Libo Zhang
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
Libo Zhang has a total of 235 co-authors. Here are the top co-authors by number of shared publications:
Tiejian Luo
University of Chinese Academy of Sciences
19 shared publications- Heng Fan
University of North Texas
18 shared publications Yanjun Wu
Institute of Software Chinese Academy of Sciences Beijing China
17 shared publicationsHeng Fan
Dept. of Computer Science & Engineering University of North Texas Denton United States of America
12 shared publicationsDawei Du
Kitware
8 shared publications- Dawei Du
Computer Science Department, University at Albany, State University of New York, Albany, NY, USA
8 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9619-9627
PanelLayout: Story-Aware Hierarchical Panel Layout Generation via Synchronized Diffusion
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9619-9627
Open AccessPanelLayout: Story-Aware Hierarchical Panel Layout Generation via Synchronized Diffusion
- 11 September 2026
- Published by Springer Nature
- p. 286-303
Towards Long-Form Spatio-Temporal Video Grounding
- 11 September 2026
- Published by Springer Nature
- p. 286-303
Towards Long-Form Spatio-Temporal Video Grounding
- 10 September 2026
- Published by Springer Nature
- p. 554-571
FlowFace: Rectifying Identity Conditioning with Riemannian Geometry for Face Generation
- 10 September 2026
- Published by Springer Nature
- p. 554-571
FlowFace: Rectifying Identity Conditioning with Riemannian Geometry for Face Generation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3062-3073
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3062-3073
Open AccessTuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
- Open Access
- 15 May 2026
- Published by Elsevier in Science Bulletin
- Vol. 71 (17) , 4386-4390
CardioNVT: an AI platform for immunostaining-free, high-throughput cardiomyocyte ploidy assessment in situ
- 15 May 2026
- Published by Elsevier in Science Bulletin
- Vol. 71 (17) , 4386-4390
Open AccessCardioNVT: an AI platform for immunostaining-free, high-throughput cardiomyocyte ploidy assessment in situ
- Open Access
VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation
Screenshot-to-code generation aims to translate user interface screenshots into executable frontend code that faithfully reproduces the target layout and style. Existing multimodal large language models perform this mapping directly from screenshots but are trained without observing the visual outcomes of their generated code. In contrast, human developers iteratively render their implementation, compare it with the design, and learn how visual differences relate to code changes. Inspired by this process, we propose VisRefiner, a training framework that enables models to learn from visual differences between rendered predictions and reference designs. We construct difference-aligned supervision that associates visual discrepancies with corresponding code edits, allowing the model to understand how appearance variations arise from implementation changes. Building on this, we introduce a reinforcement learning stage for self-refinement, where the model improves its generated code by observing both the rendered output and the target design, identifying their visual differences, and updating the code accordingly. Experiments show that VisRefiner substantially improves single-step generation quality and layout fidelity, while also endowing models with strong self-refinement ability. These results demonstrate the effectiveness of learning from visual differences for advancing screenshot-to-code generation.
Open AccessVisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation
Screenshot-to-code generation aims to translate user interface screenshots into executable frontend code that faithfully reproduces the target layout and style. Existing multimodal large language models perform this mapping directly from screenshots but are trained without observing the visual outcomes of their generated code. In contrast, human developers iteratively render their implementation, compare it with the design, and learn how visual differences relate to code changes. Inspired by this process, we propose VisRefiner, a training framework that enables models to learn from visual differences between rendered predictions and reference designs. We construct difference-aligned supervision that associates visual discrepancies with corresponding code edits, allowing the model to understand how appearance variations arise from implementation changes. Building on this, we introduce a reinforcement learning stage for self-refinement, where the model improves its generated code by observing both the rendered output and the target design, identifying their visual differences, and updating the code accordingly. Experiments show that VisRefiner substantially improves single-step generation quality and layout fidelity, while also endowing models with strong self-refinement ability. These results demonstrate the effectiveness of learning from visual differences for advancing screenshot-to-code generation.
- Open Access
PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
Planar tracking has drawn increasing interest owing to its key roles in robotics and augmented reality. Despite recent great advancement, further development of planar tracking, particularly in the deep learning era, is largely limited compared to generic tracking due to the lack of large-scale platforms. To mitigate this, we propose PlanarTrack, a large-scale high-quality and challenging benchmark for planar tracking. Specifically, PlanarTrack consists of 1,150 sequences with over 733K frames, including 1,000 short-term and 150 new long-term videos, which enables comprehensive evaluation of short- and long-term tracking performance. All videos in PlanarTrack are recorded in unconstrained conditions from the wild, which makes PlanarTrack challenging but more realistic for real-world applications. To ensure high-quality annotations, each video frame is manually annotated by four corner points with multi-round meticulous inspection and refinement. To enhance target diversity of PlanarTrack, we only capture a unique target in one sequence, which is different from existing benchmarks. To our best knowledge, PlanarTrack is by far the largest and most diverse and challenging dataset dedicated to planar tracking. To understand performance of existing methods on PlanarTrack and to provide a comparison for future research, we evaluate 10 representative planar trackers with extensive comparison and in-depth analysis. Our evaluation reveals that, unsurprisingly, the top planar trackers heavily degrade on the challenging PlanarTrack, which indicates more efforts are required for improving planar tracking. Our data and results will be released at https://github.com/HengLan/PlanarTrack
Open AccessPlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
Planar tracking has drawn increasing interest owing to its key roles in robotics and augmented reality. Despite recent great advancement, further development of planar tracking, particularly in the deep learning era, is largely limited compared to generic tracking due to the lack of large-scale platforms. To mitigate this, we propose PlanarTrack, a large-scale high-quality and challenging benchmark for planar tracking. Specifically, PlanarTrack consists of 1,150 sequences with over 733K frames, including 1,000 short-term and 150 new long-term videos, which enables comprehensive evaluation of short- and long-term tracking performance. All videos in PlanarTrack are recorded in unconstrained conditions from the wild, which makes PlanarTrack challenging but more realistic for real-world applications. To ensure high-quality annotations, each video frame is manually annotated by four corner points with multi-round meticulous inspection and refinement. To enhance target diversity of PlanarTrack, we only capture a unique target in one sequence, which is different from existing benchmarks. To our best knowledge, PlanarTrack is by far the largest and most diverse and challenging dataset dedicated to planar tracking. To understand performance of existing methods on PlanarTrack and to provide a comparison for future research, we evaluate 10 representative planar trackers with extensive comparison and in-depth analysis. Our evaluation reveals that, unsurprisingly, the top planar trackers heavily degrade on the challenging PlanarTrack, which indicates more efforts are required for improving planar tracking. Our data and results will be released at https://github.com/HengLan/PlanarTrack
- 25 October 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 262
PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
- 25 October 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 262
PlanarTrack: A high-quality and challenging benchmark for large-scale planar object tracking
- Open Access
G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature aggregation, a key factor in extracting meaningful representations. However, despite their success, GCNs often struggle to effectively distinguish between ambiguous actions, revealing limitations in the representation of learned topological and spatial features. To address this challenge, we propose a novel approach, Gaussian Topology Refinement Gated Graph Convolution (G$^{3}$CN), to address the challenge of distinguishing ambiguous actions in skeleton-based action recognition. G$^{3}$CN incorporates a Gaussian filter to refine the skeleton topology graph, improving the representation of ambiguous actions. Additionally, Gated Recurrent Units (GRUs) are integrated into the GCN framework to enhance information propagation between skeleton points. Our method shows strong generalization across various GCN backbones. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA benchmarks demonstrate that G$^{3}$CN effectively improves action recognition, particularly for ambiguous samples.
Open AccessG3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature aggregation, a key factor in extracting meaningful representations. However, despite their success, GCNs often struggle to effectively distinguish between ambiguous actions, revealing limitations in the representation of learned topological and spatial features. To address this challenge, we propose a novel approach, Gaussian Topology Refinement Gated Graph Convolution (G$^{3}$CN), to address the challenge of distinguishing ambiguous actions in skeleton-based action recognition. G$^{3}$CN incorporates a Gaussian filter to refine the skeleton topology graph, improving the representation of ambiguous actions. Additionally, Gated Recurrent Units (GRUs) are integrated into the GCN framework to enhance information propagation between skeleton points. Our method shows strong generalization across various GCN backbones. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA benchmarks demonstrate that G$^{3}$CN effectively improves action recognition, particularly for ambiguous samples.
- 16 May 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (8) , 5788-5805
High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion
- 16 May 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (8) , 5788-5805
High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion