AI Paper Atlas

Research map / Video / Action recognition

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

ICML 2023 · Video › Action recognition · approach: Contrastive video representation learning · 6 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 temporal attention across neighboring video frames (ablation)CLIP adapted as VCLIP · UCF-101, HMDB-51, Kinetics-600zero-shot accuracyImproved
Add Interpolated Weight Regularization (IWR) during training (ablation)Open-VCLIP · UCF-101, HMDB-51, Kinetics-600zero-shot accuracyImproved
Add stochastic weight averaging (SWA) (ablation)Open-VCLIP · UCF-101, HMDB-51, Kinetics-600zero-shot accuracyImproved
Use IWR and SWA together rather than either alone (ablation)Open-VCLIP · UCF-101, HMDB-51, Kinetics-600zero-shot accuracyImproved
Replace IWR with simple L2 weight regularization (ablation)VCLIP · UCF-101, HMDB-51, Kinetics-600zero-shot accuracyHurt
Fine-tune CLIP conventionally instead of using Open-VCLIP optimization (ablation)CLIP · Kinetics-600zero-shot accuracy: 68.1 -> 65.9Hurt
Fine-tune CLIP conventionally instead of using Open-VCLIP optimization (ablation)CLIP ViT-L/14 · HMDB-51zero-shot accuracy: 55.0 -> 51.9Hurt
Adapt with ST-Adapter modules while keeping CLIP parameters frozen (ablation)CLIP ViT-B/16 · Kinetics-600zero-shot accuracy: 68.1 -> 60.2$\pm$1.8Hurt
Use a larger ViT-L/14 backbone rather than ViT-B/16 (ablation)Open-VCLIP · UCF-101, HMDB-51, Kinetics-600zero-shot accuracy: 80.5 -> 87.9; 55.0 -> 58.3; 76.2 -> 81.1Improved
Increase the CLIP interpolation coefficient from 0.5 to 0.7 (ablation)Open-VCLIP · MSR-VTTtext-to-video recall@1: 31.3 -> 33.2Improved
Increase the CLIP interpolation coefficient from 0.5 to 0.7 (ablation)Open-VCLIP · Kinetics-400accuracy: 78.9 -> 73.4Hurt
Increase the CLIP interpolation coefficient from 0.5 to 0.7 (ablation)Open-VCLIP · MSR-VTTvideo-to-text recall@1: 33.6 -> 34.4Improved

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