24 citations · 90 across the 14 of their papers we have counts for
14 papers
SamLP: A Customized Segment Anything Model for License Plate Detection
Haoxuan Ding, Junyu Gao, Yuan Yuan +1
With the emergence of foundation model, this novel paradigm of deep learning has encouraged many powerful achievements in natural language processing and computer vision. There are…
Imbalanced Aircraft Data Anomaly Detection
Hao Yang, Junyu Gao, Yuan Yuan +1
Anomaly detection in temporal data from sensors under aviation scenarios is a practical but challenging task: 1) long temporal data is difficult to extract contextual information w…
Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects
Qi Wang, Juncheng Wang, Junyu Gao +2
The mainstream crowd counting methods regress density map and integrate it to obtain counting results. Since the density representation to one head accords to its adjacent distribu…
MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting
Pengyu Chen, Junyu Gao, Yuan Yuan +1
RGB-Thermal (RGB-T) crowd counting is a challenging task, which uses thermal images as complementary information to RGB images to deal with the decreased performance of unimodal RG…
Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher
Juncheng Wang, Junyu Gao, Yuan Yuan +1
Crowd localization is to predict each instance head position in crowd scenarios. Since the distance of instances being to the camera are variant, there exists tremendous gaps among…
AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild
Libo Zhang, Junyuan Gao, Zhen Xiao +1
Multi-animal tracking (MAT), a multi-object tracking (MOT) problem, is crucial for animal motion and behavior analysis and has many crucial applications such as biology, ecology an…
DR.VIC: Decomposition and Reasoning for Video Individual Counting
Tao Han, Lei Bai, Junyu Gao +2
Pedestrian counting is a fundamental tool for understanding pedestrian patterns and crowd flow analysis. Existing works (e.g., image-level pedestrian counting, crossline crowd coun…
Audio-visual Representation Learning for Anomaly Events Detection in Crowds
Junyu Gao, Maoguo Gong, Xuelong Li
In recent years, anomaly events detection in crowd scenes attracts many researchers' attention, because of its importance to public safety. Existing methods usually exploit visual…
Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
Qi Wang, Sikai Bai, Junyu Gao +2
Person re-identification (re-ID) has gained more and more attention due to its widespread applications in intelligent video surveillance. Unfortunately, the mainstream deep learnin…
LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
Qi wang, Tao Han, Junyu Gao +2
The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map. It also enlightens us back…
Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer
Junyu Gao, Maoguo Gong, Xuelong Li
Crowd localization is a new computer vision task, evolved from crowd counting. Different from the latter, it provides more precise location information for each instance, not just…
Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark
Haopeng Li, Lingbo Liu, Kunlin Yang +5
Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos. To model spatial-temporal dependencie…
Health Status Prediction with Local-Global Heterogeneous Behavior Graph
Xuan Ma, Xiaoshan Yang, Junyu Gao +1
Health management is getting increasing attention all over the world. However, existing health management mainly relies on hospital examination and treatment, which are complicated…
Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
Junyu Gao, Tao Han, Qi Wang +1
Recently, crowd counting using supervised learning achieves a remarkable improvement. Nevertheless, most counters rely on a large amount of manually labeled data. With the release…