mlsanityData to 14 Oct 2026

Less is More: Learning Highlight Detection from Video Duration

arXiv 1903.00859 ↗First posted 3 Mar 2019cs.CVcited by 60

Not on the map. Why?

Abstract (arXiv)

Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manually identify highlights in training videos. We propose a scalable unsupervised solution that exploits video duration as an implicit supervision signal. Our key insight is that video segments from shorter user-generated videos are more likely to be highlights than those from longer videos, since users tend to be more selective about the content when capturing shorter videos. Leveraging this insight, we introduce a novel ranking framework that prefers segments from shorter videos, while properly accounting for the inherent noise in the (unlabeled) training data. We use it to train a highlight detector with 10M hashtagged Instagram videos. In experiments on two challenging public video highlight detection benchmarks, our method substantially improves the state-of-the-art for unsupervised highlight detection.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 10; 2024: 14; 2025: 13; 2026: 6.

60 papers.

Sort:

By area:

  1. 2023UniVTG: Towards Unified Video-Language Temporal Groundingcited by 190
  2. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
  3. 2022UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detectioncited by 148
  4. 2024TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Abilitycited by 70
  5. 2021Learning Action Completeness from Points for Weakly-supervised Temporal Action Localizationcited by 42
  6. 2023MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformercited by 40
  7. 2021Cross-category Video Highlight Detection via Set-based Learningcited by 38
  8. 2024R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Groundingcited by 34
  9. 2023Correlation-Guided Query-Dependency Calibration for Video Temporal Groundingcited by 31
  10. 2024Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrievalcited by 30
  11. 2023BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videoscited by 29
  12. 2024SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Groundingcited by 25
38 more
  1. 2024Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detectioncited by 25
  2. 2023Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videoscited by 23
  3. 2024FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Groundingcited by 23
  4. 2024Saliency-Guided DETR for Moment Retrieval and Highlight Detectioncited by 21
  5. 2023Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localizationcited by 20
  6. 2024Multimodal Action Quality Assessmentcited by 20
  7. 2025A Survey on Video Temporal Grounding with Multimodal Large Language Modelcited by 20
  8. 2022Learning Pixel-Level Distinctions for Video Highlight Detectioncited by 16
  9. 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMscited by 15
  10. 2023DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Groundingcited by 11
  11. 2022Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Rewardcited by 10
  12. 2024Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Groundingcited by 10
  13. 2025MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learningcited by 10
  14. 2022Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learningcited by 9
  15. 2025LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detectioncited by 8
  16. 2022Smart Director: An Event-Driven Directing System for Live Broadcastingcited by 7
  17. 2024Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learningcited by 7
  18. 2021How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarizationcited by 6
  19. 2021PR-Net: Preference Reasoning for Personalized Video Highlight Detectioncited by 6
  20. 2022ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generationcited by 6
  21. 2022Video Summarization Overviewcited by 6
  22. 2024Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrencecited by 6
  23. 2025From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understandingcited by 6
  24. 2025ChronusOmni: Improving Time Awareness of Omni Large Language Modelscited by 6
  25. 2026CutClaw: Agentic Hours-Long Video Editing via Music Synchronizationcited by 6
  26. 2025Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detectioncited by 5
  27. 2022Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localizationcited by 4
  28. 2025Moment Quantization for Video Temporal Groundingcited by 4
  29. 2025Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Groundingcited by 4
  30. 2026AutoCut: End-to-end advertisement video editing based on multimodal discretization and controllable generationcited by 4
  31. 2021HighlightMe: Detecting Highlights from Human-Centric Videoscited by 3
  32. 2024VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrievalcited by 3
  33. 2025CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusioncited by 3
  34. 2022Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attentioncited by 2
  35. 2023DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detectioncited by 2
  36. 2024ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Groundingcited by 2
  37. 2025Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinationscited by 2
  38. 2022Exploring Global Diversity and Local Context for Video Summarizationcited by 1

50 most cited of 60 All 60 (JSON)