AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Zero-Shot Temporal Action Detection via Vision-Language Prompting

Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

ECCV 2022 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 72 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 Maskformer decoder representation masking (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 10.9 -> 24.9Improved
use Maskformer decoder instead of 1-D CNN for masking (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 20.1 -> 24.9Improved
increase decoder queries from 5 to 100 (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 24.4 -> 25.1Improved
add text encoder (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 11.5 -> 24.9Improved
fine-tune the CLIP text encoder (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 22.8 -> 24.9Improved
use Transformer instead of MS-TCN for temporal modeling (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 21.4 -> 24.9Improved
use Transformer instead of 1D CNN (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 19.3 -> 24.9Improved
add vision-to-language cross-modal adaptation (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 23.5 -> 24.9Improved
increase context tokens from 10 to 50 (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 24.2 -> 24.9Improved
increase context tokens from 50 to 70 (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP: 24.9 -> 24.8No clear effect
use parallel mask/classification (STALE) instead of proposal-based B-I (ablation)STALE · ActivityNet v1.3 zero-shot, 75% seenavg mAP drop from GT to predicted: 47.1 -> 19.9 for B-I vs 42.3 -> 24.9 for STALEImproved
use STALE instead of EffPromptSTALE · THUMOS14 zero-shot, 50% seenavg mAP: 21.9 -> 22.2Improved

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