AI Paper Atlas

Research map / Video / Video-language understanding

VTC: Improving Video-Text Retrieval with User Comments

Laura Hanu, James Thewlis, Yuki M. Asano, Christian Rupprecht

ECCV 2022 · Video › Video-language understanding · approach: Text-video retrieval · 9 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 Context Adapter Module instead of averaging comment features (ablation)fine-tuned CLIP · VTC test (title adapted, 5 comments)TVR R@1: 16.6 -> 18.4Improved
add comments via Context Adapter Modulefine-tuned CLIP · VTC test (title adapted, 5 comments)TVR R@1: 15.5 -> 18.4Improved
fine-tune the CLIP encoder on VTCCLIP ViT-B/32 · VTC testTVR R@1: 11.1 -> 15.5Improved
average comment features with title, zero-shotCLIP ViT-B/32 · VTC test (title adapted, 5 comments)TVR R@1: 11.1 -> 7.3Hurt
adapt the image branch instead of the title branch (ablation)CAM · VTC test (adaptation modality)TVR R@1: 18.0 -> 28.2Improved
train with comments but evaluate without commentsCAM · VTC testTVR R@10: 34.9 -> 34.5No clear effect
add audio to img+title+comments (ablation)CAM · VTC testTVR R@1: 18.0 -> 19.6Improved
increase comments from 5 to 20 (ablation)CAM, CLIP ViT-B/32 · VTC test (frozen encoder + CAM, 5 comments, image from text+comments)R@10: 32.3 -> 34.1Improved
add 5 commentsCAM, CLIP ViT-L/14 · VTC test (frozen encoder + CAM, 5 comments, image from text+comments)R@10: 32.9 -> 42.0Improved
remove videos containing faces from training (ablation)CAM · VTC testTVR R@10: 43.2 -> 44.0No clear effect
add comments to 8-frame video modelCAM · KineticsComments VTR R@10VTR R@10: 56.9 -> 68.0Improved
adapt text branch instead of video branch for video model (ablation)CAM · VTC and KineticsComments VTR R@10 (8 frames)VTR R@10: 28.6 -> 33.7 (VTC), 57.5 -> 57.3 (KineticsComments)Mixed

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