Fan Zhou

Visualization Imaging Model Guided Generalizable Real Rainy Image Deraining

Xin Li, Yuxin Feng, Zhe Huang, Fan Zhou et autres

cn (code pays fourni par la source)

DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale

Ke Du, Yimin Peng, Chao Gao, Fan Zhou et autres

DORAEMON is an open-source PyTorch library that unifies visual object modeling and representation learning across diverse scales. A single YAML-driven workflow covers classification, retrieval and metric learning; more than 1000 pretrained backbones are exposed through a timm-compatible interface, together with modular losses, …

Breaking the Synthetic Barrier: Towards Stable and Generalizable Real-World Image Dehazing

Zhuo Su, Jufeng Li, Fuwei Zhang, Yuxin Feng et autres

Existing learning-based dehazing methods perform well on synthetic data but struggle in real scenarios due to the domain gap, causing residual haze and detail loss. To address this, we propose a Multilevel Subspace Distribution Adapter (MSDA) to progressively reduce the feature distribution …

cn, mo (code pays fourni par la source)

VisAug: Facilitating Speech-Rich Web Video Navigation and Engagement with Auto-Generated Visual Augmentations

Baoquan Zhao, Xiaofan Ma, Qianshi Pang, Ruomei Wang et autres

The widespread adoption of digital technology has ushered in a new era of digital transformation across all aspects of our lives. Online learning, social, and work activities, such as distance education, videoconferencing, interviews, and talks, have led to a dramatic increase in …

cn (code pays fourni par la source)

DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition

Juepeng Zheng, Yikun Chen, Xudong Mao, Guanghui Yue et autres

Robust gait recognition requires highly discriminative representations, which are closely tied to input modalities. While binary silhouettes and skeletons have dominated recent literature, these 2D representations fall short of capturing sufficient cues that can be exploited to handle viewpoint variations, and capture …

cn, gb (code pays fourni par la source)

Free-Moref: Instantly Multiplexing Context Perception Capabilities of Video-Mllms Within Single Inference

Kuo Wang, Quanlong Zheng, Junlin Xie, Yanhao Zhang et autres

Video Multimodal Large Language Models~(Video-MLLM) have achieved remarkable advancements in video understanding tasks. However, constrained by the context length limitation in the underlying LLMs, existing Video-MLLMs typically exhibit suboptimal performance on long video scenarios. To understand extended input frames, common solutions span …

cn, nl (code pays fourni par la source)

Qwen3-Omni Technical Report

Xu Jin, Zhifang Guo, H. Hu, Yunfei Chu et autres

We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the performance of same-sized single-modal models within the Qwen series and excels …

Design optimization of stress isolation groove for off-axis three-reflector based on sensitivity analysis of structural parameters

Fan Zhou, Mingchao Wang, Huilin Wang, Bo Zhang

This study presents a methodical approach for optimizing stress isolation grooves in off-axis three-reflector systems through sensitivity analysis of structural parameters. Findings reveal that groove depth and spacing are critical parameters determining isolation effectiveness, accounting for 54% of performance variability according to …

MSPoint-Gait: Multi-Scale Point Cloud Analysis for 3D Gait Recognition via Cross-Modal Learning

Xinzhu Li, Yang Yi, Yikun Chen, Guanghui Yue et autres

Recent advances in LiDAR technology have enabled privacy-preserving gait recognition using 3D point cloud data. However, existing approaches struggle with the inherent challenges of point cloud processing and understanding such as spatial sparsity, irregular sampling, and complex temporal dynamics. In this paper, …

cn, gb (code pays fourni par la source)

MCSMoG: Multi-Conditional Diffusion for Stylized Motion Generation with Parametric Control

Yi Yang, Xinzhu Li, Yufeng Chen, Guanghui Yue et autres

Stylized human motion synthesis remains a fundamental challenge in computer animation and graphics, with a wide spectrum of applications spanning gaming, film production, virtual reality, and beyond. While recent advances in text-driven motion generation have shown promise, existing approaches face critical limitations …

cn, gb (code pays fourni par la source)

A clinically applicable AI system for detection and diagnosis of bone metastases using CT scans

Jiao Li, Shaohan Yin, Jing Hou, Xiaohuan Cao et autres

Manual interpretation of CT images for bone metastasis (BM) detection in primary cancer remains challenging. We present an automated Bone Lesion Detection System (BLDS) developed using CT scans from 2518 patients (9177 BMs; 12,824 non-BM lesions) across five hospitals. The system, developed …

cn (code pays fourni par la source)

Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation

Xovee Xu, Yifan Zhang, Fan Zhou, Jingkuan Song

Understanding and predicting the popularity of online User-Generated Content (UGC) is critical for various social and recommendation systems. Existing efforts have focused on extracting predictive features and using pre-trained deep models to learn and fuse multimodal UGC representations. However, the dissemination of …

cn (code pays fourni par la source)