3.7k citations
- Meta (United States)US158 papers
- New York UniversityUS11 papers
- Carnegie Mellon UniversityUS10 papers
- University of California, BerkeleyUS8 papers
- Stanford UniversityUS7 papers
- University of WashingtonUS7 papers
- Cornell UniversityUS6 papers
- University of OxfordGB6 papers
- Massachusetts Institute of TechnologyUS5 papers
- Meta (Israel)IL5 papers
- ETH ZurichCH4 papers
- Google (United States)US4 papers
7 papers · 2 filters
Listen to Look: Action Recognition by Previewing Audio
Ruohan Gao, Tae-Hyun Oh, Kristen Grauman +1
In the face of the video data deluge, today's expensive clip-level classifiers are increasingly impractical. We propose a framework for efficient action recognition in untrimmed vi…
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
Humam Alwassel, Dhruv Mahajan, Bruno Korbar +3
Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible to predict the semantics of one from the other…
Fine-grained Synthesis of Unrestricted Adversarial Examples
Omid Poursaeed, Tianxing Jiang, Yordanos Goshu +3
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typ…
Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
Ronghang Hu, Amanpreet Singh, Trevor Darrell +1
Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water la…
On the Evaluation of Conditional GANs
Terrance DeVries, Adriana Romero, Luis Pineda +2
Conditional Generative Adversarial Networks (cGANs) are finding increasingly widespread use in many application domains. Despite outstanding progress, quantitative evaluation of su…
Video Modeling with Correlation Networks
Heng Wang, Du Tran, Lorenzo Torresani +1
Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly b…