlas

Research map / Video / Action recognition

Language-based Action Concept Spaces Improve Video Self-Supervised Learning

Kanchana Ranasinghe, Michael S Ryoo

NeurIPS 2023 · Video › Action recognition · approach: Contrastive video representation learning · 7 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
add category-space concept distillation over CLIP with temporal modification (ablation)LSS · HMDB-51 linear probingtop-1 acc: 67.3 -> 68.5Improved
add description-space concept distillation (ablation)LSS · HMDB-51 linear probingtop-1 acc: 68.5 -> 69.0Improved
add concept alignment (ablation)LSS · HMDB-51 linear probingtop-1 acc: 69.0 -> 69.2Improved
add concept alignment (ablation)LSS · HMDB-51 zero-shottop-1 acc: 49.2 -> 49.5Improved
add category-space concept distillation (ablation)LSS · HMDB-51 zero-shottop-1 acc: 47.2 -> 48.8Improved
generic SSL (SVT) from CLIP init instead of language-aligned SSL (ablation)LSS · HMDB-51 linear probingtop-1 acc: 63.9 -> 62.2Hurt
remove uniform distribution prior (ablation)LSS · HMDB-51 zero-shottop-1 acc: 48.4 -> 33.4Hurt
remove uniform distribution prior (ablation)LSS · UCF-101 zero-shottop-1 acc: 71.1 -> 54.3Hurt
remove significance weight (ablation)LSS · HMDB-51 zero-shottop-1 acc: 48.4 -> 47.2Hurt
remove significance weight (ablation)LSS · UCF-101 zero-shottop-1 acc: 71.1 -> 70.3Hurt
add 2000 WordNet words to category space (ablation)LSS · HMDB-51 zero-shottop-1 acc: 49.5 -> 48.6Hurt
add 10K WordNet sentences to description space (ablation)LSS · HMDB-51 zero-shottop-1 acc: 49.5 -> 49.6No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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