AI Paper Atlas

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

Clover: Towards a Unified Video-Language Alignment and Fusion Model

Jingjia Huang, Yinan Li, Jiashi Feng, Xinglong Wu, Xiaoshuai Sun, Rongrong Ji

CVPR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 42 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 Clover pretraining with tri-modal alignment, semantic masking, and pair-wise rankingVideo-language retrieval model · DiDeMo fine-tuneR@10: 78.8 -> 85.6Improved
Use Clover pretraining with tri-modal alignment, semantic masking, and pair-wise rankingVideo-language retrieval model · MSRVTT fine-tuneR@10: 78.0 -> 79.4Improved
Use Clover pretraining with tri-modal alignment, semantic masking, and pair-wise rankingVideo-language retrieval model · LSMDC fine-tuneR@10: 45.9 -> 54.5Improved
Use Clover pretraining with tri-modal alignment, semantic masking, and pair-wise rankingVideo-language retrieval model · DiDeMo zero-shotR@10: 63.6 -> 66.3Improved
Use Clover pretraining with tri-modal alignment, semantic masking, and pair-wise rankingVideo-language retrieval model · MSRVTT zero-shotR@10: +0.3Improved
Use Clover pretraining with tri-modal alignment, semantic masking, and pair-wise rankingVideo-language retrieval model · LSMDC zero-shotR@10: 32.2 -> 38.2Improved
Add tri-modal alignment (ablation)Baseline pretraining · DiDeMo zero-shot ablationR@1: 22.6 -> 24.7Improved
Add tri-modal alignment (ablation)Baseline pretraining · MSRVTT zero-shot ablationR@1: 19.8 -> 22.7Improved
Add semantic masking to TMA (ablation)TMA pretraining · DiDeMo zero-shot ablationR@1: 24.7 -> 25.3Improved
Add semantic masking to TMA (ablation)TMA pretraining · MSRVTT zero-shot ablationR@1: 22.7 -> 22.5Hurt
Add pair-wise ranking loss to TMA and semantic masking (ablation)TMA plus semantic masking · DiDeMo zero-shot ablationR@1: 25.3 -> 26.4Improved
Add pair-wise ranking loss to TMA and semantic masking (ablation)TMA plus semantic masking · MSRVTT zero-shot ablationR@1: 22.5 -> 23.4Improved

Later papers that compared with this method

5 later accepted papers report CLOVER as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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