AI Paper Atlas

Research map / Video / Video-language understanding

Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training

Dezhao Luo, Jiabo Huang, Shaogang Gong, Hailin Jin, Yang Liu

CVPR 2023 · Video › Video-language understanding · approach: Video moment retrieval · 36 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 visual-dynamic injection to MMN with CLIPMMN · Charades-STA novel-word OODR@1, IoU=0.5: 43.85 -> 46.47Improved
Add visual-dynamic injection to MMN with CLIPMMN · ActivityNet-Captions novel-word OODR@1, IoU=0.7: 15.48 -> 16.02Improved
Add visual-dynamic injection to MMN with image-text pre-trainingMMN · Charades-STA standard splitR@1, IoU=0.5: 50.48 -> 52.32Improved
Add visual-dynamic injection to MMN with image-text pre-trainingMMN · ActivityNet-Captions standard splitR@1, IoU=0.5: 46.89 -> 48.09Improved
Use visual context injection without a text query (ablation)MMN with CLIP on Charades-STA novel-word OOD · Charades-STA novel-word OODR@1, IoU=0.5: 43.85 -> 43.12Hurt
Use the complete query instead of the static query for visual context injection (ablation)MMN with CLIP on Charades-STA novel-word OOD · Charades-STA novel-word OODR@1, IoU=0.5: 43.85 -> 45.02Improved
Use the static query to probe visual context (ablation)MMN with CLIP on Charades-STA novel-word OOD · Charades-STA novel-word OODR@1, IoU=0.7: 24.17 -> 29.35Improved
Add spatial dynamic injection with an LSTM (ablation)MMN with CLIP on Charades-STA novel-word OOD · Charades-STA novel-word OODR@1, IoU=0.5: 43.85 -> 45.32Improved
Add spatial dynamic injection with a Transformer encoder (ablation)MMN with CLIP on Charades-STA novel-word OOD · Charades-STA novel-word OODR@1, IoU=0.5: 43.85 -> 44.60Improved
Combine visual context and spatial dynamic injection (ablation)MMN with CLIP on Charades-STA novel-word OOD · Charades-STA novel-word OODR@1, IoU=0.5: 43.85 -> 46.47Improved

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