74 citations
- Tsinghua UniversityCN3 papers
- Nanjing UniversityCN2 papers
- Peking UniversityCN2 papers
- State Key Laboratory of Intelligent Technology and Systems2 papers
- University of Technology SydneyAU2 papers
- Wuhan UniversityCN2 papers
- Beijing Institute of TechnologyCN1 paper
- Beijing National Research Center for Information Science and TechnologyCN1 paper
- Beijing University of Posts and TelecommunicationsCN1 paper
- Centre for Quantum Computation and Communication TechnologyAU1 paper
- China Telecom1 paper
- China Telecom (China)CN1 paper
17 papers
FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning
Jinhui Pang, Changqing Lin, Xiaoshuai Hao +5
Continual graph learning (CGL) is an important and challenging task that aims to extend static GNNs to dynamic task flow scenarios. As one of the mainstream CGL methods, the experi…
ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera
Jun Shi, Yong A, Yixiang Jin +4
In this paper, we tackle the problem of grasping transparent and specular objects. This issue holds importance, yet it remains unsolved within the field of robotics due to failure…
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Ivan DeAndres-Tame, Ruben Tolosana, Pietro Melzi +55
Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class v…
Information Bottleneck-Inspired Type Based Multiple Access for Remote Estimation in IoT Systems
Meiyi Zhu, Chunyan Feng, Caili Guo +2
Type-based multiple access (TBMA) is a semantics-aware multiple access protocol for remote inference. In TBMA, codewords are reused across transmitting sensors, with each codeword…
DMTNet: Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer
Dafeng Zhang, Xiaobing Wang
Recent works achieve excellent results in defocus deblurring task based on dual-pixel data using convolutional neural network (CNN), while the scarcity of data limits the explorati…
Leveraged Weighted Loss for Partial Label Learning
Hongwei Wen, Jingyi Cui, Hanyuan Hang +3
As an important branch of weakly supervised learning, partial label learning deals with data where each instance is assigned with a set of candidate labels, whereas only one of the…