activity
20172022
most citedUnderstanding the Role of Individual Units in a Deep Neural Network

385 citations · 959 across the 32 of their papers we have counts for

collaborators
Showing cs.CVShow all

45 papers · 1 filter

cs.CV202212 cited

Improving GANs with A Dynamic Discriminator

Ceyuan Yang, Yujun Shen, Yinghao Xu +3

Discriminator plays a vital role in training generative adversarial networks (GANs) via distinguishing real and synthesized samples. While the real data distribution remains the sa…

cs.CV20226 cited

Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation

Xian Liu, Qianyi Wu, Hang Zhou +7

Generating speech-consistent body and gesture movements is a long-standing problem in virtual avatar creation. Previous studies often synthesize pose movement in a holistic manner,…

cs.CV20224 cited

LocATe: End-to-end Localization of Actions in 3D with Transformers

Jiankai Sun, Bolei Zhou, Michael J. Black +1

Understanding a person's behavior from their 3D motion is a fundamental problem in computer vision with many applications. An important component of this problem is 3D Temporal Act…

cs.CV2022

Visual Sound Localization in the Wild by Cross-Modal Interference Erasing

Xian Liu, Rui Qian, Hang Zhou +5

The task of audio-visual sound source localization has been well studied under constrained scenes, where the audio recordings are clean. However, in real-world scenarios, audios ar…

cs.CV20227 cited

Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation

Xian Liu, Yinghao Xu, Qianyi Wu +3

Animating high-fidelity video portrait with speech audio is crucial for virtual reality and digital entertainment. While most previous studies rely on accurate explicit structural…

cs.CV2022

SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

Zhenyu Li, Zehui Chen, Ang Li +6

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy betwe…