English

A Multimodal Transformer for Live Streaming Highlight Prediction

Multimedia 2024-07-18 v1 Computer Vision and Pattern Recognition

Abstract

Recently, live streaming platforms have gained immense popularity. Traditional video highlight detection mainly focuses on visual features and utilizes both past and future content for prediction. However, live streaming requires models to infer without future frames and process complex multimodal interactions, including images, audio and text comments. To address these issues, we propose a multimodal transformer that incorporates historical look-back windows. We introduce a novel Modality Temporal Alignment Module to handle the temporal shift of cross-modal signals. Additionally, using existing datasets with limited manual annotations is insufficient for live streaming whose topics are constantly updated and changed. Therefore, we propose a novel Border-aware Pairwise Loss to learn from a large-scale dataset and utilize user implicit feedback as a weak supervision signal. Extensive experiments show our model outperforms various strong baselines on both real-world scenarios and public datasets. And we will release our dataset and code to better assess this topic.

Keywords

Cite

@article{arxiv.2407.12002,
  title  = {A Multimodal Transformer for Live Streaming Highlight Prediction},
  author = {Jiaxin Deng and Shiyao Wang and Dong Shen and Liqin Zhao and Fan Yang and Guorui Zhou and Gaofeng Meng},
  journal= {arXiv preprint arXiv:2407.12002},
  year   = {2024}
}

Comments

Accepted at ICME 2024 as poster presentation. arXiv admin note: text overlap with arXiv:2306.14392

R2 v1 2026-06-28T17:43:30.852Z