no code implementations • 29 Sep 2020 • Zhiyuan Zhao, Tao Han, Junyu. Gao, Qi. Wang, Xuelong. Li
Drones shooting can be applied in dynamic traffic monitoring, object detecting and tracking, and other vision tasks.
no code implementations • 30 Jul 2020 • Qi. Wang, Junyu. Gao, Wei. Lin, Yuan Yuan
To be specific, 1) supervised crowd understanding: pre-train a crowd analysis model on the synthetic data, then fine-tune it using the real data and labels, which makes the model perform better on the real world; 2) crowd understanding via domain adaptation: translate the synthetic data to photo-realistic images, then train the model on translated data and labels.
1 code implementation • 14 May 2020 • Di Hu, Lichao Mou, Qingzhong Wang, Junyu. Gao, Yuansheng Hua, Dejing Dou, Xiao Xiang Zhu
Visual crowd counting has been recently studied as a way to enable people counting in crowd scenes from images.
1 code implementation • 5 Apr 2020 • Qi. Wang, Tao Han, Junyu. Gao, Yuan Yuan
Specifically, for a specific neuron of a source model, NLT exploits few labeled target data to learn domain shift parameters.
3 code implementations • 28 Mar 2020 • Guangshuai Gao, Junyu. Gao, Qingjie Liu, Qi. Wang, Yunhong Wang
Through our analysis, we expect to make reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other fields.
1 code implementation • 6 Mar 2020 • Wei. Lin, Junyu. Gao, Qi. Wang, Xuelong. Li
Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields.
no code implementations • 20 Feb 2020 • Tao Han, Junyu. Gao, Yuan Yuan, Qi. Wang
According to the semantic consistency, a similar distribution in deep layer's features of the synthetic and real-world crowd area, we first introduce a semantic extractor to effectively distinguish crowd and background in high-level semantic information.
4 code implementations • 10 Jan 2020 • Qi. Wang, Junyu. Gao, Wei. Lin, Xuelong. Li
In the last decade, crowd counting and localization attract much attention of researchers due to its wide-spread applications, including crowd monitoring, public safety, space design, etc.
no code implementations • 8 Dec 2019 • Junyu. Gao, Tao Han, Qi. Wang, Yuan Yuan
Recently, crowd counting using supervised learning achieves a remarkable improvement.
no code implementations • 8 Dec 2019 • Junyu. Gao, Yuan Yuan, Qi Wang
To reduce the gap, in this paper, we propose a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes.
no code implementations • 10 Aug 2019 • Junyu. Gao, Qi. Wang, Yuan Yuan
The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes.
3 code implementations • 5 Jul 2019 • Junyu. Gao, Wei. Lin, Bin Zhao, Dong Wang, Chenyu Gao, Jun Wen
This technical report attempts to provide efficient and solid kits addressed on the field of crowd counting, which is denoted as Crowd Counting Code Framework (C$^3$F).
1 code implementation • CVPR 2019 • Junyu. Gao, Tianzhu Zhang, Changsheng Xu
To comprehensively leverage the spatial-temporal structure of historical target exemplars and get benefit from the context information, in this work, we present a novel Graph Convolutional Tracking (GCT) method for high-performance visual tracking.
1 code implementation • 24 May 2019 • Junyu. Gao, Qi. Wang, Xuelong. Li
Crowd counting from a single image is a challenging task due to high appearance similarity, perspective changes and severe congestion.
no code implementations • 5 May 2019 • Qi. Wang, Junyu. Gao, Yuan Yuan
Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving.
no code implementations • 5 May 2019 • Qi. Wang, Junyu. Gao, Yuan Yuan
Our contributions are threefold: (1) A priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; (2) A hierarchical data augmentation method is presented to alleviate dataset bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; (3) A soft restricted MRF energy function is defined to improve the priori s-CNNs model's labeling performance and reduce the over smoothness at the same time.
no code implementations • 19 Apr 2019 • Qi. Wang, Junyu. Gao, Xuelong. Li
In this paper, we propose a weakly supervised adversarial domain adaptation to improve the segmentation performance from synthetic data to real scenes, which consists of three deep neural networks.
no code implementations • CVPR 2019 • Qi. Wang, Junyu. Gao, Wei. Lin, Yuan Yuan
Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations.