AI Paper Atlas

Research map / Video / Video-language understanding

Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval

Chengzhi Lin, Ancong Wu, Junwei Liang, Jun Zhang, Wenhang Ge, Wei-Shi Zheng, Chunhua Shen

NeurIPS 2022 · Video › Video-language understanding · approach: Text-video retrieval

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
Replace a single video representation with multiple mask-generated prototypes and text-adaptive matching (ablation)Frozen on MSR-VTT · MSR-VTTSumR: 167.9 -> 173.2Improved
Add variance loss to mask-based prototype matching (ablation)TVMM-Mask on MSR-VTT · MSR-VTTSumR: 173.2 -> 176.1Improved
Use mask aggregation rather than part-based prototype production (ablation)TVMM on MSR-VTT · MSR-VTTSumR: 169.2 -> 173.2Improved
Use mask aggregation rather than a two-layer decoder for prototype production (ablation)TVMM on MSR-VTT · MSR-VTTSumR: 170.9 -> 173.2Improved
Use three extra prototypes instead of one (ablation)TVMM-Mask on MSR-VTT · MSR-VTTSumR: 172.0 -> 176.1Improved
Use three extra prototypes instead of two (ablation)TVMM-Mask on MSR-VTT · MSR-VTTSumR: 175.6 -> 176.1No clear effect
Increase the extra prototype count from three to four (ablation)TVMM-Mask on MSR-VTT · MSR-VTTSumR: 176.1 -> 173.1Hurt
Increase the extra prototype count from three to ten (ablation)TVMM-Mask on MSR-VTT · MSR-VTTSumR: 176.1 -> 168.9Hurt
Generate an extra prototype for every token instead of using three extra prototypes (ablation)TVMM-Mask on MSR-VTT · MSR-VTTSumR: 176.1 -> 163.8Hurt
Add multiple prototype matching and variance loss (ablation)Frozen baseline with one input frame · MSR-VTT, 1 frameSumR: 133.3 -> 137.3Improved
Add multiple prototype matching and variance loss (ablation)Frozen baseline with four input frames · MSR-VTT, 4 framesSumR: 163.7 -> 170.4Improved
Add multiple prototype matching and variance loss (ablation)Frozen baseline with eight input frames · MSR-VTT, 8 framesSumR: 167.9 -> 176.1Improved

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