9 citations · 21 across the 19 of their papers we have counts for
17 papers · 1 filter
WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World Consistency
Zhuohong Chen, Zhengxian Wu, Yunyao Yu +7
Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artifacts and higher-level visual…
VoRTeC: Taming Foundation Flow for One-step Real time Video Compression
Yichong Xia, Qinhong Wu, Bin Chen +3
Ultra-low bitrate video compression still faces critical challenges: traditional neural video compression inevitably introduces blurring artifacts, while diffusion-based generative…
DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models
Guorui Song, Runqing Tang, Jingye Zhang +11
Large vision-language models (VLMs) are increasingly deployed in safety-critical settings, yet existing visual jailbreak research has focused almost exclusively on autoregressive a…
Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering
Zhuohong Chen, Zhenxian Wu, Yunyao Yu +6
Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts…
R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
Zhuohong Chen, Zhengxian Wu, Zirui Liao +6
Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and i…
Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval
Xiaowan Hu, Yiyi Chen, Yan Li +5
With the rapid expansion of e-commerce, more consumers have become accustomed to making purchases via livestreaming. Accurately identifying the products being sold by salespeople,…
Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images
Chuanrui Zhang, Yonggen Ling, Minglei Lu +2
We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RG…
Monocular Gaussian SLAM with Language Extended Loop Closure
Tian Lan, Qinwei Lin, Haoqian Wang
Recently,3DGaussianSplattinghasshowngreatpotentialin visual Simultaneous Localization And Mapping (SLAM). Existing methods have achieved encouraging results on RGB-D SLAM, but stud…
Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections
Dongbin Zhang, Chuming Wang, Weitao Wang +3
Novel view synthesis from unconstrained in-the-wild images remains a meaningful but challenging task. The photometric variation and transient occluders in those unconstrained image…
Improving Medical Report Generation with Adapter Tuning and Knowledge Enhancement in Vision-Language Foundation Models
Shibin Wu, Bang Yang, Zhiyu Ye +3
Medical report generation demands automatic creation of coherent and precise descriptions for medical images. However, the scarcity of labelled medical image-report pairs poses for…
DPoser: Diffusion Model as Robust 3D Human Pose Prior
Junzhe Lu, Jing Lin, Hongkun Dou +4
This work targets to construct a robust human pose prior. However, it remains a persistent challenge due to biomechanical constraints and diverse human movements. Traditional prior…
Animatable 3D Gaussian: Fast and High-Quality Reconstruction of Multiple Human Avatars
Yang Liu, Xiang Huang, Minghan Qin +2
Neural radiance fields are capable of reconstructing high-quality drivable human avatars but are expensive to train and render and not suitable for multi-human scenes with complex…
DT-NeRF: Decomposed Triplane-Hash Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
Yaoyu Su, Shaohui Wang, Haoqian Wang
In this paper, we present the decomposed triplane-hash neural radiance fields (DT-NeRF), a framework that significantly improves the photorealistic rendering of talking faces and a…
Binarized Spectral Compressive Imaging
Yuanhao Cai, Yuxin Zheng, Jing Lin +3
Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources.…
AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Image
Zhuchen Shao, Liuxi Dai, Yifeng Wang +2
Multiple Instance Learning (MIL), a powerful strategy for weakly supervised learning, is able to perform various prediction tasks on gigapixel Whole Slide Images (WSIs). However, t…
Multiple Instance Learning with Mixed Supervision in Gleason Grading
Hao Bian, Zhuchen Shao, Yang Chen +4
With the development of computational pathology, deep learning methods for Gleason grading through whole slide images (WSIs) have excellent prospects. Since the size of WSIs is ext…
Fast and High Quality Highlight Removal from A Single Image
Dongsheng An, Jinli Suo, Xiangyang Ji +2
Specular reflection exists widely in photography and causes the recorded color deviating from its true value, so fast and high quality highlight removal from a single nature image…