Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay B. Baiyya, +22 more

International Journal of Computer Vision · 2025

To push the frontier of first-person video understanding of skilled human activity, a suite of benchmark tasks and their annotations are presented, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose.

Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin Qinghong Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, +2 more

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2024

A novel Learning-In- Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time dialogue within a continuous video stream within a continuous video stream.

Haiming Wang, Mert Unsal, Xiaohan Lin, Mantas Baksys, Junqi Liu, Marco Dos Santos, Flood Sung, Marina Vinyes, +22 more

arXiv · 2025

Kimina-Prover Preview is introduced, a large language model that pioneers a novel reasoning-driven exploration paradigm for formal theorem proving, as showcased in this preview release, and the learned reasoning style shows potential to bridge the gap between formal verification and informal mathematical intuition.

Jay Zhangjie Wu, Guian Fang, Haoning Wu, Xintao Wang, Yixiao Ge, Xiaodong Cun, David Junhao Zhang, Jia-Wei Liu, +6 more

arXiv · 2024

This paper investigates the limitations inherent in existing metrics and introduces a novel evaluation pipeline, the Text-to-Video Score (T2VScore), which integrates two pivotal criteria: Text-Video Alignment, which scrutinizes the fidelity of the video in representing the given text description, and Video Quality, which evaluates the video's overall production caliber with a mixture of experts.

Jia-Wei Liu, Weining Wang, Sihan Chen, Xinxin Zhu, Jing Liu

IEEE Transactions on Multimedia · 2023

This work proposes the Sounding Video Generator (SVG), a unified framework for generating realistic videos along with audio signals and presents the SVG-VQGAN, a novel hybrid contrastive learning method to model inter-modal and intra-modal consistency and improve the quantized representations.

Weifeng Liu, Tianyi She, Jia-Wei Liu, Weifeng Liu, Dongyu Yao, Ziyou Liang, Run Wang

neural information processing systems · 2024

Sihan Chen, Xinxin Zhu, Dongze Hao, Wei Liu, Jia-Wei Liu, Zijia Zhao, Longteng Guo, Jing Liu

ACM International Conference on Multimedia (ACM MM) · 2021

This paper proposes single-modality pretrained feature fusion technique which is composed of reasonable multi-view feature extraction method and designed multi- modality feature fusion strategy and it surpasses the state-of-the-art methods on both MSR-VTT and VATEX datasets.

Jia-Wei Liu, Yue‐Tong Qian, Xiao Ma, Junping Fan, Lan-Wei Guo, Hongbo Yang

Research Square · 2025