mlsanityData to 7 Oct 2026

ComVi: Context-Aware Optimized Comment Display in Video Playback

arXiv 2603.26173 ↗First posted 27 Mar 2026cs.MM cs.CV cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

On general video-sharing platforms like YouTube, comments are displayed independently of video playback. As viewers often read comments while watching a video, they may encounter ones referring to moments unrelated to the current scene, which can reveal spoilers and disrupt immersion. To address this problem, we present ComVi, a novel system that displays comments at contextually relevant moments, enabling viewers to see time-synchronized comments and video content together. We first map all comments to relevant video timestamps by computing audio-visual correlation, then construct the comment sequence through an optimization that considers temporal relevance, popularity (number of likes), and display duration for comfortable reading. In a user study, ComVi provided a significantly more engaging experience than conventional video interfaces (i.e., YouTube and Danmaku), with 71.9% of participants selecting ComVi as their most preferred interface.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 95 references that are in the map. First posted on arXiv 27 Mar 2026.

Builds on

17 of 95 references.

References · 17

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  3. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  4. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  5. 2017Temporal Action Detection with Structured Segment Networkscited by 265
  6. 2025Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understandingcited by 80
  7. 2019Less is More: Learning Highlight Detection from Video Durationcited by 60
  8. 2021Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Explorationcited by 44
  9. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  10. 2020GAZED- Gaze-guided Cinematic Editing of Wide-Angle Monocular Video Recordingscited by 11
  11. 2023ViCo: Engaging Video Comment Generation with Human Preference Rewardscited by 8
  12. 2023Automated Conversion of Music Videos into Lyric Videoscited by 4
5 more
  1. 2025DanmuA11y: Making Time-Synced On-Screen Video Comments (Danmu) Accessible to Blind and Low Vision Users via Multi-Viewer Audio Discussionscited by 4
  2. 2025CoKnowledge: Supporting Assimilation of Time-synced Collective Knowledge in Online Science Videoscited by 4
  3. 2023Papeos: Augmenting Research Papers with Talk Videoscited by 3
  4. 2025TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve Content and Stylecited by 2
  5. 2025Branch Explorer: Leveraging Branching Narratives to Support Interactive 360deg Video Viewing for Blind and Low Vision Userscited by 1

Built on by

Not cited yet.