Yixiu Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yixiu Liu has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Yunzhou Zhang
College of Information Science and Engineering, Northeastern University, Shenyang, China
4 shared publications - Zhigao Zheng
School of Computer Science, Wuhan University, Wuhan, China
4 shared publications - Chenggang Yan
Hangzhou Dianzi University, Hangzhou, China
3 shared publications - Fawei Ge
College of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian, China
3 shared publications - Shangdong Zhu
School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China
3 shared publications - Pengfei Jiao
Hangzhou Dianzi University
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17510-17524
EventLens: Event-Aware Hierarchical Evidence Construction for Long-Video Understanding
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 17510-17524
EventLens: Event-Aware Hierarchical Evidence Construction for Long-Video Understanding
- Open Access
- 1 January 2026
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 87 (2) , 1-10
Abel-Net: Aggregate Bilateral Edge Localization Network for Multi-Task Binary Segmentation
Binary segmentation tasks in computer vision exhibit diverse appearance distributions and complex boundary characteristics. To address the limited generalization and adaptability of existing models across heterogeneous tasks, we propose Abel-Net, an Aggregated Bilateral Edge Localization Network designed as a universal framework for multi-task binary segmentation. Abel-Net integrates global and local contextual cues to enhance feature learning and edge precision. Specifically, a multi-scale feature pyramid fusion strategy is implemented via an Aggregated Skip Connection (ASC) module to strengthen feature adaptability, while the Edge Dual Localization (EDL) mechanism performs coarse-to-fine refinement through edge-aware supervision. Additionally, Edge Attention (EA) and Edge Fusion Attention (EFA) modules prioritize edge-critical regions and facilitate accurate boundary alignment. Extensive experiments on nine diverse binary segmentation tasks demonstrate that Abel-Net performs comparably to or surpasses state-of-the-art task-specific networks, exhibiting strong adaptability to a wide range of visual perception challenges.
- 1 January 2026
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 87 (2) , 1-10
Open AccessAbel-Net: Aggregate Bilateral Edge Localization Network for Multi-Task Binary Segmentation
Binary segmentation tasks in computer vision exhibit diverse appearance distributions and complex boundary characteristics. To address the limited generalization and adaptability of existing models across heterogeneous tasks, we propose Abel-Net, an Aggregated Bilateral Edge Localization Network designed as a universal framework for multi-task binary segmentation. Abel-Net integrates global and local contextual cues to enhance feature learning and edge precision. Specifically, a multi-scale feature pyramid fusion strategy is implemented via an Aggregated Skip Connection (ASC) module to strengthen feature adaptability, while the Edge Dual Localization (EDL) mechanism performs coarse-to-fine refinement through edge-aware supervision. Additionally, Edge Attention (EA) and Edge Fusion Attention (EFA) modules prioritize edge-critical regions and facilitate accurate boundary alignment. Extensive experiments on nine diverse binary segmentation tasks demonstrate that Abel-Net performs comparably to or surpasses state-of-the-art task-specific networks, exhibiting strong adaptability to a wide range of visual perception challenges.
- 4 November 2025
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 171, 103289
Multi-annotation agreement and prediction consistency networks: Improving semi-supervised segmentation of medical images with ambiguous boundaries
- 4 November 2025
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 171, 103289
Multi-annotation agreement and prediction consistency networks: Improving semi-supervised segmentation of medical images with ambiguous boundaries
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (7) , 6914-6921
SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection
Unsupervised camouflaged object detection (UCOD) poses significant challenges, primarily attributed to the absence of human labels. Existing UCOD methodologies, leveraging attention mechanisms, often struggle to achieve precise localization of camouflaged objects. To overcome this limitation, we introduce a groundbreaking fully unsupervised algorithm for attention-guided camouflaged object localization, shift, and inference, termed the self-distilled attention localization and shift network (SdalsNet). In this study, we formulate an attention localization methodology aimed at accurately identifying the central coordinate of the camouflaged object. Furthermore, we propose four distinct loss functions tailored to refine the precision of attentional positioning. These loss functions effectively constrain the distances between three types of class tokens, facilitating seamless attentional shifting across the input sample. Additionally, we design a sophisticated prediction inference technique to reconstruct the binary output of an attention map, thereby providing a comprehensive understanding of the detected camouflaged objects. Experimental results on four challenging COD benchmark datasets corroborate the effectiveness of our proposed approach, demonstrating notable superiority over state-of-the-art methods.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (7) , 6914-6921
Open AccessSdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection
Unsupervised camouflaged object detection (UCOD) poses significant challenges, primarily attributed to the absence of human labels. Existing UCOD methodologies, leveraging attention mechanisms, often struggle to achieve precise localization of camouflaged objects. To overcome this limitation, we introduce a groundbreaking fully unsupervised algorithm for attention-guided camouflaged object localization, shift, and inference, termed the self-distilled attention localization and shift network (SdalsNet). In this study, we formulate an attention localization methodology aimed at accurately identifying the central coordinate of the camouflaged object. Furthermore, we propose four distinct loss functions tailored to refine the precision of attentional positioning. These loss functions effectively constrain the distances between three types of class tokens, facilitating seamless attentional shifting across the input sample. Additionally, we design a sophisticated prediction inference technique to reconstruct the binary output of an attention map, thereby providing a comprehensive understanding of the detected camouflaged objects. Experimental results on four challenging COD benchmark datasets corroborate the effectiveness of our proposed approach, demonstrating notable superiority over state-of-the-art methods.
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Improving Grasp Pose Detection by Implicitly Utilizing Geometric Information and Spatial Relations of Objects in Clutter
6-DoF grasp pose detection in clutter is an essential but challenging task in the vision measurement. However, most current detection methods often fail to consider the geometric information and partial occlusions of objects in clutter, resulting in inaccurate robotic grasping and potential collisions. In this work, we propose an end-to-end grasping system to directly generate 6-DoF grasp poses from point clouds in clutter. Our system first selects the most feasible positions as the grasp centers, and then determines their grasp parameters, such as approaching vectors and in-plane rotations. Specifically, we design an optimality criterion based on the geometric information of objects to extract rich object features from the scene and identify high-graspablity areas. To alleviate the collision problem caused by occlusions, we focus on the spatial relations among objects and explicitly train a collision predictor to directly select collision-free points as grasp centers from high-graspablity areas. Based on these grasp centers, our model can easily generate diverse sets of collision- free and robust grasp poses for successful grasping. To efficiently determine grasp parameters, we exploit neighbor search to capture the local context around each grasp center and then implicitly learn relations among objects using the self-attention mechanism. Compared with previous methods, our grasping system improves performance by a large margin (>10%), and achieves state-of-the-art results on GraspNet-1Billion, a largescale dataset. Besides, our method has a high success rate for grasping in simulation and real-world experiments, verifying the validity in clutter.
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Improving Grasp Pose Detection by Implicitly Utilizing Geometric Information and Spatial Relations of Objects in Clutter
6-DoF grasp pose detection in clutter is an essential but challenging task in the vision measurement. However, most current detection methods often fail to consider the geometric information and partial occlusions of objects in clutter, resulting in inaccurate robotic grasping and potential collisions. In this work, we propose an end-to-end grasping system to directly generate 6-DoF grasp poses from point clouds in clutter. Our system first selects the most feasible positions as the grasp centers, and then determines their grasp parameters, such as approaching vectors and in-plane rotations. Specifically, we design an optimality criterion based on the geometric information of objects to extract rich object features from the scene and identify high-graspablity areas. To alleviate the collision problem caused by occlusions, we focus on the spatial relations among objects and explicitly train a collision predictor to directly select collision-free points as grasp centers from high-graspablity areas. Based on these grasp centers, our model can easily generate diverse sets of collision- free and robust grasp poses for successful grasping. To efficiently determine grasp parameters, we exploit neighbor search to capture the local context around each grasp center and then implicitly learn relations among objects using the self-attention mechanism. Compared with previous methods, our grasping system improves performance by a large margin (>10%), and achieves state-of-the-art results on GraspNet-1Billion, a largescale dataset. Besides, our method has a high success rate for grasping in simulation and real-world experiments, verifying the validity in clutter.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (5) , 3518-3532
AE-Net: Appearance-Enriched Neural Network With Foreground Enhancement for Person Re-Identification
Person re-identification (Re-ID) in environments subject to intensive appearance and background variations due to seasons, weather conditions, illumination and human factors is a challenging task. A wide variety of existing algorithms address this problem either for appearance changes or background clutter, but neglect to explore a powerful framework to consider solving both cases simultaneously. To overcome this limitation, this research introduces an effective appearance-enriched neural network (AE-Net) with foreground enhancement based on generative adversarial nets (GANs) and an attention mechanism to enrich the appearance of person images while suppressing the influence of the background. Specifically, a channel-grouped convolution and squeeze weighted (CGCSW) module is first proposed to extract the powerful feature representation of individuals. Secondly, a foreground-enhanced and background-suppressed (FEBS) module is proposed to enhance the foreground of individual samples while weakening the impact of the background. Thirdly, A stage-wise consistency loss is presented to enable our model maintain consistent foreground-enhanced and background-suppressed stages. Finally, this study evaluates the proposed method and compares it with state-of-the-art approaches on three public datasets. The experimental results demonstrate the effectiveness and improvements achieved by using the presented architecture.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (5) , 3518-3532
AE-Net: Appearance-Enriched Neural Network With Foreground Enhancement for Person Re-Identification
Person re-identification (Re-ID) in environments subject to intensive appearance and background variations due to seasons, weather conditions, illumination and human factors is a challenging task. A wide variety of existing algorithms address this problem either for appearance changes or background clutter, but neglect to explore a powerful framework to consider solving both cases simultaneously. To overcome this limitation, this research introduces an effective appearance-enriched neural network (AE-Net) with foreground enhancement based on generative adversarial nets (GANs) and an attention mechanism to enrich the appearance of person images while suppressing the influence of the background. Specifically, a channel-grouped convolution and squeeze weighted (CGCSW) module is first proposed to extract the powerful feature representation of individuals. Secondly, a foreground-enhanced and background-suppressed (FEBS) module is proposed to enhance the foreground of individual samples while weakening the impact of the background. Thirdly, A stage-wise consistency loss is presented to enable our model maintain consistent foreground-enhanced and background-suppressed stages. Finally, this study evaluates the proposed method and compares it with state-of-the-art approaches on three public datasets. The experimental results demonstrate the effectiveness and improvements achieved by using the presented architecture.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Joint Representation Learning Based on Feature Center Region Diffusion and Edge Radiation for Cross-View Geo-Localization
The essence of the cross-view geo-localization task is to accurately identify the same object across images captured from different viewpoints. Due to variations in image acquisition methods and viewing angles, the content information of the images can differ significantly, which may result in localization failure. Therefore, cross-view geo-localization remains a challenging task. To solve this issue, a joint representation learning network based on feature center region diffusion and edge radiation is proposed in this article. First, to extract the crucial information from the global features, we design the central diffusion module that identifies important regions within the features and enhances feature robustness. Additionally, we design an edge radiation mechanism that expands the receptive field and further highlights crucial information in the image to support the central diffusion module in achieving more stable performance. On this basis, we propose an adaptive triple InfoNCE loss function to assist network training, improving the discriminability of the extracted features. Finally, the proposed network is tested on two mainstream datasets, and experimental results demonstrate that the proposed model outperforms the state-of-the-art methods, which can prove its effectiveness.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Joint Representation Learning Based on Feature Center Region Diffusion and Edge Radiation for Cross-View Geo-Localization
The essence of the cross-view geo-localization task is to accurately identify the same object across images captured from different viewpoints. Due to variations in image acquisition methods and viewing angles, the content information of the images can differ significantly, which may result in localization failure. Therefore, cross-view geo-localization remains a challenging task. To solve this issue, a joint representation learning network based on feature center region diffusion and edge radiation is proposed in this article. First, to extract the crucial information from the global features, we design the central diffusion module that identifies important regions within the features and enhances feature robustness. Additionally, we design an edge radiation mechanism that expands the receptive field and further highlights crucial information in the image to support the central diffusion module in achieving more stable performance. On this basis, we propose an adaptive triple InfoNCE loss function to assist network training, improving the discriminability of the extracted features. Finally, the proposed network is tested on two mainstream datasets, and experimental results demonstrate that the proposed model outperforms the state-of-the-art methods, which can prove its effectiveness.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 785-795
Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection
Precisely locating the edges of objects camouflaged as background is an exceedingly complicated task. Existing camouflaged object detection (COD) methods can accurately pinpoint the positions of objects, but the edges remain ambiguous. To tackle this challenge, we propose a multi-stage refinement framework to locate the precise edges of camouflaged objects coarse-to-fine, coined SAE, which integrates “shrink" and “expose" in each stage. In this paper, we transform the process by which humans capture object edges into a multi-stage shrinking process. Firstly, we obtain the edge probability distribution by subtracting a negative prediction result from a positive prediction result, thus proposing the positive-negative edge shrink module. The edge probability distribution from the previous stage is then explicitly propagated to the current stage to enhance the edge texture details. Second, we introduce edge exposure attention to expose significant edges, which also reflects the impact of the previous stage’s edge state and edge probability distribution on the current stage’s edge state. Finally, to eliminate state transition and edge deformation anomalies, we propose the abnormal localization restriction to ensure the proper execution of “shrink” and “expose”. Experimental results show that our model significantly outperforms recent SOTA methods on three COD benchmarks.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 785-795
Shrink and Expose: Locate Edge Coarse-to-Fine for Camouflaged Object Detection
Precisely locating the edges of objects camouflaged as background is an exceedingly complicated task. Existing camouflaged object detection (COD) methods can accurately pinpoint the positions of objects, but the edges remain ambiguous. To tackle this challenge, we propose a multi-stage refinement framework to locate the precise edges of camouflaged objects coarse-to-fine, coined SAE, which integrates “shrink" and “expose" in each stage. In this paper, we transform the process by which humans capture object edges into a multi-stage shrinking process. Firstly, we obtain the edge probability distribution by subtracting a negative prediction result from a positive prediction result, thus proposing the positive-negative edge shrink module. The edge probability distribution from the previous stage is then explicitly propagated to the current stage to enhance the edge texture details. Second, we introduce edge exposure attention to expose significant edges, which also reflects the impact of the previous stage’s edge state and edge probability distribution on the current stage’s edge state. Finally, to eliminate state transition and edge deformation anomalies, we propose the abnormal localization restriction to ensure the proper execution of “shrink” and “expose”. Experimental results show that our model significantly outperforms recent SOTA methods on three COD benchmarks.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 883-894
A Dual-Stream Cross-Domain Integration Network for RGB-T Salient Object Detection
RGB-T salient object detection enhances the performance of detection in complex scenes by integrating RGB and thermal data, but effective fusion remains challenging. To this end, we propose a dual-stream cross-domain integration network (DSCDNet), which explores the effective integration of spatial and frequency domain features, demonstrating remarkable accuracy and stability. Specifically, in the bimodal integration stage, to deeply extract high-level fusion information from multiple modalities, we introduce the spatial domain bimodal integration module and the frequency domain bimodal integration module. This parallel integration strategy facilitates the deep integration of RGB and thermal image from multiple dimensions. After that, our proposed feature decomposition strategy decomposes the spatial fused features into two streams: region perception stream and detail-aware stream, which interpret spatial features from the perspectives of regional and detail understanding, making the model more flexible and efficient in complex scenes. Further, to maximize the complementary advantages between spatial and frequency domain, we design a cross domain feature alignment module to facilitate the interactive learning between the two domains, thereby providing the model with a more comprehensive and enriched representation perspective. Experimental results demonstrate that the proposed DSCDNet outperforms 11 state-of-the-art (SOTA) methods.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 883-894
A Dual-Stream Cross-Domain Integration Network for RGB-T Salient Object Detection
RGB-T salient object detection enhances the performance of detection in complex scenes by integrating RGB and thermal data, but effective fusion remains challenging. To this end, we propose a dual-stream cross-domain integration network (DSCDNet), which explores the effective integration of spatial and frequency domain features, demonstrating remarkable accuracy and stability. Specifically, in the bimodal integration stage, to deeply extract high-level fusion information from multiple modalities, we introduce the spatial domain bimodal integration module and the frequency domain bimodal integration module. This parallel integration strategy facilitates the deep integration of RGB and thermal image from multiple dimensions. After that, our proposed feature decomposition strategy decomposes the spatial fused features into two streams: region perception stream and detail-aware stream, which interpret spatial features from the perspectives of regional and detail understanding, making the model more flexible and efficient in complex scenes. Further, to maximize the complementary advantages between spatial and frequency domain, we design a cross domain feature alignment module to facilitate the interactive learning between the two domains, thereby providing the model with a more comprehensive and enriched representation perspective. Experimental results demonstrate that the proposed DSCDNet outperforms 11 state-of-the-art (SOTA) methods.