Haiying Xia

GeoFANet: A Geometry–Frequency Adaptive Network for Robust Cross-Domain Point Cloud Registration

Anran Lei, Lineng Chen, Hui Li, Shuxiang Song et autres

cn (code pays fourni par la source)

Mamba-Driven Diffusion Model for Salient Object Detection in Optical Remote Sensing Images

Jinsheng Yang, Bineng Zhong, Qihua Liang, Yufei Tan et autres

Existing Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) methods mainly rely on a semantic segmentation paradigm, which relies on pixel-wise probabilities, leading to overconfident mispredictions. In contrast, the random sampling process of the diffusion model allows multiple possible predictions to be …

cn (code pays fourni par la source)

Enhancing Intra-class Diversity Perception for Facial Emotion Recognition

Yanling Gan, Luhui Xu, Haiying Xia, Shuxiang Song et autres

cn (code pays fourni par la source)

ACT-YOLO: An Efficient Multi-Module Fusion Object Detection Algorithm for Steel Surface Defect Detection

Peng Tang, Peng Chen, Ting Tin Tin, Jiaqi Zhao et autres

With the development of intelligent manufacturing, higher requirements for real-time performance and accuracy have been placed on the inspection of surface quality in industrial products. As a core basic material in manufacturing, steel has various complex surface defects, such as cracks, scratches, …

cn (code pays fourni par la source)

HEL-Net: Heterogeneous Ensemble Learning for comprehensive diabetic retinopathy multi-lesion segmentation via Mamba-UNet

Lingyu Wu, Haiying Xia, Shuxiang Song, Lan Yang

cn (code pays fourni par la source)

Explicit Context Reasoning with Supervision for Visual Tracking

Bineng Zhong, Haiying Xia, Yufei Tan, Xiantao Hu et autres

Contextual reasoning with constraints is crucial for enhancing temporal consistency in cross-frame modeling for visual tracking. However, mainstream tracking algorithms typically associate context by merely stacking historical information without explicitly supervising the association process, making it difficult to effectively model the target's …

cn (code pays fourni par la source)

Momentum-based prototype-centered learning for dynamic facial expression recognition

Zichen Liang, Haiying Xia, Yumei Tan, Shuxiang Song

cn (code pays fourni par la source)

Explicit Context Reasoning with Supervision for Visual Tracking

Fansheng Zeng, Bineng Zhong, Haiying Xia, Yufei Tan et autres

Contextual reasoning with constraints is crucial for enhancing temporal consistency in cross-frame modeling for visual tracking. However, mainstream tracking algorithms typically associate context by merely stacking historical information without explicitly supervising the association process, making it difficult to effectively model the target's …

TEMSA:Text enhanced modal representation learning for multimodal sentiment analysis

Shuxiang Song, Yumei Tan, Haiying Xia

cn (code pays fourni par la source)

DTIL-Net: Dual-Task Interactive Learning Network for Automated Grading of Diabetic Retinopathy and Macular Edema

Jie Long, Yumei Tan, Shuxiang Song, Haiying Xia

cn (code pays fourni par la source)

CFMISA: Cross-Modal Fusion of Modal Invariant and Specific Representations for Multimodal Sentiment Analysis

Haiying Xia, Jingwen Chen, Yumei Tan, Xiaohu Tang

cn (code pays fourni par la source)

Unifying Motion and Appearance Cues for Visual Tracking via Shared Queries

Chaocan Xue, Bineng Zhong, Qihua Liang, Haiying Xia et autres

The rich motion and appearance cues between consecutive frames are crucial for robust visual tracking. However, most existing tracking methods are still limited in designing different components to separately employ corresponding cues and even ignore one of them. This makes them difficult …

cn (code pays fourni par la source)