User Generated Video
User-generated video (UGV) research focuses on analyzing and processing the massive volume of short-form videos uploaded to online platforms. Current efforts concentrate on improving content moderation (e.g., identifying inappropriate content for children), efficient video summarization (using graph-based algorithms and deep learning), and enhancing video quality assessment (through deep learning models trained on large datasets). These advancements are crucial for improving user experience, creating safer online environments, and enabling new applications like personalized assistance in augmented reality and improved video search functionality.
Papers
Step Differences in Instructional Video
Tushar Nagarajan, Lorenzo Torresani
AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results
Marcos V. Conde, Saman Zadtootaghaj, Nabajeet Barman, Radu Timofte, Chenlong He, Qi Zheng, Ruoxi Zhu, Zhengzhong Tu, Haiqiang Wang, Xiangguang Chen, Wenhui Meng, Xiang Pan, Huiying Shi, Han Zhu, Xiaozhong Xu, Lei Sun, Zhenzhong Chen, Shan Liu, Zicheng Zhang, Haoning Wu, Yingjie Zhou, Chunyi Li, Xiaohong Liu, Weisi Lin, Guangtao Zhai, Wei Sun, Yuqin Cao, Yanwei Jiang, Jun Jia, Zhichao Zhang, Zijian Chen, Weixia Zhang, Xiongkuo Min, Steve Göring, Zihao Qi, Chen Feng