7 papers
FOUND: Fourier-based von Mises Distribution for Robust Single Domain Generalization in Object Detection
Mengzhu Wang, Changyuan Deng, Shanshan Wang +3
Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent metho…
Geometry-Aware Spiking Graph Neural Network
Bowen Zhang, Genan Dai, Hu Huang +1
Graph Neural Networks (GNNs) have demonstrated impressive capabilities in modeling graph-structured data, while Spiking Neural Networks (SNNs) offer high energy efficiency through…
DMSC: Dynamic Multi-Scale Coordination Framework for Time Series Forecasting
Haonan Yang, Jianchao Tang, Zhuo Li +1
Time Series Forecasting (TSF) faces persistent challenges in modeling intricate temporal dependencies across different scales. Despite recent advances leveraging different decompos…
TransMedSeg: A Transferable Semantic Framework for Semi-Supervised Medical Image Segmentation
Mengzhu Wang, Jiao Li, Shanshan Wang +4
Semi-supervised learning (SSL) has achieved significant progress in medical image segmentation (SSMIS) through effective utilization of limited labeled data. While current SSL meth…
Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering
Peipei Song, Long Zhang, Long Lan +4
Partially relevant video retrieval (PRVR) is a practical yet challenging task in text-to-video retrieval, where videos are untrimmed and contain much background content. The pursui…
JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation
Fangda Chen, Shanshan Zhao, Chuanfu Xu +1
Recent advancements in customized video generation have led to significant improvements in the simultaneous adaptation of appearance and motion. Typically, decoupling the appearanc…
Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization
Hao Li, Yubin Xiao, Ke Liang +4
Single Domain Generalization (SDG) aims to train models that maintain consistent performance across diverse scenarios using data from a single source. While latent diffusion models…