AI Paper Atlas

Research map / Video / Video-language understanding

Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data

Wufei Ma, Kai Li, Zhongshi Jiang, Moustafa Meshry, Qihao Liu, Huiyu Wang, Christian Haene, Alan Yuille

ECCV 2024 · Video › Video-language understanding · approach: Video-language pretraining · 4 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 LLM-teacher with soft logits to InternVideoInternVideo · Feint6K (MSR-VTT)R@1: 58.6 -> 65.8Improved
add LLM-teacher with soft logits to SimVTPSimVTP · Feint6K (MSR-VTT)R@1: 35.7 -> 43.5Improved
use binary pseudo-labels instead of soft logits (ablation)LLM-teacher on InternVideo · VATEX retrievalR@1: 87.3 -> 85.2Hurt
add LLM-teacher soft logitsInternVideo · VATEX standard retrievalR@1: 87.9 -> 87.3No clear effect
use 5 instead of 10 action captions (ablation)LLM-teacher · Feint6K (VATEX)R@1: 65.6 -> 64.7Hurt
add object-based captions alongside action captions (ablation)LLM-teacher · Feint6K (VATEX)R@1: 65.6 -> 64.2Hurt
generate captions with LLM chatbot instead of mask filling (ablation)LLM-teacher · Feint6K (VATEX)R@1: 65.6 -> 65.9No clear effect
counterfactual negatives instead of random negatives (benchmark design)InternVideo finetuned · MSR-VTT vs Feint6KR@1: 49.1 -> 58.6 vs human 95.2Hurt

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