AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Collaborative Noisy Label Cleaner: Learning Scene-Aware Trailers for Multi-Modal Highlight Detection in Movies

Bei Gan, Xiujun Shu, Ruizhi Qiao, Haoqian Wu, Keyu Chen, Hanjun Li, Bo Ren

CVPR 2023 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 10 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 CLC instead of UMTMovie highlight detection · MovieLightsmAP: 38.7 -> 43.88Improved
Use CLC instead of UMTYouTube Highlights · YouTube Highlightsaverage mAP: 74.9 -> 80.1Improved
Use CLC instead of UMT under noisy training labelsYouTube Highlights · Harvested matched (clean)average mAP: 74.90 -> 80.05 (↑5.15)Improved
Use CLC instead of UMT under slight label noiseYouTube Highlights · Harvested borderlineaverage mAP: 74.39 -> 79.71 (↑5.32)Improved
Use CLC instead of UMT under severe label noiseYouTube Highlights · Mturkaverage mAP: 73.36 -> 79.22 (↑5.86)Improved
Add multi-modality sample cleaning (ablation)CLC- · MovieLightsmAP: 39.65 -> 41.69Improved
Add cross-propagation (ablation)CLC with multi-modality sample cleaning · MovieLightsmAP: 41.69 -> 42.79Improved
Add consistency loss (ablation)CLC with multi-modality sample cleaning and cross-propagation · MovieLightsmAP: 42.79 -> 43.22Improved
Add median-filter post-processing (ablation)CLC with multi-modality sample cleaning, cross-propagation, and consistency loss · MovieLightsmAP: 43.22 -> 43.88Improved

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