244 citations · 772 across the 26 of their papers we have counts for
7 papers · 1 filter
MAViL: Masked Audio-Video Learners
Po-Yao Huang, Vasu Sharma, Hu Xu +7
We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of…
Scaling Language-Image Pre-training via Masking
Yanghao Li, Haoqi Fan, Ronghang Hu +2
We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP. Our method randomly masks out and removes a large portion of image patches…
Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization
Mengmeng Xu, Yanghao Li, Cheng-Yang Fu +3
This paper deals with the problem of localizing objects in image and video datasets from visual exemplars. In particular, we focus on the challenging problem of egocentric visual q…
Negative Frames Matter in Egocentric Visual Query 2D Localization
Mengmeng Xu, Cheng-Yang Fu, Yanghao Li +3
The recently released Ego4D dataset and benchmark significantly scales and diversifies the first-person visual perception data. In Ego4D, the Visual Queries 2D Localization task ai…
Masked Autoencoders As Spatiotemporal Learners
Christoph Feichtenhofer, Haoqi Fan, Yanghao Li +1
This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in vid…
Exploring Plain Vision Transformer Backbones for Object Detection
Yanghao Li, Hanzi Mao, Ross Girshick +1
We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for object detection. This design enables the original ViT architecture to be fine-tuned for o…
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
Chao-Yuan Wu, Yanghao Li, Karttikeya Mangalam +4
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video ar…