AI Paper Atlas

Research map / Video / Video-language understanding

TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal

ECCV 2020 · Video › Video-language understanding · approach: Video moment retrieval · 294 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 XML's late-fusion ConvSE design instead of retrieval+re-ranking with early-fusion ExCLXML · TVR test-public VCMRR@1 IoU=0.7: 0.33 -> 3.25Improved
add ConvSE start-end detector instead of sliding-window proposals (ablation)XML · TVR test-public VCMRR@1 IoU=0.7: 1.91 -> 3.25Improved
add hierarchical video-then-moment retrieval (reduce candidates) to proposal-based MCN/CAL via MEE retrievalMCN / CAL · TVR test-public VCMRR@1 IoU=0.7: 0.04 -> 0.39Improved
use ConvSE kernel size 1 instead of 3, 5 or 7 (ablation)ConvSE · TVR VCMRperformanceHurt
add transformer self-encoder instead of bidirectional LSTM (ablation)XML · TVR val VCMR, IoU=0.7R@1: 2.12 -> 2.62Improved
add transformer self-encoder instead of CNN encoder (ablation)XML · TVR val VCMR, IoU=0.7R@1: 2.45 -> 2.62Improved
add modular (two) queries instead of one max-pooled query (ablation)XML · TVR val VCMR, IoU=0.7R@1: 2.46 -> 2.62Improved
add I3D action features to ResNet appearance features (ablation)XML · TVR val VCMR, IoU=0.7R@1: 2.28 -> 2.62Improved
add ResNet appearance features to I3D action features (ablation)XML · TVR val VCMR, IoU=0.7R@1: 2.22 -> 2.62Improved
use both video and subtitle inputs instead of a single modality (ablation)XML · TVR val VCMRoverall performanceImproved
increase retrieved videos from 10 to 200 (ablation)XML · TVR VCMR IoU=0.5R@100: 31.05 -> 36.20Mixed
add Temporal Endpoint Feature (TEF) to MCN and CAL (ablation)MCN / CAL / MEE+CAL · TVR test-public VCMR, IoU=0.5R@1: 0.97 -> 1.23Mixed

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