5 papers
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
Xingyu Qiu, Yuqian Fu, Jiawei Geng +70
Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across…
A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models
Weixin Ye, Wei Wang, Yahui Liu +5
In federated learning, Transformer, as a popular architecture, faces critical challenges in defending against gradient attacks and improving model performance in both Computer Visi…
DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining
Yihong Wu, Jinqiao Wei, Xionghui Zhao +4
Deep learning-based crowd counting methods have achieved remarkable progress in recent years. However, in complex crowd scenarios, existing models still face challenges when adapti…
Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities
Yidi Li, Yihan Li, Yixin Guo +5
In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking…
Hierarchical Cross-Attention Network for Virtual Try-On
Hao Tang, Bin Ren, Pingping Wu +1
In this paper, we present an innovative solution for the challenges of the virtual try-on task: our novel Hierarchical Cross-Attention Network (HCANet). HCANet is crafted with two…