AI Paper Atlas

Research map / Video / Video-language understanding

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding

CVPR 2023 · Video › Video-language understanding · approach: Temporal video grounding · 35 citations (OpenAlex)

Read the paper

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 both visual and text prompts (ablation)2D TVG base model · Charades-STAR@1, IoU=0.5: 40.43 -> 44.39Improved
Add visual prompts alone (ablation)2D TVG base model · ActivityNet CaptionsR@1, IoU=0.7: 19.14 -> 23.71Improved
Add text prompts alone (ablation)2D TVG base model · ActivityNet CaptionsR@1, IoU=0.7: 19.14 -> 24.39Improved
Combine text and visual prompts rather than use either alone (ablation)2D TVG base model · ActivityNet CaptionsR@1, IoU=0.7: 30.77%Improved
Replace padding-region pixels with visual prompts rather than add them (ablation)2D TVG base model · Charades-STAR@1, IoU=0.3: 61.29 -> 65.38Improved
Add temporal-distance loss to tIoU loss (ablation)TVP · Charades-STAR@1, IoU=0.7: 11.82 -> 16.77Improved
Add duration loss to tIoU loss (ablation)TVP · Charades-STAR@1, IoU=0.7: 11.82 -> 16.34Improved
Add both distance and duration losses to tIoU loss (ablation)TVP · Charades-STAR@1, IoU=0.7: 68.27%Improved
Use a visual prompt size of 96 (ablation)TVP visual prompts · Charades-STAR@1, IoU=0.3: 61.29 -> 65.38Improved
Increase visual prompt size beyond 96 (ablation)TVP visual prompts · Charades-STAR@1, IoU=0.3: 65.38 -> 64.73Hurt
Use text prompts rather than no text prompts (ablation)TVP text prompts · Charades-STAR@1, IoU=0.3: 57.20 -> 65.81Improved
Increase sampled frames beyond 48 (ablation)Base model · Charades-STAR@1Hurt

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