ComVi: Context-Aware Optimized Comment Display in Video Playback

Minsun Kim; Dawon Lee; Junyong Noh

cs.MMMar 27, 2026

ComVi: Context-Aware Optimized Comment Display in Video Playback

Authors: Minsun Kim, Dawon Lee, Junyong Noh

Organizations: KAIST Daejeon, Republic of Korea · Kookmin University Seoul, Republic of Korea

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.

LOLGORITHM: Funny Comment Generation Agent For Short Videos
Apr 9, 2026Xuan Ouyang, Bouzhou Wang, Senan Wang +3Text Generation Controllable Text Generation
University of New South Wales Sydney, Australia · University of Sydney Sydney, Australia · The University of Hong Kong Hong Kong, China +1
Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation
May 9, 2026Yang Xiao, Huiyuan Chen, Kaiyuan Deng +5Video Representation Learning Embedding Compression
University of Tulsa · Amazon · University of Arizona +1
Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches
Mar 3, 2026Anum Afzal, Yuki Saito, Hiroya Takamura +5Language Model Decoding Multimodal Large Language Models
School of CIT, Technical University of Munich · National Institute of Advanced Industrial Science and Technology (AIST) · The University of Tokyo +3

Apr 9, 2026J/K move · Enter open · S save

LOLGORITHM: Funny Comment Generation Agent For Short Videos

Xuan Ouyang, Bouzhou Wang, Senan Wang, Siyuan Xiahou+2

University of New South Wales Sydney, Australia · University of Sydney Sydney, Australia · The University of Hong Kong Hong Kong, China+1

Text Generation Controllable Text Generation Multi-Agent Systems

Open paper AskPDF arXiv

Short-form video platforms have become central to multimedia information dissemination, where comments play a critical role in driving engagement, propagation, and algorithmic feedback. However, existing approaches -- including video summarization and live-streaming danmaku generation -- fail to produce authentic comments that conform to platform-specific cultural and linguistic norms. In this paper, we present LOLGORITHM, a novel modular multi-agent framework for stylized short-form video comment generation. LOLGORITHM supports six controllable comment styles and comprises three core modules: video content summarization, video classification, and comment generation with semantic retrieval and hot meme augmentation. We further construct a bilingual dataset of 3,267 videos and 16,335 comments spanning five high-engagement categories across YouTube and Douyin. Evaluation combining automatic scoring and large-scale human preference analysis demonstrates that LOLGORITHM consistently outperforms baseline methods, achieving human preference selection rates of 80.46% on YouTube and 84.29% on Douyin across 107 respondents. Ablation studies confirm that these gains are attributable to the framework architecture rather than the choice of backbone LLM, underscoring the robustness and generalizability of our approach.

Abstract

Explore similar work

LOLGORITHM: Funny Comment Generation Agent For Short Videos

Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation

Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches