Yiming Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiming Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jinqing Zheng
College of Intelligence and Computing, Tianjin University, Tianjin, China
3 shared publications - Meng Xing
School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China
3 shared publications - Zhiyong Feng
Tianjin University, Tianjin, China
3 shared publications - Jie Sun
Nankai University
2 shared publications - Shaojie Zhang
Key Laboratory of Colloid and Interface Chemistry Ministry of Education School of Chemistry and Chemical Engineering Shandong University Jinan 250100 P. R. China
2 shared publications - Yong Su
Tianjin Normal University
2 shared publications
Latest Publications
- Top Cited Papers
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-17
DFGOVD: A New Dataset and Benchmark for Drone Fine-Grained Oriented Vehicle Detection in the Wild
Oriented Vehicle Detection (OVD) in drone imagery plays a fundamental role in a wide range of downstream applications, owing to its capacity to provide accurate localization and corresponding categorization of vehicle instances in complex scenes. Existing OVD methods for drone-based scenes are limited by their coarse granularity, while real-world applications often require fine-grained detection—for example, distinguishing between van trucks and tank trucks is critical for traffic regulation and road safety. To address this gap, we introduce Fine-Grained Oriented Vehicle Detection (FGOVD) task for the first time in drone-based scenarios. To facilitate this task, we develop a Semi-Automatic Labeling approach for Fine-Grained Oriented Object Detection, named SAL-FGOOD, and construct a truly fine-grained multi-scene dataset, Drone Fine-Grained Oriented Vehicle Detection (DFGOVD) dataset. SALFGOOD extends the existing labeling paradigm by incorporating a category-adjustment branch, reducing manual workload by 94.7% for our DFGOVD dataset and 77.7% for the public FAIR1M-v2 dataset. Building upon SAL-FGOOD, we construct DFGOVD, the first large-scale and comprehensive FGOVD dataset for drone-based scenes. The dataset comprises 33,669 images and 816,239 vehicle instances spanning 53 categories and captures subtle distinctions in vehicle appearance, size, and functionality. We benchmark state-of-the-art oriented object detection methods on the DFGOVD dataset, exposing its inherent complexity and challenge. The dataset is available upon request from https://github.com/JinqingZhengTju/DFGOVD.
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-17
Top Cited PapersDFGOVD: A New Dataset and Benchmark for Drone Fine-Grained Oriented Vehicle Detection in the Wild
Oriented Vehicle Detection (OVD) in drone imagery plays a fundamental role in a wide range of downstream applications, owing to its capacity to provide accurate localization and corresponding categorization of vehicle instances in complex scenes. Existing OVD methods for drone-based scenes are limited by their coarse granularity, while real-world applications often require fine-grained detection—for example, distinguishing between van trucks and tank trucks is critical for traffic regulation and road safety. To address this gap, we introduce Fine-Grained Oriented Vehicle Detection (FGOVD) task for the first time in drone-based scenarios. To facilitate this task, we develop a Semi-Automatic Labeling approach for Fine-Grained Oriented Object Detection, named SAL-FGOOD, and construct a truly fine-grained multi-scene dataset, Drone Fine-Grained Oriented Vehicle Detection (DFGOVD) dataset. SALFGOOD extends the existing labeling paradigm by incorporating a category-adjustment branch, reducing manual workload by 94.7% for our DFGOVD dataset and 77.7% for the public FAIR1M-v2 dataset. Building upon SAL-FGOOD, we construct DFGOVD, the first large-scale and comprehensive FGOVD dataset for drone-based scenes. The dataset comprises 33,669 images and 816,239 vehicle instances spanning 53 categories and captures subtle distinctions in vehicle appearance, size, and functionality. We benchmark state-of-the-art oriented object detection methods on the DFGOVD dataset, exposing its inherent complexity and challenge. The dataset is available upon request from https://github.com/JinqingZhengTju/DFGOVD.
- 28 January 2024
- Published by Springer Nature
- p. 242-256
Exploring Imperceptible Adversarial Examples in $YC_bC_r$ Color Space- 28 January 2024
- Published by Springer Nature
- p. 242-256
Exploring Imperceptible Adversarial Examples in $YC_bC_r$ Color Space- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 1940-1953
Energy-Based Temporal Summarized Attentive Network for Zero-Shot Action Recognition
Recently, Action Recognition (AR) is facing the scalability problem, since collecting and annotating data for the ever-growing action categories is exhausting and inappropriate. As an alternative to AR, Zero-Shot Action Recognition (ZSAR) is getting more and more attention in the community, as they could utilize a shared semantic/attribute space to recognize novel categories without annotated data. Different from the AR focuses on learning the correlation between actions, ZSAR needs to consider the correlation of action-action, label-label and action-label at the same time. However, as far as we know, there is no work to provide structural guidance for the framework design of ZSAR according to its task characteristics. In this paper, we demonstrate the rationality of using the Energy-Based Model (EBM) to guide the framework design of ZSAR based on their inference mechanism. Furthermore, under the guidance of EBM, we propose an Energy-based Temporal Summarized Attentive Network (ETSAN) to achieve ZSAR. Specifically, to ensure the effectiveness of cross-modal matching, EBM needs to capture the correlations of input-input, output-output and input-output, based on discriminative and focused input and output space. To this end, we first design the Temporal Summarized Attentive Mechanism (TSAM) to capture the correlation of action-action by constructing discriminative and focused input space. Then, a Label Semantic Adaptive Mechanism (LSAM) is proposed to learn the correlation of label-label by adjusting the semantic structure according to the target task. Finally, we devise an Energy Score Estimation Mechanism (ESEM) to measure the compatibility (i.e. energy score) between video representation and label semantic embedding. With end-to-end training, our framework can capture all three of the correlations mentioned above simultaneously by minimizing the energy score of the correct action-label pair. Experiments on the HMDB51 and UCF101 datasets show that the proposed architecture achieves comparable results among methods based on the spatial-temporal visual feature of sequence-level, which demonstrates the efficiency of the EBM in guiding the framework design of ZSAR. In addition, our code is available at https://github.com/oOHCIOo/ETSAN .
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 1940-1953
Energy-Based Temporal Summarized Attentive Network for Zero-Shot Action Recognition
Recently, Action Recognition (AR) is facing the scalability problem, since collecting and annotating data for the ever-growing action categories is exhausting and inappropriate. As an alternative to AR, Zero-Shot Action Recognition (ZSAR) is getting more and more attention in the community, as they could utilize a shared semantic/attribute space to recognize novel categories without annotated data. Different from the AR focuses on learning the correlation between actions, ZSAR needs to consider the correlation of action-action, label-label and action-label at the same time. However, as far as we know, there is no work to provide structural guidance for the framework design of ZSAR according to its task characteristics. In this paper, we demonstrate the rationality of using the Energy-Based Model (EBM) to guide the framework design of ZSAR based on their inference mechanism. Furthermore, under the guidance of EBM, we propose an Energy-based Temporal Summarized Attentive Network (ETSAN) to achieve ZSAR. Specifically, to ensure the effectiveness of cross-modal matching, EBM needs to capture the correlations of input-input, output-output and input-output, based on discriminative and focused input and output space. To this end, we first design the Temporal Summarized Attentive Mechanism (TSAM) to capture the correlation of action-action by constructing discriminative and focused input space. Then, a Label Semantic Adaptive Mechanism (LSAM) is proposed to learn the correlation of label-label by adjusting the semantic structure according to the target task. Finally, we devise an Energy Score Estimation Mechanism (ESEM) to measure the compatibility (i.e. energy score) between video representation and label semantic embedding. With end-to-end training, our framework can capture all three of the correlations mentioned above simultaneously by minimizing the energy score of the correct action-label pair. Experiments on the HMDB51 and UCF101 datasets show that the proposed architecture achieves comparable results among methods based on the spatial-temporal visual feature of sequence-level, which demonstrates the efficiency of the EBM in guiding the framework design of ZSAR. In addition, our code is available at https://github.com/oOHCIOo/ETSAN .
- 1 March 2022
- Published by Elsevier in Journal of Energy Chemistry
- Vol. 70, 276-282
A one-for-all strategy of polyimide coating layer for resolving the comprehensive issues of phosphorus anode
- 1 March 2022
- Published by Elsevier in Journal of Energy Chemistry
- Vol. 70, 276-282
A one-for-all strategy of polyimide coating layer for resolving the comprehensive issues of phosphorus anode
- 29 December 2021
- Published by American Chemical Society (ACS) in Nano Letters
- Vol. 22 (4) , 1795-1803
Facile Separator Modification Strategy for Trapping Soluble Polyphosphides and Enhancing the Electrochemical Performance of Phosphorus Anode
Phosphorus anode is one of the most promising candidates for high-energy-density lithium-ion batteries. Recent studies found the lithiation process of phosphorus is accompanied by the soluble intermediates of lithium polyphosphides. The trans-separator diffusion of polyphosphides is responsible for the capacity decay. Herein, a facile separator modification strategy is proposed for improving the performance of phosphorus anode. The lightweight CNT-modified layer that has a continuous conductive skeleton, a dense structure, and a strong interaction with the soluble lithium polyphosphides can trap, stabilize, and reactivate the active material. Without sophisticated electrode structure design, the cyclability and high-rate performance of the phosphorus anode has been significantly improved, leading to a higher specific capacity of 1505 mAh/g at 250 mA/g (200th cycle) and 1312 mAh/g at 2 A/g. With the advantages of simplicity and low cost, the separator modification strategy provides a new feasible way for further improvement of the phosphorus-based anode.
- 29 December 2021
- Published by American Chemical Society (ACS) in Nano Letters
- Vol. 22 (4) , 1795-1803
Facile Separator Modification Strategy for Trapping Soluble Polyphosphides and Enhancing the Electrochemical Performance of Phosphorus Anode
Phosphorus anode is one of the most promising candidates for high-energy-density lithium-ion batteries. Recent studies found the lithiation process of phosphorus is accompanied by the soluble intermediates of lithium polyphosphides. The trans-separator diffusion of polyphosphides is responsible for the capacity decay. Herein, a facile separator modification strategy is proposed for improving the performance of phosphorus anode. The lightweight CNT-modified layer that has a continuous conductive skeleton, a dense structure, and a strong interaction with the soluble lithium polyphosphides can trap, stabilize, and reactivate the active material. Without sophisticated electrode structure design, the cyclability and high-rate performance of the phosphorus anode has been significantly improved, leading to a higher specific capacity of 1505 mAh/g at 250 mA/g (200th cycle) and 1312 mAh/g at 2 A/g. With the advantages of simplicity and low cost, the separator modification strategy provides a new feasible way for further improvement of the phosphorus-based anode.