AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Yizhen Chen, Jie Wang, Lijian Lin, Zhongang Qi, Jin Ma, Ying Shan

AAAI 2023 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 37 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
Use multi-modal tags as alignment anchors (ablation)TABLE · MSR-VTT, T2VR@1: 45.2 -> 46.8Improved
Add object tags (ablation)TABLE · MSR-VTT, T2VR@1: 45.2 -> 45.6Improved
Add person tags to object tags (ablation)TABLE · MSR-VTT, T2VR@1: 45.6 -> 45.6No clear effect
Add motion tags to object and person tags (ablation)TABLE · MSR-VTT, T2VR@1: 45.6 -> 46.2Improved
Add scene tags to object, person, and motion tags (ablation)TABLE · MSR-VTT, T2VR@1: 46.2 -> 46.5Improved
Add audio tags to object, person, motion, and scene tags (ablation)TABLE · MSR-VTT, T2VR@1: 46.5 -> 46.8Improved
Add VTM auxiliary supervision (ablation)TABLE · MSR-VTT, V2TR@1: 45.9 -> 46.6Improved
Add MLM to VTM auxiliary supervision (ablation)TABLE · MSR-VTT, T2VR@1: 46.7 -> 47.1Improved
Add MLM to VTM auxiliary supervision (ablation)TABLE · MSR-VTT, V2TR@1: 46.6 -> 47.2Improved
Apply the CAMoE inference strategy (ablation)TABLE · MSR-VTT, T2VR@1: 47.1 -> 52.3Improved
Use TABLE instead of CAMoECLIP-based video-text retrieval · MSR-VTT, T2VR@1: 47.1 vs 44.6Improved
Use TABLE instead of CAMoECLIP-based video-text retrieval · MSVD, T2VR@1: 49.9 vs 46.9Improved

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