1.1k citations · 2.6k across the 75 of their papers we have counts for
76 papers
Keypoint Message Passing for Video-based Person Re-Identification
Di Chen, Andreas Doering, Shanshan Zhang +3
Video-based person re-identification (re-ID) is an important technique in visual surveillance systems which aims to match video snippets of people captured by different cameras. Ex…
Fine-Grained Image Analysis with Deep Learning: A Survey
Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha +5
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The…
3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
Le Hui, Lingpeng Wang, Mingmei Cheng +2
3D object tracking in point clouds is still a challenging problem due to the sparsity of LiDAR points in dynamic environments. In this work, we propose a Siamese voxel-to-BEV track…
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Haobo Jiang, Yaqi Shen, Jin Xie +3
In this paper, by modeling the point cloud registration task as a Markov decision process, we propose an end-to-end deep model embedded with the cross-entropy method (CEM) for unsu…
FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation
Guangwei Gao, Guoan Xu, Juncheng Li +3
Real-time semantic segmentation, which can be visually understood as the pixel-level classification task on the input image, currently has broad application prospects, especially i…
Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration
Haobo Jiang, Jin Xie, Jianjun Qian +1
Point cloud registration is a fundamental problem in 3D computer vision. In this paper, we cast point cloud registration into a planning problem in reinforcement learning, which ca…
Going Deeper in Frequency Convolutional Neural Network: A Theoretical Perspective
Xiaohan Zhu, Zhen Cui, Tong Zhang +2
Convolutional neural network (CNN) is one of the most widely-used successful architectures in the era of deep learning. However, the high-computational cost of CNN still hampers mo…
Learning Fair Face Representation With Progressive Cross Transformer
Yong Li, Yufei Sun, Zhen Cui +2
Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still…
Graph Jigsaw Learning for Cartoon Face Recognition
Yong Li, Lingjie Lao, Zhen Cui +2
Cartoon face recognition is challenging as they typically have smooth color regions and emphasized edges, the key to recognize cartoon faces is to precisely perceive their sparse a…
Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection
Zhenyu Zhang, Yanhao Ge, Renwang Chen +6
Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. While plausible facial details are predicted, the models tend to over-depend on…
DONet: Dual-Octave Network for Fast MR Image Reconstruction
Chun-Mei Feng, Zhanyuan Yang, Huazhu Fu +3
Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multi…
SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
Mingmei Cheng, Le Hui, Jin Xie +1
Point cloud semantic segmentation is a crucial task in 3D scene understanding. Existing methods mainly focus on employing a large number of annotated labels for supervised semantic…
Learning Normal Dynamics in Videos with Meta Prototype Network
Hui Lv, Chen Chen, Zhen Cui +3
Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstructio…
Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks
Haobo Jiang, Jin Xie, Jian Yang
Double Q-learning is a popular reinforcement learning algorithm in Markov decision process (MDP) problems. Clipped Double Q-learning, as an effective variant of Double Q-learning,…
Contrastive Embedding for Generalized Zero-Shot Learning
Zongyan Han, Zhenyong Fu, Shuo Chen +1
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Recent feature gen…
Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition
Guangwei Gao, Yi Yu, Jian Yang +2
Cross-resolution face recognition (CRFR), which is important in intelligent surveillance and biometric forensics, refers to the problem of matching a low-resolution (LR) probe face…
Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction
Xuran Xu, Tong Zhang, Chunyan Xu +2
Accurate traffic prediction is crucial to the guidance and management of urban traffics. However, most of the existing traffic prediction models do not consider the computational b…
MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
Guangwei Gao, Guoan Xu, Yi Yu +3
In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital…
Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
Le Hui, Mingmei Cheng, Jin Xie +1
Point cloud based retrieval for place recognition is still a challenging problem due to drastic appearance and illumination changes of scenes in changing environments. Existing dee…
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Qizhou Wang, Bo Han, Tongliang Liu +3
The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Dee…
Globally Optimal Relative Pose Estimation with Gravity Prior
Yaqing Ding, Daniel Barath, Jian Yang +2
Smartphones, tablets and camera systems used, e.g., in cars and UAVs, are typically equipped with IMUs (inertial measurement units) that can measure the gravity vector accurately.…
They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning
Zhuo Huang, Ying Tai, Chengjie Wang +2
Semi-Supervised Learning (SSL) with mismatched classes deals with the problem that the classes-of-interests in the limited labeled data is only a subset of the classes in massive u…
Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising
Yali Peng, Yue Cao, Shigang Liu +2
Recent years have witnessed the great success of deep convolutional neural networks (CNNs) in image denoising. Albeit deeper network and larger model capacity generally benefit per…
Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification
Sheng Wan, Chen Gong, Shirui Pan +2
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the curre…