activity
20182021
most citedUniCon: Unified Context Network for Robust Active Speaker Detection

39 citations · 45 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV202139 cited

UniCon: Unified Context Network for Robust Active Speaker Detection

Yuanhang Zhang, Susan Liang, Shuang Yang +4

We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candida…

cs.CV2020

Deformation Flow Based Two-Stream Network for Lip Reading

Jingyun Xiao, Shuang Yang, Yuanhang Zhang +2

Lip reading is the task of recognizing the speech content by analyzing movements in the lip region when people are speaking. Observing on the continuity in adjacent frames in the s…

cs.CV2020

Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition

Yuanhang Zhang, Shuang Yang, Jingyun Xiao +2

Recent advances in deep learning have heightened interest among researchers in the field of visual speech recognition (VSR). Currently, most existing methods equate VSR with automa…

cs.CV20206 cited

T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild

Yuan-Hang Zhang, Rulin Huang, Jiabei Zeng +2

This report describes a multi-modal multi-task (T) approach underlying our submission to the valence-arousal estimation track of the Affective Behavior Analysis in-the-wild (A…

cs.CV2018

LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild

Shuang Yang, Yuanhang Zhang, Dalu Feng +6

Large-scale datasets have successively proven their fundamental importance in several research fields, especially for early progress in some emerging topics. In this paper, we focu…

cs.CV2018

3D Feature Pyramid Attention Module for Robust Visual Speech Recognition

Jingyun Xiao

Visual speech recognition is the task to decode the speech content from a video based on visual information, especially the movements of lips. It is also referenced as lipreading.…