AI Paper Atlas

Research map / Video / Action recognition

Expanding Language-Image Pretrained Models for General Video Recognition

Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, Haibin Ling

ECCV 2022 · Video › Action recognition · approach: Contrastive video representation learning · 410 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 cross-frame communication to CLIP-Mean (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: +1.2%Improved
add 1-layer multi-frame integration transformer (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: +0.5%Improved
add video-specific prompting (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: +2.3% over CLIP-MeanImproved
add multi-view inference (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: +1.5%Improved
finetune the image encoder instead of freezing it (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: +3.0%Improved
freeze the text encoder (ablation)X-CLIP-B/16 8f · Kinetics-400CUDA memory: 22G -> 6GImproved
add text branch instead of random FC head (ablation)X-CLIP-B/16 8f · HMDB-51 few-shot K=2top-1 accuracy: +18.8%Improved
add text branch instead of random FC head (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: +0.7%Improved
CLIP pretraining instead of ImageNet-21k (ablation)X-CLIP-B/16 8f · Kinetics-400top-1 accuracy: 79.8 -> 82.3Improved
video-specific prompts instead of handcrafted ensemble / learnable vectors (ablation)X-CLIP-B/16 · UCF-101 zero-shottop-1 accuracy: +6.1%Improved
sparse instead of dense sampling (ablation)X-CLIP-B/16 · Kinetics-400top-1 accuracyImproved
cross-frame attention vs CLIP-Joint space-time attention (ablation)X-CLIP-B/16 · Kinetics-400 fully-supervised / HMDB-51 few-shottop-1 accuracy: +0.2% and +9.5%Improved

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