9 citations · 31 across the 12 of their papers we have counts for
13 papers
CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
Lin Sun, Jiale Cao, Jin Xie +2
Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level…
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
Xiaoheng Jiang, Feng Yan, Yang Lu +6
Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods…
Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects
Feng Yan, Xiaoheng Jiang, Yang Lu +5
Surface defect inspection is a very challenging task in which surface defects usually show weak appearances or exist under complex backgrounds. Most high-accuracy defect detection…
CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation
Xiaoheng Jiang, Kaiyi Guo, Yang Lu +5
Surface defect inspection is of great importance for industrial manufacture and production. Though defect inspection methods based on deep learning have made significant progress,…
Decision Fusion Network with Perception Fine-tuning for Defect Classification
Xiaoheng Jiang, Shilong Tian, Zhiwen Zhu +5
Surface defect inspection is an important task in industrial inspection. Deep learning-based methods have demonstrated promising performance in this domain. Nevertheless, these met…
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…
Multi-scale Feature Aggregation for Crowd Counting
Xiaoheng Jiang, Xinyi Wu, Hisham Cholakkal +5
Convolutional Neural Network (CNN) based crowd counting methods have achieved promising results in the past few years. However, the scale variation problem is still a huge challeng…
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…
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…
Depth Information Guided Crowd Counting for Complex Crowd Scenes
Mingliang Xu, Zhaoyang Ge, Xiaoheng Jiang +4
It is important to monitor and analyze crowd events for the sake of city safety. In an EDOF (extended depth of field) image with a crowded scene, the distribution of people is high…
Efficiently Disassemble-and-Pack for Mechanism
Mingyuan Li, Xiaoheng Jiang, Ningbo Gu +4
In this paper, we present a disassemble-and-pack approach for a mechanism to seek a box which contains total mechanical parts with high space utilization. Its key feature is that m…
Convolution in Convolution for Network in Network
Yanwei Pang, Manli Sun, Xiaoheng Jiang +1
Network in Netwrok (NiN) is an effective instance and an important extension of Convolutional Neural Network (CNN) consisting of alternating convolutional layers and pooling layers…
Cascaded Subpatch Networks for Effective CNNs
Xiaoheng Jiang, Yanwei Pang, Manli Sun +1
Conventional Convolutional Neural Networks (CNNs) use either a linear or non-linear filter to extract features from an image patch (region) of spatial size (Typically…