431 citations · 1k across the 24 of their papers we have counts for
24 papers
Streaming Autoregressive Video Generation via Diagonal Distillation
Jinxiu Liu, Xuanming Liu, Kangfu Mei +3
Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer…
Towards Variable and Coordinated Holistic Co-Speech Motion Generation
Yifei Liu, Qiong Cao, Yandong Wen +2
This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the…
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Weiyang Liu, Zeju Qiu, Yao Feng +11
Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is…
Pairwise Similarity Learning is SimPLE
Yandong Wen, Weiyang Liu, Yao Feng +5
In this paper, we focus on a general yet important learning problem, pairwise similarity learning (PSL). PSL subsumes a wide range of important applications, such as open-set face…
Text-Guided Generation and Editing of Compositional 3D Avatars
Hao Zhang, Yao Feng, Peter Kulits +3
Our goal is to create a realistic 3D facial avatar with hair and accessories using only a text description. While this challenge has attracted significant recent interest, existing…
The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features
Liao Qu, Xianwei Zou, Xiang Li +3
This work unveils the enigmatic link between phonemes and facial features. Traditional studies on voice-face correlations typically involve using a long period of voice input, incl…
Rethinking Voice-Face Correlation: A Geometry View
Xiang Li, Yandong Wen, Muqiao Yang +3
Previous works on voice-face matching and voice-guided face synthesis demonstrate strong correlations between voice and face, but mainly rely on coarse semantic cues such as gender…
Emotional Speech-Driven Animation with Content-Emotion Disentanglement
Radek Daněček, Kiran Chhatre, Shashank Tripathi +3
To be widely adopted, 3D facial avatars must be animated easily, realistically, and directly from speech signals. While the best recent methods generate 3D animations that are sync…
Generating Holistic 3D Human Motion from Speech
Hongwei Yi, Hualin Liang, Yifei Liu +5
This work addresses the problem of generating 3D holistic body motions from human speech. Given a speech recording, we synthesize sequences of 3D body poses, hand gestures, and fac…
Self-Supervised 3D Face Reconstruction via Conditional Estimation
Yandong Wen, Weiyang Liu, Bhiksha Raj +1
We present a conditional estimation (CEST) framework to learn 3D facial parameters from 2D single-view images by self-supervised training from videos. CEST is based on the process…
SphereFace Revived: Unifying Hyperspherical Face Recognition
Weiyang Liu, Yandong Wen, Bhiksha Raj +2
This paper addresses the deep face recognition problem under an open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal…
SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Yandong Wen, Weiyang Liu, Adrian Weller +2
State-of-the-art deep face recognition methods are mostly trained with a softmax-based multi-class classification framework. Despite being popular and effective, these methods stil…
MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
Alexander Richard, Michael Zollhoefer, Yandong Wen +2
This paper presents a generic method for generating full facial 3D animation from speech. Existing approaches to audio-driven facial animation exhibit uncanny or static upper face…
Detecting gender differences in perception of emotion in crowdsourced data
Shahan Ali Memon, Hira Dhamyal, Oren Wright +5
Do men and women perceive emotions differently? Popular convictions place women as more emotionally perceptive than men. Empirical findings, however, remain inconclusive. Most prio…
Reconstructing faces from voices
Yandong Wen, Rita Singh, Bhiksha Raj
Voice profiling aims at inferring various human parameters from their speech, e.g. gender, age, etc. In this paper, we address the challenge posed by a subtask of voice profiling -…
Disjoint Mapping Network for Cross-modal Matching of Voices and Faces
Yandong Wen, Mahmoud Al Ismail, Weiyang Liu +2
We propose a novel framework, called Disjoint Mapping Network (DIMNet), for cross-modal biometric matching, in particular of voices and faces. Different from the existing methods,…
Optimal Strategies for Matching and Retrieval Problems by Comparing Covariates
Yandong Wen, Mahmoud Al Ismail, Bhiksha Raj +1
In many retrieval problems, where we must retrieve one or more entries from a gallery in response to a probe, it is common practice to learn to do by directly comparing the probe a…
SphereFace: Deep Hypersphere Embedding for Face Recognition
Weiyang Liu, Yandong Wen, Zhiding Yu +3
This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal in…
Large-Margin Softmax Loss for Convolutional Neural Networks
Weiyang Liu, Yandong Wen, Zhiding Yu +1
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity…
Range Loss for Deep Face Recognition with Long-tail
Xiao Zhang, Zhiyuan Fang, Yandong Wen +2
Convolutional neural networks have achieved great improvement on face recognition in recent years because of its extraordinary ability in learning discriminative features of people…
Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification
Weiyang Liu, Zhiding Yu, Yandong Wen +2
Sparse coding with dictionary learning (DL) has shown excellent classification performance. Despite the considerable number of existing works, how to obtain features on top of whic…
Efficient Face Alignment via Locality-constrained Representation for Robust Recognition
Yandong Wen, Weiyang Liu, Meng Yang +1
Practical face recognition has been studied in the past decades, but still remains an open challenge. Current prevailing approaches have already achieved substantial breakthroughs…
Structured Occlusion Coding for Robust Face Recognition
Yandong Wen, Weiyang Liu, Meng Yang +3
Occlusion in face recognition is a common yet challenging problem. While sparse representation based classification (SRC) has been shown promising performance in laboratory conditi…
KCRC-LCD: Discriminative Kernel Collaborative Representation with Locality Constrained Dictionary for Visual Categorization
Weiyang Liu, Zhiding Yu, Lijia Lu +3
We consider the image classification problem via kernel collaborative representation classification with locality constrained dictionary (KCRC-LCD). Specifically, we propose a kern…