Wen Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Wen Yang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jinjian Wu
Xidian University, Xi'an, China
6 shared publications - Guangming Shi
Peng Cheng Laboratory, Shenzhen, Guangdong, China
4 shared publications - Jupo Ma
Xidian University, Xi'an, China
4 shared publications - Weisheng Dong
School of Artificial Intelligence, Xidian University, Xi’an, China
4 shared publications - Leida Li
Xidian University, Xi'an, China
3 shared publications - Zhaoxin Liu
School of Artificial Intelligence, Xidian University, Xian, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7478-7486
Enhanced LSTM with Robust Memory and Motion Learning for Event-based Object Detection
Event cameras have shown great potential for autonomous driving due to their high temporal resolution and wide dynamic range. However, most existing event-based object detectors rely on LSTM-based temporal aggregation, which remains insufficient in highly dynamic scenes. In particular, conventional LSTMs depend on a single global memory to model temporal dependencies, making them vulnerable to abrupt variations in target-related event patterns and thus limiting robustness. Moreover, their implicit temporal modeling is not well suited to capturing motion dynamics explicitly, which often leads to inaccurate object localization. To address these issues, we propose EDeMM, a novel event-based object detection framework with enhanced memory and motion modeling capabilities. Specifically, we design a Double-Phase LSTM (DPLSTM) consisting of Outer and Inner recurrent units to jointly capture global temporal dependencies and local temporal variations, thereby improving memory robustness under dynamically changing inputs. We further introduce a Motion-Enhancement Module (MEM) to explicitly strengthen motion trend representation and improve localization accuracy in highly dynamic scenarios. Extensive experiments on the GEN1 and 1Mpx datasets demonstrate that EDeMM achieves superior detection performance and robustness under challenging real-world conditions.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7478-7486
Open AccessEnhanced LSTM with Robust Memory and Motion Learning for Event-based Object Detection
Event cameras have shown great potential for autonomous driving due to their high temporal resolution and wide dynamic range. However, most existing event-based object detectors rely on LSTM-based temporal aggregation, which remains insufficient in highly dynamic scenes. In particular, conventional LSTMs depend on a single global memory to model temporal dependencies, making them vulnerable to abrupt variations in target-related event patterns and thus limiting robustness. Moreover, their implicit temporal modeling is not well suited to capturing motion dynamics explicitly, which often leads to inaccurate object localization. To address these issues, we propose EDeMM, a novel event-based object detection framework with enhanced memory and motion modeling capabilities. Specifically, we design a Double-Phase LSTM (DPLSTM) consisting of Outer and Inner recurrent units to jointly capture global temporal dependencies and local temporal variations, thereby improving memory robustness under dynamically changing inputs. We further introduce a Motion-Enhancement Module (MEM) to explicitly strengthen motion trend representation and improve localization accuracy in highly dynamic scenarios. Extensive experiments on the GEN1 and 1Mpx datasets demonstrate that EDeMM achieves superior detection performance and robustness under challenging real-world conditions.
- 1 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 161
An event-based motion scene feature extraction framework
- 1 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 161
An event-based motion scene feature extraction framework
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 6836-6849
Learning Frame-Event Fusion for Motion Deblurring
Motion deblurring is a highly ill-posed problem due to the significant loss of motion information in the blurring process. Complementary informative features from auxiliary sensors such as event cameras can be explored for guiding motion deblurring. The event camera can capture rich motion information asynchronously with microsecond accuracy. In this paper, a novel frame-event fusion framework is proposed for event-driven motion deblurring (FEF-Deblur), which can sufficiently explore long-range cross-modal information interactions. Firstly, different modalities are usually complementary and also redundant. Cross-modal fusion is modeled as complementary-unique features separation-and-aggregation, avoiding the modality redundancy. Unique features and complementary features are first inferred with parallel intra-modal self-attention and inter-modal cross-attention respectively. After that, a correlation-based constraint is designed to act between unique and complementary features to facilitate their differentiation, which assists in cross-modal redundancy suppression. Additionally, spatio-temporal dependencies among neighboring inputs are crucial for motion deblurring. A recurrent cross attention is introduced to preserve inter-input attention information, in which the current spatial features and aggregated temporal features are attending to each other by establishing the long-range interaction between them. Extensive experiments on both synthetic and real-world motion deblurring datasets demonstrate our method outperforms state-of-the-art event-based and image/video-based methods. The code will be made publicly available.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 6836-6849
Learning Frame-Event Fusion for Motion Deblurring
Motion deblurring is a highly ill-posed problem due to the significant loss of motion information in the blurring process. Complementary informative features from auxiliary sensors such as event cameras can be explored for guiding motion deblurring. The event camera can capture rich motion information asynchronously with microsecond accuracy. In this paper, a novel frame-event fusion framework is proposed for event-driven motion deblurring (FEF-Deblur), which can sufficiently explore long-range cross-modal information interactions. Firstly, different modalities are usually complementary and also redundant. Cross-modal fusion is modeled as complementary-unique features separation-and-aggregation, avoiding the modality redundancy. Unique features and complementary features are first inferred with parallel intra-modal self-attention and inter-modal cross-attention respectively. After that, a correlation-based constraint is designed to act between unique and complementary features to facilitate their differentiation, which assists in cross-modal redundancy suppression. Additionally, spatio-temporal dependencies among neighboring inputs are crucial for motion deblurring. A recurrent cross attention is introduced to preserve inter-input attention information, in which the current spatial features and aggregated temporal features are attending to each other by establishing the long-range interaction between them. Extensive experiments on both synthetic and real-world motion deblurring datasets demonstrate our method outperforms state-of-the-art event-based and image/video-based methods. The code will be made publicly available.
- 3 November 2024
- Published by Springer Nature
- p. 354-368
A Redundancy-Suppression Based Event Sampling Method for Structured Representation
- 3 November 2024
- Published by Springer Nature
- p. 354-368
A Redundancy-Suppression Based Event Sampling Method for Structured Representation
- 21 June 2024
- Published by Springer Nature
- p. 199-211
Unsupervised Event-to-Image Reconstruction Based on Domain Adaptation
- 21 June 2024
- Published by Springer Nature
- p. 199-211
Unsupervised Event-to-Image Reconstruction Based on Domain Adaptation
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8327-8335
Event-based Motion Deblurring with Modality-Aware Decomposition and Recomposition
Event camera responds to the brightness changes at each pixel independently with microsecond accuracy. Event cameras offer attractive property that can record well high-speed scene but ignore static and non-moving areas, while conventional frame cameras are able to acquire the whole intensity information of the scene but suffer from motion blur. Therefore, it would be desirable to combine the best of two cameras for reconstructing high quality intensity frame with no motion blur. The human visual system presents a two-pathway procedure for non-action-based representation and objects motion perception, which corresponds well to the hybrid frame and event. In this paper, inspired by the two-pathway visual system, a novel dual-stream based framework is proposed for motion deblurring (DS-Deblur), which flexibly utilizes the respective advantages from frame and event. A complementary-unique information splitting based feature fusion module is firstly proposed to adaptively aggregate the frame and event progressively at multiple levels, which is well-grounded on the hierarchical process in twopathway visual system. Then, a recurrent spatio-temporal feature transformation module is designed to exploit relevant information between adjacent frames, in which features of both current and previous frames are transformed in a global-local manner. Extensive experiments on both synthetic and real motion blur datasets demonstrate our method achieves state-of-the-art performance. Project website: https://github.com/wyang-vis/Motion-Deblurringwith-Hybrid-Frames-and-Events.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8327-8335
Open AccessEvent-based Motion Deblurring with Modality-Aware Decomposition and Recomposition
Event camera responds to the brightness changes at each pixel independently with microsecond accuracy. Event cameras offer attractive property that can record well high-speed scene but ignore static and non-moving areas, while conventional frame cameras are able to acquire the whole intensity information of the scene but suffer from motion blur. Therefore, it would be desirable to combine the best of two cameras for reconstructing high quality intensity frame with no motion blur. The human visual system presents a two-pathway procedure for non-action-based representation and objects motion perception, which corresponds well to the hybrid frame and event. In this paper, inspired by the two-pathway visual system, a novel dual-stream based framework is proposed for motion deblurring (DS-Deblur), which flexibly utilizes the respective advantages from frame and event. A complementary-unique information splitting based feature fusion module is firstly proposed to adaptively aggregate the frame and event progressively at multiple levels, which is well-grounded on the hierarchical process in twopathway visual system. Then, a recurrent spatio-temporal feature transformation module is designed to exploit relevant information between adjacent frames, in which features of both current and previous frames are transformed in a global-local manner. Extensive experiments on both synthetic and real motion blur datasets demonstrate our method achieves state-of-the-art performance. Project website: https://github.com/wyang-vis/Motion-Deblurringwith-Hybrid-Frames-and-Events.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (5) , 3742-3754
Motion-Oriented Hybrid Spiking Neural Networks for Event-Based Motion Deblurring
Image deblurring based only on the blurry image is challenging as motion information is lost while imaging. Event cameras capture the texture of moving objects in high temporal resolution with asynchronous events. In this paper, we extract motion features from events and fuse them with background features from the image for event-based image deblurring. Spiking neural network (SNN), a widely recognized event feature extractor, is well suited for motion feature extraction due to its high temporal resolution. However, extracting motion information from events exclusively with SNN is challenging. We propose a novel Temporal-local-Spatio Spiking Transformer (TSST) to extract motion intensity and motion attention regions in the spatio-temporal domain. Motion intensity extracted from spiking features is represented as a high temporal resolution motion attention map to guide the fusion of the two networks. In the temporal domain, motion intensity maps spiking features to CNN features as motion features to avoid blurring. In the spatial domain, the motion intensity shows the motion regions and gives the weight of the motion feature during fusion. Moreover, a hybrid feature extraction encoder (HFEE) is introduced, which fully fuses the motion and background features for deblurring. The gradient is back-propagated from CNN to SNN, and the hybrid deblurring network is jointly optimized. We evaluated the performance of our model on the public dataset GoPro and a real event dataset we captured. Codes and pretrained models are available at https://github.com/XDULzx/MotionSNN.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (5) , 3742-3754
Motion-Oriented Hybrid Spiking Neural Networks for Event-Based Motion Deblurring
Image deblurring based only on the blurry image is challenging as motion information is lost while imaging. Event cameras capture the texture of moving objects in high temporal resolution with asynchronous events. In this paper, we extract motion features from events and fuse them with background features from the image for event-based image deblurring. Spiking neural network (SNN), a widely recognized event feature extractor, is well suited for motion feature extraction due to its high temporal resolution. However, extracting motion information from events exclusively with SNN is challenging. We propose a novel Temporal-local-Spatio Spiking Transformer (TSST) to extract motion intensity and motion attention regions in the spatio-temporal domain. Motion intensity extracted from spiking features is represented as a high temporal resolution motion attention map to guide the fusion of the two networks. In the temporal domain, motion intensity maps spiking features to CNN features as motion features to avoid blurring. In the spatial domain, the motion intensity shows the motion regions and gives the weight of the motion feature during fusion. Moreover, a hybrid feature extraction encoder (HFEE) is introduced, which fully fuses the motion and background features for deblurring. The gradient is back-propagated from CNN to SNN, and the hybrid deblurring network is jointly optimized. We evaluated the performance of our model on the public dataset GoPro and a real event dataset we captured. Codes and pretrained models are available at https://github.com/XDULzx/MotionSNN.
- 5 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 3578-3590
Fine-Grained Image Quality Caption With Hierarchical Semantics Degradation
Blind image quality assessment (BIQA), which is capable of precisely and automatically estimating human perceived image quality with no pristine image for comparison, attracts extensive attention and is of wide applications. Recently, many existing BIQA methods commonly represent image quality with a quantitative value, which is inconsistent with human cognition. Generally, human beings are good at perceiving image quality in terms of semantic description rather than quantitative value. Moreover, cognition is a needs-oriented task where humans are able to extract image contents with local to global semantics as they need. The mediocre quality value represents coarse or holistic image quality and fails to reflect degradation on hierarchical semantics. In this paper, to comply with human cognition, a novel quality caption model is inventively proposed to measure fine-grained image quality with hierarchical semantics degradation. Research on human visual system indicates there are hierarchy and reverse hierarchy correlations between hierarchical semantics. Meanwhile, empirical evidence shows that there are also bi-directional degradation dependencies between them. Thus, a novel bi-directional relationship-based network (BDRNet) is proposed for semantics degradation description, through adaptively exploring those correlations and degradation dependencies in a bi-directional manner. Extensive experiments demonstrate that our method outperforms the state-of-the-arts in terms of both evaluation performance and generalization ability.
- 5 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 3578-3590
Fine-Grained Image Quality Caption With Hierarchical Semantics Degradation
Blind image quality assessment (BIQA), which is capable of precisely and automatically estimating human perceived image quality with no pristine image for comparison, attracts extensive attention and is of wide applications. Recently, many existing BIQA methods commonly represent image quality with a quantitative value, which is inconsistent with human cognition. Generally, human beings are good at perceiving image quality in terms of semantic description rather than quantitative value. Moreover, cognition is a needs-oriented task where humans are able to extract image contents with local to global semantics as they need. The mediocre quality value represents coarse or holistic image quality and fails to reflect degradation on hierarchical semantics. In this paper, to comply with human cognition, a novel quality caption model is inventively proposed to measure fine-grained image quality with hierarchical semantics degradation. Research on human visual system indicates there are hierarchy and reverse hierarchy correlations between hierarchical semantics. Meanwhile, empirical evidence shows that there are also bi-directional degradation dependencies between them. Thus, a novel bi-directional relationship-based network (BDRNet) is proposed for semantics degradation description, through adaptively exploring those correlations and degradation dependencies in a bi-directional manner. Extensive experiments demonstrate that our method outperforms the state-of-the-arts in terms of both evaluation performance and generalization ability.
- 1 April 2014
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 85 (4) , 046102
Note: A piezo tip/tilt platform: Structure, kinematics, and experiments
A Piezo Tip/Tilt Platform (PT2P) is presented with its structure, kinematics, and preliminary experiments. Two essential models of the presented PT2P, an equivalent hinge of the flexure hinge and a simplified model of the transmission mechanism, are discussed with the analysis on the structure of the PT2P. Based on these models, the inverse kinematics of the PT2P is derived. Two experiments are conducted on a prototype of the PT2P. The kinematic model is verified with experimental results, which also indicate that the resolution and the repeatability of the PT2P is, respectively, better than 0.50 μrad and 0.25 μrad.
- 1 April 2014
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 85 (4) , 046102
Note: A piezo tip/tilt platform: Structure, kinematics, and experiments
A Piezo Tip/Tilt Platform (PT2P) is presented with its structure, kinematics, and preliminary experiments. Two essential models of the presented PT2P, an equivalent hinge of the flexure hinge and a simplified model of the transmission mechanism, are discussed with the analysis on the structure of the PT2P. Based on these models, the inverse kinematics of the PT2P is derived. Two experiments are conducted on a prototype of the PT2P. The kinematic model is verified with experimental results, which also indicate that the resolution and the repeatability of the PT2P is, respectively, better than 0.50 μrad and 0.25 μrad.