AI Paper Atlas

Research map / Video / Video-language understanding

TVHighlights: LLM-Guided Human-Free Collaborative Training for Video Highlight Detection in Movies and TV Dramas

Qi Qiu, Xuan Wu, Jiawei Peng, Yuan Miao, Xu Yang, Yanlong Du

CVPR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video

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 Stage 2 LLM-guided iterative refinement (ablation)LTV-HD Stage 1 · TVHighlights (total)AP: 62.39 -> 71.20Improved
add weakly supervised MIL pre-training (ablation)LTV-HD · TVHighlights (total)AP: 63.45 -> 67.69Improved
add weak supervised pre-training before Stage 2 refinement (ablation)LTV-HD Stage 2 · TVHighlights (total)AP: 70.01 -> 71.20Improved
add second refinement round (ablation)LTV-HD · TVHighlights (total)AP: 69.78 -> 71.20Improved
update labels during NLC training (ablation)NLC learning · TVHighlights (total)AP: 66.05 -> 70.21Improved
add compatibility loss (ablation)NLC learning · TVHighlights (total)AP: 70.21 -> 70.85Improved
add sharpness loss (ablation)NLC learning · TVHighlights (total)AP: 70.85 -> 71.20Improved
add sharpness loss (without compatibility loss) (ablation)NLC learning · TVHighlights (total)AUC: 93.31 (no cp) vs 92.74 (full)Mixed
use per-clip scoring instead of direct moment retrieval for MLLMsQwen-vl-max · TVHighlights (total)AP: 36.62 -> 47.42Improved
use NLC noisy-label learning under MTurk label noiseLTV-HD vs UMT · YouTube Highlights (MTurk)mAP: UMT drops 1.54, ours drops 0.32Improved
use LTV-HD under clean supervision vs top baselineLTV-HD · YouTube Highlights (clean)mAP: 75.8 vs UVCOM2 77.4No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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