Something Else Compositional Action Recognition

Authors: Joanna Materzynska, Tete Xiao, Roei Herzig, Huijuan Xu, Xiaolong Wang, Trevor Darrell Description: Human

Accepted at BMVC 2021 -- Oral presentation (top ~3.5% of the papers)! Arxiv: https://arxiv.org/abs/2111.01936 Code: ...

ECCV2020: Visual

In the 63rd session of Multimodal Weekly, we had three exciting presentations on video summarization,

Code is available at https://github.com/RongchangLi/ZSCAR_C2C.

Graduate Summer School 2012: Deep Learning, Feature Learning "Unsupervised

Title: C2C: Component-to-Composition Learning for Zero-Shot

Poster at CVPR 2021 Paper: https://arxiv.org/pdf/2103.16002.pdf Benchmark: https://cs.stanford.edu/people/ranjaykrishna/agqa/

Moreover, we also use the videos for

The focus of the

Yuke Zhu UT Austin February 18, 2022 Recent years have witnessed great strides in deep learning for robotics.

Workshop: ICCV'13 THUMOS Challenge: International Workshop on

Not all video frames are equally informative for