Search Results for author: Jay Wu

Found 5 papers, 2 papers with code

VEU-Bench: Towards Comprehensive Understanding of Video Editing

no code implementations CVPR 2025 Bozheng Li, Yongliang Wu, Yi Lu, Jiashuo Yu, Licheng Tang, Jiawang Cao, Wenqing Zhu, Yuyang Sun, Jay Wu, Wenbo Zhu

We also demonstrate that incorporating VEU data significantly enhances the performance of Vid-LLMs on general video understanding benchmarks, with an average improvement of 8. 3% across nine reasoning tasks.

Video Editing Video Understanding

Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark

1 code implementation12 Dec 2024 Yongliang Wu, Wenbo Zhu, Jiawang Cao, Yi Lu, Bozheng Li, Weiheng Chi, Zihan Qiu, Lirian Su, Haolin Zheng, Jay Wu, Xu Yang

The demand for producing short-form videos for sharing on social media platforms has experienced significant growth in recent times.

Highlight Detection Video Summarization

Zero-Shot Long-Form Video Understanding through Screenplay

no code implementations25 Jun 2024 Yongliang Wu, Bozheng Li, Jiawang Cao, Wenbo Zhu, Yi Lu, Weiheng Chi, Chuyun Xie, Haolin Zheng, Ziyue Su, Jay Wu, Xu Yang

The Long-form Video Question-Answering task requires the comprehension and analysis of extended video content to respond accurately to questions by utilizing both temporal and contextual information.

Form Question Answering +2

Reframe Anything: LLM Agent for Open World Video Reframing

no code implementations10 Mar 2024 Jiawang Cao, Yongliang Wu, Weiheng Chi, Wenbo Zhu, Ziyue Su, Jay Wu

The proliferation of mobile devices and social media has revolutionized content dissemination, with short-form video becoming increasingly prevalent.

object-detection Salient Object Detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.