Shanxin Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shanxin Yuan has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Greg Slabaugh
Queen Mary University of London
4 shared publications - Henry Senior
Queen Mary University of London
3 shared publications - Luca Rossi
The Hong Kong Polytechnic University
3 shared publications Bolun Zheng
Hangzhou Dianzi Universiy
1 shared publication- Changjae Oh
Queen Mary University of London
1 shared publication - Chenggang Yan
Hangzhou Dianzi University
1 shared publication
Latest Publications
- 9 November 2025
- Published by Springer Nature
- p. 1-15
SuperCap: Multi-resolution Superpixel-Based Image Captioning
- 9 November 2025
- Published by Springer Nature
- p. 1-15
SuperCap: Multi-resolution Superpixel-Based Image Captioning
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10662-10670
Robust Photo-Realistic Hand Gesture Generation: from Single View to Multiple View
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10662-10670
Open AccessRobust Photo-Realistic Hand Gesture Generation: from Single View to Multiple View
- Open Access
SuperCap: Multi-resolution Superpixel-based Image Captioning
It has been a longstanding goal within image captioning to move beyond a dependence on object detection. We investigate using superpixels coupled with Vision Language Models (VLMs) to bridge the gap between detector-based captioning architectures and those that solely pretrain on large datasets. Our novel superpixel approach ensures that the model receives object-like features whilst the use of VLMs provides our model with open set object understanding. Furthermore, we extend our architecture to make use of multi-resolution inputs, allowing our model to view images in different levels of detail, and use an attention mechanism to determine which parts are most relevant to the caption. We demonstrate our model's performance with multiple VLMs and through a range of ablations detailing the impact of different architectural choices. Our full model achieves a competitive CIDEr score of $136.9$ on the COCO Karpathy split.Open AccessSuperCap: Multi-resolution Superpixel-based Image Captioning
It has been a longstanding goal within image captioning to move beyond a dependence on object detection. We investigate using superpixels coupled with Vision Language Models (VLMs) to bridge the gap between detector-based captioning architectures and those that solely pretrain on large datasets. Our novel superpixel approach ensures that the model receives object-like features whilst the use of VLMs provides our model with open set object understanding. Furthermore, we extend our architecture to make use of multi-resolution inputs, allowing our model to view images in different levels of detail, and use an attention mechanism to determine which parts are most relevant to the caption. We demonstrate our model's performance with multiple VLMs and through a range of ablations detailing the impact of different architectural choices. Our full model achieves a competitive CIDEr score of $136.9$ on the COCO Karpathy split. - Open Access
- 29 March 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (1) , 491-516
Graph neural networks in vision-language image understanding: a survey
2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the scene. Solutions to this problem form the underpinning of a range of tasks, including image captioning, visual question answering (VQA), and image retrieval. Graphs provide a natural way to represent the relational arrangement between objects in an image, and thus, in recent years graph neural networks (GNNs) have become a standard component of many 2D image understanding pipelines, becoming a core architectural component, especially in the VQA group of tasks. In this survey, we review this rapidly evolving field and we provide a taxonomy of graph types used in 2D image understanding approaches, a comprehensive list of the GNN models used in this domain, and a roadmap of future potential developments. To the best of our knowledge, this is the first comprehensive survey that covers image captioning, visual question answering, and image retrieval techniques that focus on using GNNs as the main part of their architecture.
- 29 March 2024
- Published by Springer Nature in The Visual Computer
- Vol. 41 (1) , 491-516
Open AccessGraph neural networks in vision-language image understanding: a survey
2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the scene. Solutions to this problem form the underpinning of a range of tasks, including image captioning, visual question answering (VQA), and image retrieval. Graphs provide a natural way to represent the relational arrangement between objects in an image, and thus, in recent years graph neural networks (GNNs) have become a standard component of many 2D image understanding pipelines, becoming a core architectural component, especially in the VQA group of tasks. In this survey, we review this rapidly evolving field and we provide a taxonomy of graph types used in 2D image understanding approaches, a comprehensive list of the GNN models used in this domain, and a roadmap of future potential developments. To the best of our knowledge, this is the first comprehensive survey that covers image captioning, visual question answering, and image retrieval techniques that focus on using GNNs as the main part of their architecture.
- 26 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 7386-7397
Video Demoiréing With Deep Temporal Color Embedding and Video-Image Invertible Consistency
Demoiréing is the task of removing moiré patterns, which are commonly caused by the interference between the screen and digital cameras. Although research on single image demoiréing has made great progress, research on video demoiréing has received less attention from the community. Video demoiréing poses a new set of challenges. First, most existing video restoration algorithms rely on multi-resolution pixel-based alignment, which can cause damage to the details of the predicted results. Second, these algorithms are based on flow-based loss or relation-based loss, making it difficult to handle the large motions of adjacent frames while keeping temporal consistency intact. To address these challenges, we present a novel deep learning-based approach called the Deep Temporal Color Embedding network (DTCENet) that employs an invertible network to align distortion color patches in a patch-based embedding framework. DTCENet can well preserve details while eliminate color distortions. Furthermore, we introduce a video-image invertible loss function to effectively handle the color inconsistent problem of adjacent frames. Our approach shows promising results in demoiréing videos, with improved performance over existing state-of-the-art algorithms. Our method gets about 10% improvements in terms of LPIPS and 10.3% improvements in terms of FID compared with the recent SOTA methods.
- 26 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 7386-7397
Video Demoiréing With Deep Temporal Color Embedding and Video-Image Invertible Consistency
Demoiréing is the task of removing moiré patterns, which are commonly caused by the interference between the screen and digital cameras. Although research on single image demoiréing has made great progress, research on video demoiréing has received less attention from the community. Video demoiréing poses a new set of challenges. First, most existing video restoration algorithms rely on multi-resolution pixel-based alignment, which can cause damage to the details of the predicted results. Second, these algorithms are based on flow-based loss or relation-based loss, making it difficult to handle the large motions of adjacent frames while keeping temporal consistency intact. To address these challenges, we present a novel deep learning-based approach called the Deep Temporal Color Embedding network (DTCENet) that employs an invertible network to align distortion color patches in a patch-based embedding framework. DTCENet can well preserve details while eliminate color distortions. Furthermore, we introduce a video-image invertible loss function to effectively handle the color inconsistent problem of adjacent frames. Our approach shows promising results in demoiréing videos, with improved performance over existing state-of-the-art algorithms. Our method gets about 10% improvements in terms of LPIPS and 10.3% improvements in terms of FID compared with the recent SOTA methods.
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (1) , 340-349
Improving Dynamic HDR Imaging with Fusion Transformer
Reconstructing a High Dynamic Range (HDR) image from several Low Dynamic Range (LDR) images with different exposures is a challenging task, especially in the presence of camera and object motion. Though existing models using convolutional neural networks (CNNs) have made great progress, challenges still exist, e.g., ghosting artifacts. Transformers, originating from the field of natural language processing, have shown success in computer vision tasks, due to their ability to address a large receptive field even within a single layer. In this paper, we propose a transformer model for HDR imaging. Our pipeline includes three steps: alignment, fusion, and reconstruction. The key component is the HDR transformer module. Through experiments and ablation studies, we demonstrate that our model outperforms the state-of-the-art by large margins on several popular public datasets.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (1) , 340-349
Open AccessImproving Dynamic HDR Imaging with Fusion Transformer
Reconstructing a High Dynamic Range (HDR) image from several Low Dynamic Range (LDR) images with different exposures is a challenging task, especially in the presence of camera and object motion. Though existing models using convolutional neural networks (CNNs) have made great progress, challenges still exist, e.g., ghosting artifacts. Transformers, originating from the field of natural language processing, have shown success in computer vision tasks, due to their ability to address a large receptive field even within a single layer. In this paper, we propose a transformer model for HDR imaging. Our pipeline includes three steps: alignment, fusion, and reconstruction. The key component is the HDR transformer module. Through experiments and ablation studies, we demonstrate that our model outperforms the state-of-the-art by large margins on several popular public datasets.