BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

no code implementations • 15 May 2024 • Yunhao Ge, Yihe Tang, Jiashu Xu, Cem Gokmen, Chengshu Li, Wensi Ai, Benjamin Jose Martinez, Arman Aydin, Mona Anvari, Ayush K Chakravarthy, Hong-Xing Yu, Josiah Wong, Sanjana Srivastava, Sharon Lee, Shengxin Zha, Laurent Itti, Yunzhu Li, Roberto Martín-Martín, Miao Liu, Pengchuan Zhang, Ruohan Zhang, Li Fei-Fei, Jiajun Wu

We introduce the BEHAVIOR Vision Suite (BVS), a set of tools and assets to generate fully customized synthetic data for systematic evaluation of computer vision models, based on the newly developed embodied AI benchmark, BEHAVIOR-1K.

SF-Net: Single-Frame Supervision for Temporal Action Localization

1 code implementation • ECCV 2020 • Fan Ma, Linchao Zhu, Yi Yang, Shengxin Zha, Gourab Kundu, Matt Feiszli, Zheng Shou

To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action.

Weakly Supervised Action Localization

Only Time Can Tell: Discovering Temporal Data for Temporal Modeling

no code implementations • 19 Jul 2019 • Laura Sevilla-Lara, Shengxin Zha, Zhicheng Yan, Vedanuj Goswami, Matt Feiszli, Lorenzo Torresani

However, in current video datasets it has been observed that action classes can often be recognized without any temporal information from a single frame of video.

Benchmarking Motion Estimation +1

Exploiting Image-trained CNN Architectures for Unconstrained Video Classification

no code implementations • 13 Mar 2015 • Shengxin Zha, Florian Luisier, Walter Andrews, Nitish Srivastava, Ruslan Salakhutdinov

Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34. 95% to 38. 74%.

Classification Event Detection +3