Jinrong Cui,Yuting Li,Han Huang et al.
Jinrong Cui et al.
Consensus representation learning is one of the most popular approaches in the field of multi-view clustering. However, most of the existing methods cannot learn discriminative representations with a clustering-friendly structure since thes...
Decouple Ego-View Motions for Predicting Pedestrian Trajectory and Intention [0.03%]
解耦第一人称运动以预测行人的轨迹和意图
Zhengming Zhang,Zhengming Ding,Renran Tian
Zhengming Zhang
Pedestrian trajectory prediction is a critical component of autonomous driving in urban environments, allowing vehicles to anticipate pedestrian movements and facilitate safer interactions. While egocentric-view-based algorithms can reduce ...
Raunak Manekar,Elisa Negrini,Minh Pham et al.
Raunak Manekar et al.
Phase retrieval (PR) is fundamentally important in scientific imaging and is crucial for nanoscale techniques like coherent diffractive imaging (CDI). Low radiation dose imaging is essential for applications involving radiation-sensitive sa...
Segmentation and Completion of Human Motion Sequence via Temporal Learning of Subspace Variety Model [0.03%]
基于子空间流形模型的时间学习的人体运动序列分割和拼接
Zheng Xing,Weibing Zhao
Zheng Xing
Subspace-based models have been extensively employed in unsupervised segmentation and completion of human motion sequence (HMS). However, existing approaches often neglect the incorporation of temporal priors embedded in HMS, resulting in s...
Shiye Wang,Kaituo Feng,Changsheng Li et al.
Shiye Wang et al.
Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, making training very time- and resource-intens...
Line-Based 6-DoF Object Pose Estimation and Tracking With an Event Camera [0.03%]
基于事件相机的线特征六自由度物体姿态估计与跟踪方法
Zibin Liu,Banglei Guan,Yang Shang et al.
Zibin Liu et al.
Pose estimation and tracking of objects is a fundamental application in 3D vision. Event cameras possess remarkable attributes such as high dynamic range, low latency, and resilience against motion blur, which enables them to address challe...
Joint Under-Sampling Pattern and Dual-Domain Reconstruction for Accelerating Multi-Contrast MRI [0.03%]
基于联合降采样和双域重建的多对比度MRI快速采集方法
Pengcheng Lei,Le Hu,Faming Fang et al.
Pengcheng Lei et al.
Multi-Contrast Magnetic Resonance Imaging (MCMRI) utilizes the short-time reference image to facilitate the reconstruction of the long-time target one, providing a new solution for fast MRI. Although various methods have been proposed, they...
Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation [0.03%]
基于像素级领域自适应的弱监督语义分割研究
Ye Du,Zehua Fu,Qingjie Liu
Ye Du
Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class Activat...
Scalable and Structural Multi-View Graph Clustering With Adaptive Anchor Fusion [0.03%]
自适应锚点融合的可扩展结构多视图图聚类
Siwei Wang,Xinwang Liu,Suyuan Liu et al.
Siwei Wang et al.
Anchor graph has been recently proposed to accelerate multi-view graph clustering and widely applied in various large-scale applications. Different from capturing full instance relationships, these methods choose small portion anchors among...
Image Super-Resolution via Efficient Transformer Embedding Frequency Decomposition With Restart [0.03%]
基于重启的高效Transformer图像超分辨率方法
Yifan Zuo,Wenhao Yao,Yuqi Hu et al.
Yifan Zuo et al.
Recently, transformer-based backbones show superior performance over the convolutional counterparts in computer vision. Due to quadratic complexity with respect to the token number in global attention, local attention is always adopted in l...