213 citations · 255 across the 13 of their papers we have counts for
13 papers
On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
Jianhong Bai, Zuozhu Liu, Hualiang Wang +4
Though Self-supervised learning (SSL) has been widely studied as a promising technique for representation learning, it doesn't generalize well on long-tailed datasets due to the ma…
Learning Dynamic Graphs from All Contextual Information for Accurate Point-of-Interest Visit Forecasting
Arash Hajisafi, Haowen Lin, Sina Shaham +4
Forecasting the number of visits to Points-of-Interest (POI) in an urban area is critical for planning and decision-making for various application domains, from urban planning and…
Clustering Human Mobility with Multiple Spaces
Haoji Hu, Haowen Lin, Yao-Yi Chiang
Human mobility clustering is an important problem for understanding human mobility behaviors (e.g., work and school commutes). Existing methods typically contain two steps: choosin…
Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning
Hualiang Wang, Siming Fu, Xiaoxuan He +3
Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little at…
AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications
Jin Hao, Jiaxiang Liu, Jin Li +17
A critical step in virtual dental treatment planning is to accurately delineate all tooth-bone structures from CBCT with high fidelity and accurate anatomical information. Previous…
UWC: Unit-wise Calibration Towards Rapid Network Compression
Chen Lin, Zheyang Li, Bo Peng +4
This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance. Previous PTQ meth…
SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks
Kuan Zhang, Haoji Hu, Kenneth Philbrick +4
There is a growing demand for high-resolution (HR) medical images in both the clinical and research applications. Image quality is inevitably traded off with the acquisition time f…
Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition
Bianjiang Yang, Zi Hui, Haoji Hu +2
Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massi…
Modeling Personalized Item Frequency Information for Next-basket Recommendation
Haoji Hu, Xiangnan He, Jinyang Gao +1
Next-basket recommendation (NBR) is prevalent in e-commerce and retail industry. In this scenario, a user purchases a set of items (a basket) at a time. NBR performs sequential mod…
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
Huan Wang, Yijun Li, Yuehai Wang +2
Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of imag…
Physics-Guided Deep Neural Networks for Power Flow Analysis
Xinyue Hu, Haoji Hu, Saurabh Verma +1
Solving power flow (PF) equations is the basis of power flow analysis, which is important in determining the best operation of existing systems, performing security analysis, etc.…
Structured Pruning for Efficient ConvNets via Incremental Regularization
Huan Wang, Qiming Zhang, Yuehai Wang +1
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness,…
Structured Pruning for Efficient ConvNets via Incremental Regularization
Huan Wang, Qiming Zhang, Yuehai Wang +2
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectivene…