50 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Beijing Institute of TechnologyCN4 papers
- Beijing University of Posts and TelecommunicationsCN2 papers
- Didi Chuxing (China)2 papers
- Harbin Institute of TechnologyCN2 papers
- Syracuse UniversityUS2 papers
- Tsinghua UniversityCN2 papers
- Beijing Advanced Sciences and Innovation CenterCN1 paper
- Delft University of TechnologyNL1 paper
- East China Normal UniversityCN1 paper
- Huazhong University of Science and TechnologyCN1 paper
- Kuaishou (China)1 paper
- Michigan State UniversityUS1 paper
16 papers
EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution
Dachun Kai, Jiayao Lu, Yueyi Zhang +1
Event-based vision has drawn increasing attention owing to its distinctive properties, including ultra-high temporal resolution and extreme dynamic range. Recent works have introdu…
ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
Kun Wu, Yinuo Zhao, Zhiyuan Xu +5
Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a saf…
GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning
Heng Xiong, Changrong Guo, Jian Peng +5
Robotic object packing has broad practical applications in the logistics and automation industry, often formulated by researchers as the online 3D Bin Packing Problem (3D-BPP). How…
Visual Attention Based Cognitive Human-Robot Collaboration for Pedicle Screw Placement in Robot-Assisted Orthopedic Surgery
Chen Chen, Qikai Zou, Yuhang Song +4
Current orthopedic robotic systems largely focus on navigation, aiding surgeons in positioning a guiding tube but still requiring manual drilling and screw placement. The automatio…
Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
Siyuan Shen, Yu Gao, Feng Liu +2
The mainstream paradigm of speech emotion recognition (SER) is identifying the single emotion label of the entire utterance. This line of works neglect the emotion dynamics at fine…
DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field
Haowen Wang, Zhipeng Fan, Zhen Zhao +7
Estimating 6D poses and reconstructing 3D shapes of objects in open-world scenes from RGB-depth image pairs is challenging. Many existing methods rely on learning geometric feature…
RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion
Haowen Wang, Zhengping Che, Yufan Yang +6
Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments. For example, transparent…
Reducing Communication for Split Learning by Randomized Top-k Sparsification
Fei Zheng, Chaochao Chen, Lingjuan Lyu +1
Split learning is a simple solution for Vertical Federated Learning (VFL), which has drawn substantial attention in both research and application due to its simplicity and efficien…
Topological materials for full-vector elastic waves
Ying Wu, Jiuyang Lu, Xueqin Huang +6
Elastic wave manipulation is important in a wide variety of scales in applications including information processing in tiny elastic devices and noise control in big solid structure…
LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision
Rui Han, Qinglong Zhang, Chi Harold Liu +3
Deep neural networks (DNNs) have become ubiquitous techniques in mobile and embedded systems for applications such as image/object recognition and classification. The trend of exec…
CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization
Wenzheng Hu, Zhengping Che, Ning Liu +4
Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have…
Research on Brick Schema Representation for Building Operation with Variable Refrigerant Flow Systems
Jingming Li, Nianping Li, Rui Yan +3
Building metadata is regarded as the signpost in organizing massive building data. The application of building metadata simplifies the creation of digital representations and provi…
Human Pose Transfer with Augmented Disentangled Feature Consistency
Kun Wu, Chengxiang Yin, Zhengping Che +4
Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have…
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
Ning Liu, Geng Yuan, Zhengping Che +7
In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i.e., a properly prune…
DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
Yushuo Guan, Ning Liu, Pengyu Zhao +4
The convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead against efficient deployment. Structured (channel…
A Novel Co-design Peta-scale Heterogeneous Cluster for Deep Learning Training
Xin Chen, Hua Zhou, Yuxiang Gao +1
Large scale deep Convolution Neural Networks (CNNs) increasingly demands the computing power. It is key for researchers to own a great powerful computing platform to leverage deep…