ComVi: Context-Aware Optimized Comment Display in Video Playback

• URL: http://arxiv.org/abs/2603.26173v1
• Date: Fri, 27 Mar 2026 08:40:18 GMT
• Title: ComVi: Context-Aware Optimized Comment Display in Video Playback
• Abstract summary: ComVi is a novel system that displays comments at contextually relevant moments.<n>We first map all comments to relevant video timestamps by computing audio-visual correlation, then construct the comment sequence.<n>In a user study, ComVi provided a significantly more engaging experience than conventional video interfaces.
• Score: 19.088928992771603
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Semantic Frame Aggregation-based Transformer for Live Video Comment Generation [10.604889675520925]
  We present a novel model for generating contextually appropriate video comments on live video streams.<n>We use CLIP's visual-text multimodal knowledge to assign weights to video frames based on their semantic relevance to ongoing viewer conversation.<n>Our comment decoder with a cross-attention mechanism ensures that the generated comment reflects contextual cues from both chats and video.
  arXiv  Detail & Related papers  (2025-10-30T20:01:04Z)
• Enhancing Multimodal Affective Analysis with Learned Live Comment Features [12.437191675553423]
  Live comments, also known as Danmaku, are user-generated messages that are synchronized with video content. We first construct the Live Comment for Affective Analysis dataset which contains live comments for English and Chinese videos. We then use contrastive learning to train a video encoder to produce synthetic live comment features for enhanced multimodal affective content analysis.
  arXiv  Detail & Related papers  (2024-10-21T18:19:09Z)
• HOTVCOM: Generating Buzzworthy Comments for Videos [49.39846630199698]
  This study introduces textscHotVCom, the largest Chinese video hot-comment dataset, comprising 94k diverse videos and 137 million comments. We also present the textttComHeat framework, which synergistically integrates visual, auditory, and textual data to generate influential hot-comments on the Chinese video dataset.
  arXiv  Detail & Related papers  (2024-09-23T16:45:13Z)
• ViCo: Engaging Video Comment Generation with Human Preference Rewards [68.50351391812723]
  We propose ViCo with three novel designs to tackle the challenges for generating engaging Video Comments. To quantify the engagement of comments, we utilize the number of "likes" each comment receives as a proxy of human preference. To automatically evaluate the engagement of comments, we train a reward model to align its judgment to the above proxy.
  arXiv  Detail & Related papers  (2023-08-22T04:01:01Z)
• Audio-Visual Contrastive Learning with Temporal Self-Supervision [84.11385346896412]
  We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision. To leverage the temporal and aural dimension inherent to videos, our method extends temporal self-supervision to the audio-visual setting.
  arXiv  Detail & Related papers  (2023-02-15T15:00:55Z)
• VTC: Improving Video-Text Retrieval with User Comments [22.193221760244707]
  This paper introduces a new dataset of videos, titles and comments. By using comments, our method is able to learn better, more contextualised, representations for image, video and audio representations.
  arXiv  Detail & Related papers  (2022-10-19T18:11:39Z)
• PRVR: Partially Relevant Video Retrieval [55.41367664146273]
  In current text-to-video retrieval (T2VR), videos to be retrieved have been properly trimmed so that a correspondence between the videos and ad-hoc textual queries naturally exists.<n>This paper presents a first study on this setting which we term Partially Relevant Video Retrieval (PRVR)<n>We formulate the PRVR task as a multiple instance learning problem, and propose a Multi-Scale Similarity Learning (MS-SL++) network that jointly learns both clip-scale and frame-scale similarities.
  arXiv  Detail & Related papers  (2022-08-26T09:07:16Z)
• Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer [66.56167074658697]
  We present a method that builds on 3D-VQGAN and transformers to generate videos with thousands of frames. Our evaluation shows that our model trained on 16-frame video clips can generate diverse, coherent, and high-quality long videos. We also showcase conditional extensions of our approach for generating meaningful long videos by incorporating temporal information with text and audio.
  arXiv  Detail & Related papers  (2022-04-07T17:59:02Z)
• The Potential of Using Vision Videos for CrowdRE: Video Comments as a Source of Feedback [0.8594140167290097]
  We analyze and assess the potential of using vision videos for CrowdRE. In a case study, we analyzed 4505 comments on a vision video from YouTube. We conclude that the use of vision videos for CrowdRE has a large potential.
  arXiv  Detail & Related papers  (2021-08-04T14:18:27Z)
• QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries [89.24431389933703]
  We present the Query-based Video Highlights (QVHighlights) dataset. It consists of over 10,000 YouTube videos, covering a wide range of topics. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips.
  arXiv  Detail & Related papers  (2021-07-20T16:42:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.