287 citations · 810 across the 21 of their papers we have counts for
21 papers
Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer
Yining Ma, Jingwen Li, Zhiguang Cao +4
Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP be…
Free Lunch for Co-Saliency Detection: Context Adjustment
Lingdong Kong, Prakhar Ganesh, Tan Wang +3
We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-salien…
Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
Yu Qiu, Yun Liu, Le Zhang +1
Existing salient object detection (SOD) methods mainly rely on U-shaped convolution neural networks (CNNs) with skip connections to combine the global contexts and local spatial de…
Unsupervised Scale-consistent Depth Learning from Video
Jia-Wang Bian, Huangying Zhan, Naiyan Wang +5
We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions…
EDN: Salient Object Detection via Extremely-Downsampled Network
Yu-Huan Wu, Yun Liu, Le Zhang +2
Recent progress on salient object detection (SOD) mainly benefits from multi-scale learning, where the high-level and low-level features collaborate in locating salient objects and…
Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
Yu-Chao Gu, Le Zhang, Yun Liu +2
Generalized zero-shot learning (GZSL) aims to recognize both seen and unseen classes by transferring knowledge from semantic descriptions to visual representations. Recent generati…
Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
Yu-Huan Wu, Yun Liu, Le Zhang +2
Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we pro…
Disentangling Human Error from the Ground Truth in Segmentation of Medical Images
Le Zhang, Ryutaro Tanno, Mou-Cheng Xu +5
Recent years have seen increasing use of supervised learning methods for segmentation tasks. However, the predictive performance of these algorithms depends on the quality of label…
AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning
Xin-Yu Zhang, Le Zhang, Zao-Yi Zheng +3
Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the tri…
Robust Regression via Deep Negative Correlation Learning
Le Zhang, Zenglin Shi, Ming-Ming Cheng +5
Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning…
A Deep Framework for Bone Age Assessment based on Finger Joint Localization
Xiaoman Zhang, Ziyuan Zhao, Cen Chen +6
Bone age assessment is an important clinical trial to measure skeletal child maturity and diagnose of growth disorders. Conventional approaches such as the Tanner-Whitehouse (TW) a…
Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation
Ziyuan Zhao, Xiaoman Zhang, Cen Chen +6
Segmentation stands at the forefront of many high-level vision tasks. In this study, we focus on segmenting finger bones within a newly introduced semi-supervised self-taught deep…
High Throughput Computation of Reference Ranges of Biventricular Cardiac Function on the UK Biobank Population Cohort
Rahman Attar, Marco Pereanez, Ali Gooya +6
The exploitation of large-scale population data has the potential to improve healthcare by discovering and understanding patterns and trends within this data. To enable high throug…
Salient Object Detection via High-to-Low Hierarchical Context Aggregation
Yun Liu, Yu Qiu, Le Zhang +3
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate convolutional side-output features in convolutional neural networks (CNN). Based…
Automatic Assessment of Full Left Ventricular Coverage in Cardiac Cine Magnetic Resonance Imaging with Fisher-Discriminative 3D CNN
Le Zhang, Ali Gooya, Marco Pereanez +5
Cardiac magnetic resonance (CMR) images play a growing role in the diagnostic imaging of cardiovascular diseases. Full coverage of the left ventricle (LV), from base to apex, is a…
PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship
Le Zhang, Songyou Peng, Stefan Winkler
Apparent personality and emotion analysis are both central to affective computing. Existing works solve them individually. In this paper we investigate if such high-level affect tr…
MatchBench: An Evaluation of Feature Matchers
JiaWang Bian, Ruihan Yang, Yun Liu +4
Feature matching is one of the most fundamental and active research areas in computer vision. A comprehensive evaluation of feature matchers is necessary, since it would advance bo…
Learning Pixel-wise Labeling from the Internet without Human Interaction
Yun Liu, Yujun Shi, JiaWang Bian +3
Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samp…
A Deep Network for Arousal-Valence Emotion Prediction with Acoustic-Visual Cues
Songyou Peng, Le Zhang, Yutong Ban +2
In this paper, we comprehensively describe the methodology of our submissions to the One-Minute Gradual-Emotion Behavior Challenge 2018.
Semantic Edge Detection with Diverse Deep Supervision
Yun Liu, Ming-Ming Cheng, Deng-Ping Fan +3
Semantic edge detection (SED), which aims at jointly extracting edges as well as their category information, has far-reaching applications in domains such as semantic segmentation,…
Image Matching: An Application-oriented Benchmark
JiaWang Bian, Le Zhang, Yun Liu +3
Image matching approaches have been widely used in computer vision applications in which the image-level matching performance of matchers is critical. However, it has not been well…