papers

Publications (5)

cs.CV2020

JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

Linpu Fang, Xingyan Liu, Li Liu +2

State-of-the-art single depth image-based 3D hand pose estimation methods are based on dense predictions, including voxel-to-voxel predictions, point-to-point regression, and pixel…

cs.CV2020

EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement

Linpu Fang, Hang Xu, Zhili Liu +2

Object detectors trained on fully-annotated data currently yield state of the art performance but require expensive manual annotations. On the other hand, weakly-supervised detecto…

cs.CV2020

Dynamic Group Convolution for Accelerating Convolutional Neural Networks

Zhuo Su, Linpu Fang, Wenxiong Kang +3

Replacing normal convolutions with group convolutions can significantly increase the computational efficiency of modern deep convolutional networks, which has been widely adopted i…

cs.CV2020

FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond

Zhuo Su, Linpu Fang, Deke Guo +3

Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated…

cs.CV2020

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

Hang Xu, Linpu Fang, Xiaodan Liang +2

The dominant object detection approaches treat each dataset separately and fit towards a specific domain, which cannot adapt to other domains without extensive retraining. In this…