AI Paper Atlas

Research map / Video / Action recognition

AIM: Adapting Image Models for Efficient Video Action Recognition

Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, Mu Li

ICLR 2023 · Video › Action recognition · approach: Disentangled action recognition · 61 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 spatial adapters to the frozen space-only model (ablation)ViT-B/16 IN-21K on Something-Something-v2 · Something-Something-v2Top-1: 15.1 -> 36.7Improved
Add temporal adaptation to spatial adaptation (ablation)ViT-B/16 IN-21K on Something-Something-v2 · Something-Something-v2Top-1: 36.7 -> 61.2Improved
Add joint adaptation to spatial and temporal adaptation (ablation)ViT-B/16 IN-21K on Something-Something-v2 · Something-Something-v2Top-1: 61.2 -> 62.0Improved
Replace IN-21K image pretraining with CLIP pretraining (ablation)AIM ViT-B/16 on Something-Something-v2 · Something-Something-v2Top-1: 62.0 -> 66.4Improved
Fully finetune the space-only model instead of freezing it (ablation)ViT-B/16 IN-21K on Something-Something-v2 · Something-Something-v2Top-1: 15.1 -> 36.2Improved
Use AIM rather than full finetuningViT-B/16 IN-21K on Something-Something-v2 · Something-Something-v2Top-1: 59.5 -> 62.0Improved
Use AIM rather than EVLCLIP ViT-L/14 on Something-Something-v2 · Something-Something-v2Top-1: 66.7 -> 70.6Improved
Increase the number of input frames (ablation)AIM ViT-B/16 on Kinetics-400 · Kinetics-400Top-1: 83.9 -> 84.5 -> 84.7Improved
Use AIM rather than TimeSformerViT-B IN-21K on Kinetics-400 · Kinetics-400Top-1: 78.5 -> 78.8Improved
Use AIM rather than VideoSwin-BSwin-B IN-21K on Kinetics-400 · Kinetics-400Top-1: 82.7 -> 82.1Hurt
Place adapters in the bottom 6 blocks rather than deeper blocks (ablation)AIM · Kinetics-400Top-1Hurt
Place adapters in the top 6 blocks instead of all blocks (ablation)AIM · Kinetics-400Top-1No 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