42 citations · 248 across the 35 of their papers we have counts for
32 papers · 1 filter
MUSE: Feature Self-Distillation with Mutual Information and Self-Information
Yu Gong, Ye Yu, Gaurav Mittal +2
We present a novel information-theoretic approach to introduce dependency among features of a deep convolutional neural network (CNN). The core idea of our proposed method, called…
D3D-HOI: Dynamic 3D Human-Object Interactions from Videos
Xiang Xu, Hanbyul Joo, Greg Mori +1
We introduce D3D-HOI: a dataset of monocular videos with ground truth annotations of 3D object pose, shape and part motion during human-object interactions. Our dataset consists of…
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
Mengyao Zhai, Lei Chen, Jiawei He +3
Humans accumulate knowledge in a lifelong fashion. Modern deep neural networks, on the other hand, are susceptible to catastrophic forgetting: when adapted to perform new tasks, th…
Adaptive Appearance Rendering
Mengyao Zhai, Ruizhi Deng, Jiacheng Chen +3
We propose an approach to generate images of people given a desired appearance and pose. Disentangled representations of pose and appearance are necessary to handle the compound va…
Learning Discriminative Prototypes with Dynamic Time Warping
Xiaobin Chang, Frederick Tung, Greg Mori
Dynamic Time Warping (DTW) is widely used for temporal data processing. However, existing methods can neither learn the discriminative prototypes of different classes nor exploit s…
Activity Graph Transformer for Temporal Action Localization
Megha Nawhal, Greg Mori
We introduce Activity Graph Transformer, an end-to-end learnable model for temporal action localization, that receives a video as input and directly predicts a set of action instan…