1 code implementation • 7 Nov 2017 • Xiangyu Liu, Qingjie Liu, Yunhong Wang
Unlike previous CNN based methods that consider pan-sharpening as a super resolution problem and perform pan-sharpening in pixel level, the proposed TFNet aims to fuse PAN and MS images in feature level and reconstruct the pan-sharpened image from the fused features.
no code implementations • 21 Nov 2017 • Xingyue Chen, Yunhong Wang, Qingjie Liu
Sentiment analysis is attracting more and more attentions and has become a very hot research topic due to its potential applications in personalized recommendation, opinion mining, etc.
no code implementations • 26 Nov 2017 • Qiang Chen, Yunhong Wang, Zheng Liu, Qingjie Liu, Di Huang
In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images.
13 code implementations • 29 Nov 2017 • Zhengxin Zhang, Qingjie Liu, Yunhong Wang
Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis.
1 code implementation • 9 May 2018 • Qingjie Liu, Huanyu Zhou, Qizhi Xu, Xiangyu Liu, Yunhong Wang
This paper addresses the problem of remote sensing image pan-sharpening from the perspective of generative adversarial learning.
1 code implementation • 28 Mar 2019 • Jingchao Liu, Xuebo Liu, Jie Sheng, Ding Liang, Xin Li, Qingjie Liu
Scene text detection, an essential step of scene text recognition system, is to locate text instances in natural scene images automatically.
Ranked #1 on Scene Text Detection on ICDAR 2017 MLT
2 code implementations • 10 Dec 2019 • Jinjin Zhang, Wei Wang, Di Huang, Qingjie Liu, Yunhong Wang
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
no code implementations • 14 Feb 2020 • Guangshuai Gao, Qingjie Liu, Yunhong Wang
Significant efforts have been made to address this problem and achieve great progress, yet counting number of ground objects from remote sensing images is barely studied.
1 code implementation • 14 Mar 2020 • Bin Hou, Qingjie Liu, Heng Wang, Yunhong Wang
Traditional change detection methods usually follow the image differencing, change feature extraction and classification framework, and their performance is limited by such simple image domain differencing and also the hand-crafted features.
no code implementations • 16 Mar 2020 • Qingjie Liu, Yixuan Zuo, Xiaohui Yu, Meng Chen
In particular, we propose a novel method, called Travel Time Difference Model (TTDM), which exploits the difference between the shortest travel time and the actual travel time to predict next locations.
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.
no code implementations • 20 Aug 2020 • Guangshuai Gao, Wenting Zhao, Qingjie Liu, Yunhong Wang
Co-saliency detection aims to detect common salient objects from a group of relevant images.
1 code implementation • 28 Aug 2020 • Guangshuai Gao, Qingjie Liu, Yunhong Wang
Object counting, whose aim is to estimate the number of objects from a given image, is an important and challenging computation task.
no code implementations • 11 Sep 2020 • Jingchao Liu, Ye Du, Zehua Fu, Qingjie Liu, Yunhong Wang
Experiments on standard datasets shows our ARM can bring consistent improvements for both coarse annotations and fine annotations.
1 code implementation • 7 Dec 2020 • Guangshuai Gao, Qingjie Liu, Zhenghui Hu, Lu Li, Qi Wen, Yunhong Wang
Object counting, which aims to count the accurate number of object instances in images, has been attracting more and more attention.
1 code implementation • 16 Dec 2020 • Huanyu Zhou, Qingjie Liu, Yunhong Wang
However, since there are no intended HR MS images as references for learning, almost all of the existing methods down-sample the MS and PAN images and regard the original MS images as targets to form a supervised setting for training.
no code implementations • 20 Dec 2020 • Hao Zeng, Qingjie Liu, Mingming Zhang, Xiaoqing Han, Yunhong Wang
To further lift the classification performance, in this work we propose a graph convolution network (GCN) based framework for HSI classification that uses two clustering operations to better exploit multi-hop node correlations and also effectively reduce graph size.
no code implementations • 24 Dec 2020 • Ran Qin, Qingjie Liu, Guangshuai Gao, Di Huang, Yunhong Wang
Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected.
1 code implementation • CVPR 2021 • Zhihong Fu, Qingjie Liu, Zehua Fu, Yunhong Wang
Boosting performance of the offline trained siamese trackers is getting harder nowadays since the fixed information of the template cropped from the first frame has been almost thoroughly mined, but they are poorly capable of resisting target appearance changes.
Ranked #3 on Visual Object Tracking on OTB-2015
1 code implementation • 10 May 2021 • Ye Du, Zehua Fu, Qingjie Liu, Yunhong Wang
In this paper, we propose a transformer based approach for visual grounding.
1 code implementation • 20 Sep 2021 • Huanyu Zhou, Qingjie Liu, Dawei Weng, Yunhong Wang
Most of existing methods fall into the supervised learning framework in which they down-sample the multi-spectral (MS) and panchromatic (PAN) images and regard the original MS images as ground truths to form training samples.
1 code implementation • CVPR 2022 • Ye Du, Zehua Fu, Qingjie Liu, Yunhong Wang
Moreover, armed with our method, we increase the segmentation mIoU of EPS from 70. 8% to 73. 6%, achieving new state-of-the-art.
Ranked #14 on Weakly-Supervised Semantic Segmentation on PASCAL VOC 2012 test (using extra training data)
1 code implementation • 6 Mar 2022 • Huanyu Zhou, Qingjie Liu, Yunhong Wang
Pan-sharpening aims at producing a high-resolution (HR) multi-spectral (MS) image from a low-resolution (LR) multi-spectral (MS) image and its corresponding panchromatic (PAN) image acquired by a same satellite.
1 code implementation • 8 May 2022 • Zhihong Fu, Zehua Fu, Qingjie Liu, Wenrui Cai, Yunhong Wang
In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking.
1 code implementation • 15 Sep 2022 • Ye Du, Yujun Shen, Haochen Wang, Jingjing Fei, Wei Li, Liwei Wu, Rui Zhao, Zehua Fu, Qingjie Liu
Self-training has shown great potential in semi-supervised learning.
1 code implementation • 25 Sep 2022 • Rui He, Zehua Fu, Qingjie Liu, Yunhong Wang, Xunxun Chen
In this paper, the duplicate detection is newly and precisely defined as occlusion misreporting on the same athlete by multiple detection boxes in one frame.
1 code implementation • 5 Oct 2022 • Zhiyuan Zhao, Qingjie Liu, Yunhong Wang
For the high-shot regime, we propose to use the knowledge learned from ImageNet as guidance for the feature learning in the fine-tuning stage, which will implicitly align the distributions of the novel classes.
no code implementations • 8 Dec 2022 • Yajie Liu, Pu Ge, Qingjie Liu, Shichao Fan, Yunhong Wang
How to effectively leverage the plentiful existing datasets to train a robust and high-performance model is of great significance for many practical applications.
no code implementations • 1 Mar 2023 • Mingming Zhang, Ye Du, Zhenghui Hu, Qingjie Liu, Yunhong Wang
Extracting building footprints from remote sensing images has been attracting extensive attention recently.
1 code implementation • CVPR 2023 • Huanyu Zhou, Qingjie Liu, Yunhong Wang
Furthermore, FR Head could be imposed on different stages of GCNs to build a multi-level refinement for stronger supervision.
1 code implementation • ICCV 2023 • Jinqing Zhang, Yanan Zhang, Qingjie Liu, Yunhong Wang
In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features.
Ranked #9 on 3D Object Detection on nuScenes Camera Only
no code implementations • 18 Sep 2023 • Mingming Zhang, Qingjie Liu, Yunhong Wang
The polygon head formulates a building polygon as serialized vertices with the bidirectional characteristic, a simple and elegant polygon representation avoiding the start or end vertex hypothesis.
no code implementations • 28 Sep 2023 • Mingming Zhang, Qingjie Liu, Yunhong Wang
To address these problems, we propose a context-enhanced masked image modeling method (CtxMIM), a simple yet efficient MIM-based self-supervised learning for remote sensing image understanding.
no code implementations • 11 Oct 2023 • Ziyue Huang, Mingming Zhang, Qingjie Liu, Wei Wang, Zhe Dong, Yunhong Wang
Our approach utilizes a three-stage cascade structure to enhance the extraction of contextual information and improve building detection accuracy.
no code implementations • 13 Oct 2023 • Yupeng He, Ziyue Huang, Qingjie Liu, Yunhong Wang
In the incremental detection task, unlike the incremental classification task, data ambiguity exists due to the possibility of an image having different labeled bounding boxes in multiple continuous learning stages.
no code implementations • 29 Oct 2023 • Zehua Fu, Wenhang Zuo, Zhenghui Hu, Qingjie Liu, Yunhong Wang
Specifically, the keypoint confidence network is designed to determine whether each keypoint is occluded, and it is incorporated into the pose estimation module.
1 code implementation • 3 Nov 2023 • Wenrui Cai, Qingjie Liu, Yunhong Wang
In this paper, we show that by providing a tracker that follows Siamese paradigm with precise and updated historical information, a significant performance improvement can be achieved with completely unchanged parameters.
Ranked #2 on Visual Object Tracking on NeedForSpeed
no code implementations • 13 Nov 2023 • Wenshuai Xu, Zhenghui Hu, Yu Lu, Jinzhou Meng, Qingjie Liu, Yunhong Wang
Firstly, we select samples for annotation by optimizing the distribution similarity between the subset to be selected and the entire unlabeled pool in continuous space.
no code implementations • 17 Nov 2023 • Yongchao Feng, Shiwei Li, Yingjie Gao, Ziyue Huang, Yanan Zhang, Qingjie Liu, Yunhong Wang
Though feature-alignment based Domain Adaptive Object Detection (DAOD) have achieved remarkable progress, they ignore the source bias issue, i. e. the aligned features are more favorable towards the source domain, leading to a sub-optimal adaptation.
no code implementations • 1 Dec 2023 • Yajie Liu, Pu Ge, Haoxiang Ma, Shichao Fan, Qingjie Liu, Di Huang, Yunhong Wang
Referring image segmentation (RIS) aims to segment objects in an image conditioning on free-from text descriptions.
1 code implementation • 9 Jan 2024 • Ziyue Huang, Mingming Zhang, Yuan Gong, Qingjie Liu, Yunhong Wang
Deep learning models are essential for scene classification, change detection, land cover segmentation, and other remote sensing image understanding tasks.
no code implementations • 6 Mar 2024 • Yajie Liu, Pu Ge, Qingjie Liu, Di Huang
Recently, learning open-vocabulary semantic segmentation from text supervision has achieved promising downstream performance.
Contrastive Learning Open Vocabulary Semantic Segmentation +3
no code implementations • 9 Apr 2024 • ChenGuang Liu, Guangshuai Gao, Ziyue Huang, Zhenghui Hu, Qingjie Liu, Yunhong Wang
2) Small object size leads to insufficient information for effective detection.