136 citations · 160 across the 18 of their papers we have counts for
18 papers
Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective
Hongyi Fang, Chuwen Xie, Benjia Zhou +6
Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to-fine prediction. However, t…
PatchHead: Learning Spatial Patch Evidence for Generalizable AI-Generated Image Detection
Shengbo Qi, Hongyi Fang, Benjia Zhou +1
AI-generated image detectors generalize poorly when their training and test images originate from different generators or datasets. Despite the rich spatial representations produce…
Detail Continuation over a Trustworthy Coarse Scale for Autoregressive Super-Resolution
Hongyi Fang, Jiahui Wu, Yichen Yue +2
Hallucination remains a persistent challenge in generative super-resolution (GSR), where reconstructed results may contain visually plausible yet weakly supported content, structur…
Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction
Tianshun Han, Ziyu Shi, Lijian Liu +7
Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenarios. They often produce unstabl…
RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation
Zhi Rao, Yucheng Zhou, Benjia Zhou +3
Gloss-free sign language translation (SLT) is hindered by two key challenges: **inadequate sign representation** that fails to capture nuanced visual cues, and **sentence-level sem…
PESTalk: Speech-Driven 3D Facial Animation with Personalized Emotional Styles
Tianshun Han, Benjia Zhou, Ajian Liu +4
PESTalk is a novel method for generating 3D facial animations with personalized emotional styles directly from speech. It overcomes key limitations of existing approaches by introd…
ReMix: Towards a Unified View of Consistent Character Generation and Editing
Benjia Zhou, Bin Fu, Pei Cheng +3
Recent advances in large-scale text-to-image diffusion models (e.g., FLUX.1) have greatly improved visual fidelity in consistent character generation and editing. However, existing…
CRL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval
Zhigang Chen, Benjia Zhou, Yiqing Huang +6
Sign Language Representation Learning (SLRL) is crucial for a range of sign language-related downstream tasks such as Sign Language Translation (SLT) and Sign Language Retrieval (S…
Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation
Zhigang Chen, Benjia Zhou, Jun Li +5
Previous Sign Language Translation (SLT) methods achieve superior performance by relying on gloss annotations. However, labeling high-quality glosses is a labor-intensive task, whi…
PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features
Tianshun Han, Shengnan Gui, Yiqing Huang +9
Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading…
Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition
Yujun Ma, Benjia Zhou, Ruili Wang +1
RGB-D action and gesture recognition remain an interesting topic in human-centered scene understanding, primarily due to the multiple granularities and large variation in human mot…
Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining
Benjia Zhou, Zhigang Chen, Albert Clapés +5
Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an…
A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
Benjia Zhou, Pichao Wang, Jun Wan +2
Motion recognition is a promising direction in computer vision, but the training of video classification models is much harder than images due to insufficient data and considerable…
Effective Vision Transformer Training: A Data-Centric Perspective
Benjia Zhou, Pichao Wang, Jun Wan +2
Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we…
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
Benjia Zhou, Pichao Wang, Jun Wan +6
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognitio…
Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition
Benjia Zhou, Yunan Li, Jun Wan
Human gesture recognition has drawn much attention in the area of computer vision. However, the performance of gesture recognition is always influenced by some gesture-irrelevant f…
Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
Zitong Yu, Benjia Zhou, Jun Wan +5
Gesture recognition has attracted considerable attention owing to its great potential in applications. Although the great progress has been made recently in multi-modal learning me…
Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review
Ajian Liu, Xuan Li, Jun Wan +12
Face anti-spoofing is critical to prevent face recognition systems from a security breach. The biometrics community has %possessed achieved impressive progress recently due the exc…