Search

Your search keyword '"Junyu Gao"' showing total 141 results
Start Over Author "Junyu Gao"
141 results on '"Junyu Gao"'

1. Tailoring the amorphous Mo sites on layered double hydroxide nanosheets for nitrogen photofixation

Author

Jinhu Wang, Junyu Gao, Yingxuan Miao, Dong Li, Yunxuan Zhao, and Tierui Zhang

Subjects
Catalysis, Energy materials, Science
Abstract

Summary: While photocatalytic technology has brought additional opportunities and possibilities for the green conversion and sustainable development of ammonium-based nitrogen fertilizers, the low activation efficiency of the molecular N2 has impeded its further application feasibility. Here to address the concern, we designed an amorphous molybdenum hydroxide anchored on the ultrathin magnesium-aluminum layered double hydroxide (Mo@MgAl-LDH) nanosheets for benefiting the N2 photofixation to NH3. With the aid of the designed amorphous Mo(V) species, the pristine MgAl-LDH exhibited a considerable performance of nitrogen photofixation under visible light irradiation (NH3 production rate of 114.4 μmol g−1 h−1) due to the improved N2 activation efficiency. The work demonstrated a feasible strategy for nitrogen photofixation using amorphous Mo(V) species, which may also deliver a novel inspiration for the development of amorphous photocatalysts toward the photoactivation of molecular N2.

Published
2024
Full Text
View/download PDF

2. From the perspective of experimental practice: High-throughput computational screening in photocatalysis

Author

Yunxuan Zhao, Junyu Gao, Xuanang Bian, Han Tang, and Tierui Zhang

Subjects
Photocatalysis, High-throughput computational screening, Photocatalyst, Theoretical simulations, Experiments, Renewable energy sources, TJ807-830, Ecology, QH540-549.5
Abstract

Photocatalysis, a critical strategy for harvesting sunlight to address energy demand and environmental concerns, is underpinned by the discovery of high-performance photocatalysts, thereby how to design photocatalysts is now generating widespread interest in boosting the conversion efficiency of solar energy. In the past decade, computational technologies and theoretical simulations have led to a major leap in the development of high-throughput computational screening strategies for novel high-efficiency photocatalysts. In this viewpoint, we started with introducing the challenges of photocatalysis from the view of experimental practice, especially the inefficiency of the traditional “trial and error” method. Subsequently, a cross-sectional comparison between experimental and high-throughput computational screening for photocatalysis is presented and discussed in detail. On the basis of the current experimental progress in photocatalysis, we also exemplified the various challenges associated with high-throughput computational screening strategies. Finally, we offered a preferred high-throughput computational screening procedure for photocatalysts from an experimental practice perspective (model construction and screening, standardized experiments, assessment and revision), with the aim of a better correlation of high-throughput simulations and experimental practices, motivating to search for better descriptors.

Published
2024
Full Text
View/download PDF

3. Hyperspectral Image Classification With CapsNet and Markov Random Fields

Author

Xuefeng Jiang, Yue Zhang, Wenbo Liu, Junyu Gao, Junrui Liu, Yanning Zhang, and Jianzhe Lin

Subjects
Capsule network, deep learning, hyperspectral image classification, Markov random fields, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

Hyperspectral image (HSI) classification is one of the most challenging problems in understanding HSI. Convolutional neural network(CNN), with the strong ability to extract features using the hidden layers in the network, has been introduced to solve this problem. However, several fully connected layers are always appended at the end of CNN, which dramatically reduced the efficiency of space utilization and make the classification algorithm hard to converge. Recently, a new network architecture called capsule network (CapsNet) was presented to improve the CNN. It uses groups of neurons as capsules to replace the neurons in traditional neural networks. Since the capsule can provide superior spectral features and spatial information extracted, its performance is better than the most advanced CNN in some fields. Motivated by this idea, a new remote sensing hyperspectral image classification algorithm called Conv-Caps is proposed to make full use of the advantages of both. We integrate spectral and spatial information into the proposed framework and combine Conv-Caps with Markov Random Field (MRF), which uses the graph cut expansion method to solve the classification task. The Caps-MRF method is further proposed. First, select an initial feature extractor, which a CNN without fully connected layers. Then, the initial recognition feature map is put into the newly designed CapsNet to obtain the probability map. Finally, the MRF model is used to calculate the subdivision labels. The presented method is trained with three real HSI datasets and is compared with the latest methods. We find the framework can produce competitive classification performance.

Published
2020
Full Text
View/download PDF

4. Convolutional Regression Network for Multi-Oriented Text Detection

Author

Junyu Gao, Qi Wang, and Yuan Yuan

Subjects
Text detection, object segmentation, fully convolutional network, Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

Multi-oriented text detection in the wild is a challenging task due to the variations of scales, orientations, illumination, and languages. The traditional anchor mechanism on generic object detection can only generate horizontal proposals, which cannot be applied to detecting multi-oriented text regions. Considering this, in this paper, we propose a novel convolutional regression network (CRN) to localize multi-oriented text in natural images, which consists of two components: region proposal extractor and text locator. To be specific, we first present a hierarchical deconvolution module (HDM), a text-line and geometry segmentation module (TGM) to segment the multi-oriented proposals accurately, both of which are fully convolutional networks. Then, a classification and regression module (CRM) is adopted to process the proposals and obtain the final localization results. The whole framework can be trained in an end-to-end mechanism which is suitable for detecting multi-oriented texts. The extensive experiments are conducted on three mainstream scene-text datasets, and the experimental results evidence the proposed CRN achieves competitive performance.

Published
2019
Full Text
View/download PDF

5. Global Multi-Scale Information Fusion for Multi-Class Object Counting in Remote Sensing Images

Author

Junyu Gao, Maoguo Gong, and Xuelong Li

Subjects
couting, remote counting, transformer, remote sensing image, Science
Abstract

In recent years, object counting has been investigated and has made significant progress under a surveillance-view. However, there exists only a few works focusing on the remote sensing object density estimation, and the performance of existing methods is not promising. On the one hand, due to the imbalance distribution of targets in remote sensing images, the model might collapse, leading a severe degradation. On the other hand, the scale of targets in remote sensing images actually varies in real scenarios, which remains a challenge for counting objects accurately. To remedy the above problems, we propose an approach named “SwinCounter” for object counting in remote sensing. Moreover, we introduce a Balanced MSE Loss to pay more attention to the fewer samples, which alleviates the problem of imbalanced object labels. In addition, the attention mechanism in our SwinCounter can precisely capture multi-scale information. Thus, the model is aware of different scales of objects, which capture small and dense targetes more precisely. We build experiments on the RSOC dataset, achieving MAEs of 7.2, 151.5, 14.38, and 52.88 and MSEs of 10.1, 436.0, 22.7, and 74.82 on the Building, Small-Vehicle, Large-Vehicle, and Ship sub-datasets, which demonstrates the competitiveness and superiority of the proposed method.

Published
2022
Full Text
View/download PDF

26. VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results.

Author

Dawei Du, Longyin Wen, Pengfei Zhu 0001, Heng Fan 0001, Qinghua Hu, Haibin Ling, Mubarak Shah, Junwen Pan, Ali Al-Ali, Amr Mohamed 0001, Bakour Imene, Bin Dong 0006, Binyu Zhang, Bouchali Hadia Nesma, Chenfeng Xu, Chenzhen Duan, Ciro Castiello, Corrado Mencar, Dingkang Liang, Florian Krüger, Gennaro Vessio, Giovanna Castellano, Jieru Wang, Junyu Gao 0001, Khalid Abualsaud, Laihui Ding, Lei Zhao, Marco Cianciotta, Muhammad Saqib, Noor Almaadeed, Omar Elharrouss, Pei Lyu, Qi Wang 0009, Shidong Liu, Shuang Qiu, Siyang Pan, Somaya Al-Máadeed, Sultan Daud Khan, Tamer Khattab, Tao Han 0002, Thomas Golda, Wei Xu 0017, Xiang Bai, Xiaoqing Xu, Xuelong Li 0001, Yanyun Zhao, Ye Tian 0026, Yingnan Lin, Yongchao Xu, Yuehan Yao, Zhenyu Xu, Zhijian Zhao, Zhipeng Luo, Zhiwei Wei, and Zhiyuan Zhao

Published
2020
Full Text
View/download PDF

36. The Sixth Visual Object Tracking VOT2018 Challenge Results.

Author

Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Luka Cehovin Zajc, Tomás Vojír, Goutam Bhat, Alan Lukezic, Abdelrahman Eldesokey, Gustavo Fernández, álvaro García-Martín, álvaro Iglesias-Arias, A. Aydin Alatan, Abel González-García, Alfredo Petrosino, Alireza Memarmoghadam, Andrea Vedaldi, Andrej Muhic, Anfeng He, Arnold W. M. Smeulders, Asanka G. Perera, Bo Li 0114, Boyu Chen, Changick Kim, Changsheng Xu, Changzhen Xiong, Cheng Tian, Chong Luo, Chong Sun, Cong Hao, Daijin Kim 0001, Deepak Mishra 0002, Deming Chen, Dong Wang 0004, Dongyoon Wee, Efstratios Gavves, Erhan Gundogdu, Erik Velasco-Salido, Fahad Shahbaz Khan, Fan Yang 0035, Fei Zhao, Feng Li 0031, Francesco Battistone, George De Ath, Gorthi R. K. Sai Subrahmanyam, Guilherme Sousa Bastos, Haibin Ling, Hamed Kiani Galoogahi, Hankyeol Lee, Haojie Li, Haojie Zhao, Heng Fan 0001, Honggang Zhang 0002, Horst Possegger, Houqiang Li, Huchuan Lu, Hui Zhi, Huiyun Li, Hyemin Lee, Hyung Jin Chang, Isabela Drummond, Jack Valmadre, Jaime Spencer Martin, Javaan Singh Chahl, Jin Young Choi 0002, Jing Li 0036, Jinqiao Wang, Jinqing Qi, Jinyoung Sung, Joakim Johnander, João F. Henriques, Jongwon Choi, Joost van de Weijer 0001, Jorge Rodríguez Herranz, José M. Martínez 0001, Josef Kittler, Junfei Zhuang, Junyu Gao 0002, Klemen Grm, Lichao Zhang, Lijun Wang, Lingxiao Yang, Litu Rout, Liu Si, Luca Bertinetto, Lutao Chu, Manqiang Che, Mario Edoardo Maresca, Martin Danelljan, Ming-Hsuan Yang 0001, Mohamed H. Abdelpakey, Mohamed S. Shehata, Myunggu Kang, Namhoon Lee, Ning Wang 0020, Ondrej Miksik, Payman Moallem, Pablo Vicente-Moñivar, Pedro Senna, Peixia Li, Philip H. S. Torr, Priya Mariam Raju, Ruihe Qian, Qiang Wang 0051, Qin Zhou, Qing Guo 0005, Rafael Martin Nieto, Rama Krishna Sai Subrahmanyam Gorthi, Ran Tao 0004, Richard Bowden, Richard M. Everson, Runling Wang, Sangdoo Yun, Seokeon Choi, Sergio Vivas, Shuai Bai, Shuangping Huang, Sihang Wu, Simon Hadfield, Siwen Wang, Stuart Golodetz, Ming Tang 0001, Tianyang Xu, Tianzhu Zhang, Tobias Fischer 0001, Vincenzo Santopietro, Vitomir Struc, Wei Wang 0335, Wangmeng Zuo, Wei Feng 0005, Wei Wu 0021, Wei Zou, Weiming Hu, Wengang Zhou, Wenjun Zeng, Xiaofan Zhang 0002, Xiaohe Wu, Xiao-Jun Wu 0001, Xinmei Tian 0001, Yan Li 0014, Yan Lu 0001, Yee Wei Law, Yi Wu 0001, Yiannis Demiris, Yicai Yang, Yifan Jiao, Yuhong Li, Yunhua Zhang, Yuxuan Sun, Zheng Zhang 0022, Zheng Zhu, Zhen-Hua Feng, Zhihui Wang 0001, and Zhiqun He

Published
2018
Full Text
View/download PDF

37. Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features.

Author

WEN GUO, WUZHOU QUAN, JUNYU GAO, TIANZHU ZHANG, and CHANGSHENG XU

Abstract

To reduce computational redundancies, a common approach is to integrate detection and re-identification (Re-ID) into a single network in multi-object tracking (MOT), referred to as "tracking by detection." Most of the previous research has focused on resolving the conflict between the detection and Re-ID branches, considering it a simple coupling. In our work, we uncover that the entangled state between the detection and Re-ID tasks is much more complex than previous idea, resulting in a form of competition that degrades performance. To address the preceding issue, we propose a feature disentanglement network that deeply disentangles the intricately interwoven latent space of features and provides differentiated feature maps for each individual task. Furthermore, considering the demand for shallow semantic features in the feature re-ID branch, we also introduce a feature re-globalization module to enrich the shallow semantics. By integrating two distinct networks into a one-shot online MOT method, we develop a robust MOT tracker (named HDGTrack). We conduct extensive experiments on a number of benchmarks, and our experimental results demonstrate that our method significantly outperforms state-of-the-art MOT methods. Besides, HDGTrack is efficient and can run at 13.9 (MOT17) and 8.7 (MOT20) frames per second. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

38. The Visual Object Tracking VOT2017 Challenge Results.

Author

Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Luka Cehovin Zajc, Tomas Vojir, Gustav Häger, Alan Lukezic, Abdelrahman Eldesokey, Gustavo Fernández, álvaro García-Martín, Andrej Muhic, Alfredo Petrosino, Alireza Memarmoghadam, Andrea Vedaldi, Antoine Manzanera, Antoine Tran, A. Aydin Alatan, Bogdan Mocanu, Boyu Chen, Chang Huang, Changsheng Xu, Chong Sun, Dalong Du, David Zhang 0001, Dawei Du, Deepak Mishra 0002, Erhan Gundogdu, Erik Velasco-Salido, Fahad Shahbaz Khan, Francesco Battistone, Gorthi R. K. Sai Subrahmanyam, Goutam Bhat, Guan Huang, Guilherme Sousa Bastos, Guna Seetharaman, Hongliang Zhang, Houqiang Li, Huchuan Lu, Isabela Drummond, Jack Valmadre, Jae-chan Jeong, Jaeil Cho, Jae-Yeong Lee, Jana Noskova, Jianke Zhu, Jin Gao, Jingyu Liu 0004, Ji-Wan Kim, João F. Henriques, José M. Martínez 0001, Junfei Zhuang, Junliang Xing, Junyu Gao 0002, Kai Chen 0023, Kannappan Palaniappan, Karel Lebeda, Ke Gao, Kris M. Kitani, Lei Zhang 0006, Lijun Wang, Lingxiao Yang, Longyin Wen, Luca Bertinetto, Mahdieh Poostchi, Martin Danelljan, Matthias Mueller 0001, Mengdan Zhang, Ming-Hsuan Yang 0001, Nianhao Xie, Ning Wang 0020, Ondrej Miksik, Payman Moallem, Pallavi M. Venugopal, Pedro Senna, Philip H. S. Torr, Qiang Wang 0051, Qifeng Yu, Qingming Huang, Rafael Martin Nieto, Richard Bowden, Risheng Liu, Ruxandra Tapu, Simon Hadfield, Siwei Lyu, Stuart Golodetz, Sunglok Choi, Tianzhu Zhang, Titus B. Zaharia, Vincenzo Santopietro, Wei Zou, Weiming Hu, Wenbing Tao, Wenbo Li 0001, Wengang Zhou, Xianguo Yu, Xiao Bian, Yang Li 0041, Yifan Xing, Yingruo Fan, Zheng Zhu, Zhipeng Zhang, and Zhiqun He

Published
2017
Full Text
View/download PDF

43. The Visual Object Tracking VOT2016 Challenge Results.

Author

Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Luka Cehovin, Tomás Vojír, Gustav Häger, Alan Lukezic, Gustavo Fernández, Abhinav Gupta 0001, Alfredo Petrosino, Alireza Memarmoghadam, álvaro García-Martín, Andrés Solís Montero, Andrea Vedaldi, Andreas Robinson, Andy Jinhua Ma, Anton Varfolomieiev, A. Aydin Alatan, Aykut Erdem, Bernard Ghanem, Bin Liu 0014, Bohyung Han, Brais Martínez, Chang-Ming Chang, Changsheng Xu, Chong Sun, Daijin Kim 0001, Dapeng Chen, Dawei Du, Deepak Mishra 0002, Dit-Yan Yeung, Erhan Gundogdu, Erkut Erdem, Fahad Shahbaz Khan, Fatih Porikli, Fei Zhao, Filiz Bunyak, Francesco Battistone, Gao Zhu, Giorgio Roffo, Gorthi R. K. Sai Subrahmanyam, Guilherme Sousa Bastos, Guna Seetharaman, Henry Medeiros 0001, Hongdong Li, Honggang Qi, Horst Bischof, Horst Possegger, Huchuan Lu, Hyemin Lee, Hyeonseob Nam, Hyung Jin Chang, Isabela Drummond, Jack Valmadre, Jae-chan Jeong, Jaeil Cho, Jae-Yeong Lee, Jianke Zhu, Jiayi Feng, Jin Gao, Jin Young Choi 0002, Jingjing Xiao, Ji-Wan Kim, Jiyeoup Jeong, João F. Henriques, Jochen Lang 0001, Jongwon Choi, José M. Martínez 0001, Junliang Xing, Junyu Gao 0002, Kannappan Palaniappan, Karel Lebeda, Ke Gao, Krystian Mikolajczyk, Lei Qin, Lijun Wang, Longyin Wen, Luca Bertinetto, Madan Kumar Rapuru, Mahdieh Poostchi, Mario Edoardo Maresca, Martin Danelljan, Matthias Mueller 0001, Mengdan Zhang, Michael Arens, Michel F. Valstar, Ming Tang 0001, Mooyeol Baek, Muhammad Haris Khan, Naiyan Wang, Nana Fan, Noor Al-Shakarji, Ondrej Miksik, Osman Akin, Payman Moallem, Pedro Senna, Philip H. S. Torr, Pong C. Yuen, Qingming Huang, Rafael Martin Nieto, Rengarajan Pelapur, Richard Bowden, Robert Laganière, Rustam Stolkin, Ryan Walsh, Sebastian Bernd Krah, Shengkun Li, Shengping Zhang, Shizeng Yao, Simon Hadfield, Simone Melzi, Siwei Lyu, Siyi Li, Stefan Becker, Stuart Golodetz, Sumithra Kakanuru, Sunglok Choi, Tao Hu, Thomas Mauthner, Tianzhu Zhang, Tony P. Pridmore, Vincenzo Santopietro, Weiming Hu, Wenbo Li 0001, Wolfgang Hübner 0001, Xiangyuan Lan, Xiaomeng Wang, Xin Li 0034, Yang Li 0041, Yiannis Demiris, Yifan Wang 0004, Yuankai Qi, Zejian Yuan, Zexiong Cai, Zhan Xu, Zhenyu He 0001, and Zhizhen Chi

Published
2016
Full Text
View/download PDF

46. Multitask Attention Network for Lane Detection and Fitting

Author

Junyu Gao, Qi Wang, Zequn Qin, Xuelong Li, and Tao Han

Subjects
Computer Networks and Communications, Computer science, business.industry, Pattern recognition, 02 engineering and technology, Computer Science Applications, Artificial Intelligence, Position (vector), Attention network, Line (geometry), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Point (geometry), Lane detection, Artificial intelligence, business, Software
Abstract

Many CNN-based segmentation methods have been applied in lane marking detection recently and gain excellent success for a strong ability in modeling semantic information. Although the accuracy of lane line prediction is getting better and better, lane markings' localization ability is relatively weak, especially when the lane marking point is remote. Traditional lane detection methods usually utilize highly specialized handcrafted features and carefully designed postprocessing to detect the lanes. However, these methods are based on strong assumptions and, thus, are prone to scalability. In this work, we propose a novel multitask method that: 1) integrates the ability to model semantic information of CNN and the strong localization ability provided by handcrafted features and 2) predicts the position of vanishing line. A novel lane fitting method based on vanishing line prediction is also proposed for sharp curves and nonflat road in this article. By integrating segmentation, specialized handcrafted features, and fitting, the accuracy of location and the convergence speed of networks are improved. Extensive experimental results on four-lane marking detection data sets show that our method achieves state-of-the-art performance.

Published
2022

47. Learning Video Moment Retrieval Without a Single Annotated Video

Author

Changsheng Xu and Junyu Gao

Subjects
Matching (graph theory), Natural language user interface, Computer science, business.industry, computer.software_genre, Task (project management), Moment (mathematics), Media Technology, Embedding, Artificial intelligence, Electrical and Electronic Engineering, Representation (mathematics), business, computer, Sentence, Natural language processing, Generator (mathematics)
Abstract

Video moment retrieval has progressed significantly over the past few years, aiming to search the moment that is most relevant to a given natural language query. Most existing methods are trained in a fully-supervised or a weakly-supervised manner, which requires a time-consuming and expensive manually labeling process. In this work, we propose an alternative approach to achieving video moment retrieval that requires no textual annotations of videos and instead leverages the existing visual concept detectors and a pre-trained image-sentence embedding space. Specifically, we design a video-conditioned sentence generator to produce a suitable sentence representation by utilizing the mined visual concepts in videos. We then design a GNN-based relation-aware moment localizer to reasonably select a portion of video clips under the guidance of the generated sentence. Finally, the pre-trained image-sentence embedding space is adopted to evaluate the matching scores between the generated sentence and moment representations with the knowledge transferred from the image domain. By maximizing these scores, the sentence generator and moment localizer can enhance and complement each other to achieve the moment retrieval task. Experimental results on the Charades-STA and ActivityNet Captions datasets demonstrate the effectiveness of our proposed method.

Published
2022

50. Learning Hierarchical Video Graph Networks for One-Stop Video Delivery

Author

Yaguang Song, Junyu Gao, Xiaoshan Yang, and Changsheng Xu

Subjects
Computer Networks and Communications, Hardware and Architecture
Abstract

The explosive growth of video data has brought great challenges to video retrieval, which aims to find out related videos from a video collection. Most users are usually not interested in all the content of retrieved videos but have a more fine-grained need. In the meantime, most existing methods can only return a ranked list of retrieved videos lacking a proper way to present the video content. In this paper, we introduce a distinctively new task, namely One-Stop Video Delivery (OSVD) aiming to realize a comprehensive retrieval system with the following merits: it not only retrieves the relevant videos but also filters out irrelevant information and presents compact video content to users, given a natural language query and video collection. To solve this task, we propose an end-to-end Hierarchical Video Graph Reasoning framework (HVGR) , which considers relations of different video levels and jointly accomplishes the one-stop delivery task. Specifically, we decompose the video into three levels, namely the video-level, moment-level, and the clip-level in a coarse-to-fine manner, and apply Graph Neural Networks (GNNs) on the hierarchical graph to model the relations. Furthermore, a pairwise ranking loss named Progressively Refined Loss is proposed based on prior knowledge that there is a relative order of the similarity of query-video, query-moment, and query-clip due to the different granularity of matched information. Extensive experimental results on benchmark datasets demonstrate that the proposed method achieves superior performance compared with baseline methods.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results