541 citations · 1.2k across the 53 of their papers we have counts for
29 papers · 1 filter
Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition
Zhimin Gao, Peitao Wang, Pei Lv +5
Despite great progress achieved by transformer in various vision tasks, it is still underexplored for skeleton-based action recognition with only a few attempts. Besides, these met…
FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis
Zihui Guo, Yonghong Hou, Pichao Wang +3
Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first person vision (FPV) or third person vision (TPV). How…
FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring
Suiyi Zhao, Zhao Zhang, Richang Hong +3
Blind image deblurring (BID) remains a challenging and significant task. Benefiting from the strong fitting ability of deep learning, paired data-driven supervised BID method has o…
Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition
Jinfeng Wei, Yunxin Wang, Mengli Guo +3
Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task. However, the skeleton graph cannot fully represent t…
SSAGCN: Social Soft Attention Graph Convolution Network for Pedestrian Trajectory Prediction
Pei Lv, Wentong Wang, Yunxin Wang +3
Pedestrian trajectory prediction is an important technique of autonomous driving, which has become a research hot-spot in recent years. Previous methods mainly rely on the position…
A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition
Shuangyan Miao, Yonghong Hou, Zhimin Gao +2
This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate no…
Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
Pei Lv, Suqi Hu, Tianran Hao
Weakly supervised object detection (WSOD) has attracted more and more attention since it only uses image-level labels and can save huge annotation costs. Most of the WSOD methods u…
Zero-sample surface defect detection and classification based on semantic feedback neural network
Yibo Guo, Yiming Fan, Zhiyang Xiang +3
Defect detection and classification technology has changed from traditional artificial visual inspection to current intelligent automated inspection, but most of the current defect…
User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning
Pei Lv, Jianqi Fan, Xixi Nie +5
Personalized image aesthetic assessment (PIAA) has recently become a hot topic due to its usefulness in a wide variety of applications such as photography, film and television, e-c…
A self-adapting super-resolution structures framework for automatic design of GAN
Yibo Guo, Haidi Wang, Yiming Fan +2
With the development of deep learning, the single super-resolution image reconstruction network models are becoming more and more complex. Small changes in hyperparameters of the m…
Lottery Jackpots Exist in Pre-trained Models
Yuxin Zhang, Mingbao Lin, Yunshan Zhong +2
Network pruning is an effective approach to reduce network complexity with acceptable performance compromise. Existing studies achieve the sparsity of neural networks via time-cons…
Revisiting Local Descriptor for Improved Few-Shot Classification
Jun He, Richang Hong, Xueliang Liu +2
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts…
Trear: Transformer-based RGB-D Egocentric Action Recognition
Xiangyu Li, Yonghong Hou, Pichao Wang +3
In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear. It consists of two modules, inter-fra…
Probability Trajectory: One New Movement Description for Trajectory Prediction
Pei Lv, Hui Wei, Tianxin Gu +4
Trajectory prediction is a fundamental and challenging task for numerous applications, such as autonomous driving and intelligent robots. Currently, most of existing work treat the…
Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry
Xiangyu Li, Yonghong Hou, Pichao Wang +3
Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images…
An End-to-end Method for Producing Scanning-robust Stylized QR Codes
Hao Su, Jianwei Niu, Xuefeng Liu +4
Quick Response (QR) code is one of the most worldwide used two-dimensional codes.~Traditional QR codes appear as random collections of black-and-white modules that lack visual sema…
Memory-Augmented Relation Network for Few-Shot Learning
Jun He, Richang Hong, Xueliang Liu +3
Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision…
BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation
Yifeng Chen, Guangchen Lin, Songyuan Li +6
Panoptic segmentation aims to perform instance segmentation for foreground instances and semantic segmentation for background stuff simultaneously. The typical top-down pipeline co…
Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization
Pei Lv, Haiyu Yu, Junxiao Xue +5
Localizing objects with weak supervision in an image is a key problem of the research in computer vision community. Many existing Weakly-Supervised Object Localization (WSOL) appro…
Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
Yingyue Xu, Dan Xu, Xiaopeng Hong +4
Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many appro…
Adaptive Exploration for Unsupervised Person Re-Identification
Yuhang Ding, Hehe Fan, Mingliang Xu +1
Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this pa…
Abnormal Event Detection and Location for Dense Crowds using Repulsive Forces and Sparse Reconstruction
Pei Lv, Shunhua Liu, Mingliang Xu +1
This paper proposes a method based on repulsive forces and sparse reconstruction for the detection and location of abnormal events in crowded scenes. In order to avoid the challeng…
USAR: an Interactive User-specific Aesthetic Ranking Framework for Images
Pei Lv, Meng Wang, Yongbo Xu +5
When assessing whether an image is of high or low quality, it is indispensable to take personal preference into account. Existing aesthetic models lay emphasis on hand-crafted feat…
Bi-directional Graph Structure Information Model for Multi-Person Pose Estimation
Jing Wang, Ze Peng, Pei Lv +3
In this paper, we propose a novel multi-stage network architecture with two branches in each stage to estimate multi-person poses in images. The first branch predicts the confidenc…