activity
20192021
most citedJoint Ranking SVM and Binary Relevance with Robust Low-Rank Learning for Multi-Label Classification

120 citations · 174 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV202152 cited

Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function

Kai Li, Bo Wang, Yingjie Tian +1

Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function…

cs.LG2021

Two-stage Training for Learning from Label Proportions

Jiabin Liu, Bo Wang, Xin Shen +2

Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. Existing deep learning based LLP methods utiliz…

eess.IV20202 cited

Concatenated Attention Neural Network for Image Restoration

Tian YingJie, Wang YiQi, Yang LinRui +1

In this paper, we present a general framework for low-level vision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concaten…

cs.LG2019120 cited

Joint Ranking SVM and Binary Relevance with Robust Low-Rank Learning for Multi-Label Classification

Guoqiang Wu, Ruobing Zheng, Yingjie Tian +1

Multi-label classification studies the task where each example belongs to multiple labels simultaneously. As a representative method, Ranking Support Vector Machine (Rank-SVM) aims…

cs.LG2019

Learning from Label Proportions with Generative Adversarial Networks

Jiabin Liu, Bo Wang, Zhiquan Qi +2

In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level propo…