This paper presents an overview of the VQualA 2025 Challenge on Engagement Prediction for Short Videos, held in conjunction with ICCV 2025. The challenge focuses on understanding and modeling the popularity of user-generated content (UGC) short videos on social media platforms. To support this goal, the challenge uses a new short-form UGC dataset featuring engagement metrics derived from real-world user interactions. This objective of the Challenge is to promote robust modeling strategies that capture the complex factors influencing user engagement. Participants explored a variety of multi-modal features, including visual content, audio, and metadata provided by creators. The challenge attracted 97 participants and received 15 valid test submissions, contributing significantly to progress in short-form UGC video engagement prediction.
@article{arxiv.2509.02969,
title = {VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results},
author = {Dasong Li and Sizhuo Ma and Hang Hua and Wenjie Li and Jian Wang and Chris Wei Zhou and Fengbin Guan and Xin Li and Zihao Yu and Yiting Lu and Ru-Ling Liao and Yan Ye and Zhibo Chen and Wei Sun and Linhan Cao and Yuqin Cao and Weixia Zhang and Wen Wen and Kaiwei Zhang and Zijian Chen and Fangfang Lu and Xiongkuo Min and Guangtao Zhai and Erjia Xiao and Lingfeng Zhang and Zhenjie Su and Hao Cheng and Yu Liu and Renjing Xu and Long Chen and Xiaoshuai Hao and Zhenpeng Zeng and Jianqin Wu and Xuxu Wang and Qian Yu and Bo Hu and Weiwei Wang and Pinxin Liu and Yunlong Tang and Luchuan Song and Jinxi He and Jiaru Wu and Hanjia Lyu},
journal= {arXiv preprint arXiv:2509.02969},
year = {2025}
}