Search Results - "Lei, Stan Weixian"

Generic Event Boundary Detection: A Benchmark for Event Segmentation by Shou, Mike Zheng, Lei, Stan Weixian, Wang, Weiyao, Ghadiyaram, Deepti, Feiszli, Matt

“…This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks…”
Get full text

Too Large; Data Reduction for Vision-Language Pre-Training by Wang, Alex Jinpeng, Lin, Kevin Qinghong, Zhang, David Junhao, Lei, Stan Weixian, Shou, Mike Zheng

“…This paper examines the problems of severe image-text misalignment and high redundancy in the widely-used large-scale Vision-Language Pre-Training (VLP)…”
Get full text

GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval by Wang, Yuxuan, Gao, Difei, Yu, Licheng, Lei, Stan Weixian, Feiszli, Matt, Shou, Mike Zheng

“…Cognitive science has shown that humans perceive videos in terms of events separated by the state changes of dominant subjects. State changes trigger new…”
Get full text

AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant by Wong, Benita, Chen, Joya, Wu, You, Lei, Stan Weixian, Mao, Dongxing, Gao, Difei, Shou, Mike Zheng

“…A long-standing goal of intelligent assistants such as AR glasses/robots has been to assist users in affordance-centric real-world scenarios, such as "how can…”
Get full text

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant by Lei, Stan Weixian, Gao, Difei, Wang, Yuxuan, Mao, Dongxing, Liang, Zihan, Ran, Lingmin, Shou, Mike Zheng

“…It is still a pipe dream that personal AI assistants on the phone and AR glasses can assist our daily life in addressing our questions like ``how to adjust the…”
Get full text

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task by Lei, Stan Weixian, Gao, Difei, Wu, Jay Zhangjie, Wang, Yuxuan, Liu, Wei, Zhang, Mengmi, Shou, Mike Zheng

“…VQA is an ambitious task aiming to answer any image-related question. However, in reality, it is hard to build such a system once for all since the needs of…”
Get full text

Generic Event Boundary Detection: A Benchmark for Event Segmentation by Shou, Mike Zheng, Lei, Stan Weixian, Wang, Weiyao, Ghadiyaram, Deepti, Feiszli, Matt

“…This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks…”
Get full text