AI Paper Atlas

Research map / Video / Video-language understanding

Large Scale Video Representation Learning via Relational Graph Clustering

Hyodong Lee, Joonseok Lee, Joe Yue-Hei Ng, Paul Natsev

CVPR 2020 · Video › Video-language understanding · approach: Text-video retrieval · 17 citations (OpenAlex)

Check 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 random negatives with graph-cluster smart negativesCDML-style triplet learning · Related video retrievalMAP: 2.85% -> 3.57%Improved
Replace random negatives with graph-cluster smart negativesCDML-style triplet learning · Related video retrievalNDCG@60: 6.05% -> 7.19%Improved
Use harder negatives sampled from lower-level clusters (ablation)GCML · Related video retrievalMAP: 3.37% -> 3.43% -> 3.57%Improved
Use harder negatives sampled from lower-level clusters (ablation)GCML · Related video retrievalNDCG@60: 6.64% -> 6.91% -> 7.19%Improved
Increase GCML training triplets from 45M to 420MGCML · Related video retrievalMAP: 3.57% -> 3.74%Improved
Train with graph-cluster pseudo-label classification instead of triplet lossVideo embedding learning · Related video retrievalMAP: 3.41% vs 3.34% (CDML 458M)Mixed
Limit sampled examples to 20–100 rather than 1,000 per cluster (ablation)CLC · Related video retrievalMAP: 3.24% -> 3.42%Improved
Increase sampled classes from 10,000 to 200,000 (ablation)CLC · Related video retrievalMAP: 3.21% -> 3.42%Improved
Increase sampled classes from 200,000 to 400,000 (ablation)CLC · Related video retrievalMAP: 3.42% -> 3.42%No clear effect
Use GCML instead of CDML with small training setsVideo annotation · YouTube-8MMAP: 51.7% -> 52.5%Improved
Use GCML instead of CDML with large training setsVideo annotation · YouTube-8MMAP: 55.5% vs 55.5%No clear effect
Use GCML embeddings instead of CDML embeddingsVideo annotation · Sports-1MHit@1 (embedding only): 67.0% -> 68.7%Improved

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