AI Paper Atlas

Research map / Video / Video-language understanding

Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer

Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H.S. Torr, Xiao-Ping Zhang, Yansong Tang

ICCV 2023 · Video › Video-language understanding · approach: Video-language pretraining · 28 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 language template converting QA pairs to declarative sentences (ablation)Tem-Adapter · SUTD-TrafficQAaverage accuracy: 43.9 -> 46.0Improved
add Semantic Aligner (ablation)Tem-Adapter · SUTD-TrafficQAaverage accuracy: 44.2 -> 46.0Improved
add Temporal Aligner (ablation)Tem-Adapter · SUTD-TrafficQAaverage accuracy: 43.6 -> 46.0Improved
add language-guided auto-regression loss (ablation)Tem-Adapter · SUTD-TrafficQAaverage accuracy: 44.9 -> 46.0Improved
add auto-regression loss (ablation)Tem-Adapter · MSR-VTT-MCaccuracy: 92.6 -> 94.3Improved
add both Temporal and Semantic Aligners (ablation)CLIP + template · MSR-VTT-MCaccuracy: 74.1 -> 94.3Improved
add language guidance to the autoregressive Temporal Aligner (ablation)Temporal Aligner · SUTD-TrafficQA reconstructionPSNR: 28.7 -> 29.1Improved
more trainable parameters (full vs partial finetuning; multi-layer vs single adapter)CLIP adaptation · SUTD-TrafficQA vs MSR-VTT-MCaccuracy: SUTD: 41.7 vs 40.3; MSR-VTT-MC: 88.5 vs 89.0Mixed
vary Semantic/Temporal Aligner hidden size and layer counts (ablation)Tem-Adapter · SUTD-TrafficQAaccuracy: 44.6 to 45.8 versus default 46.0No clear effect
adapt CLIP features with Tem-Adapter inside HCRNCLIP+HCRN · SUTD-TrafficQAaccuracy: 41.9 -> 46.0Improved

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