Yanchun Ma
Research Subjects
Yanchun Ma has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jiachen Li
Wuhan University of Technology, Wuhan, China
13 shared publications - Qing Xie
Wuhan University of Technology, Wuhan, Hubei, China
13 shared publications - Jinyu Xu
Wuhan University of Technology, Wuhan, China
9 shared publications - Yongjian Liu
Wuhan University of Technology, Wuhan, China
9 shared publications - Anshu Hu
Wuhan University of Technology, Wuhan, China
3 shared publications - Zhifeng Bao
The University of Queensland, Brisbane, Australia
3 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3498-3505
A Sketch+Text Composed Image Retrieval Dataset for Thangka
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3498-3505
Open AccessA Sketch+Text Composed Image Retrieval Dataset for Thangka
- Open Access
- 21 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (6) , 1-24
Relation-Aware Proxy Hashing for Cross-Modal Retrieval
Proxy hashing methods have attracted increasing attention in cross-modal retrieval, because they are able to learn the mapping of different modalities into a common low-dimensional hash space by leveraging global proxies. However, existing approaches typically suffer from two limitations: (1) They solely utilize prior labels to capture the global semantic information, and hence lack the ability to explore necessary fine-grained semantic information to bridge the modality gap effectively. (2) They seldom consider the guidance information of intrinsic semantic similarity on proxy-centered space, and thus fail to leverage the similarity relations among instances sufficiently. To mitigate these limitations, we propose RAPH, a novel Relation-Aware Proxy Hashing framework that learns the semantic relations between different modalities and different semantic levels to enhance the discriminative capability of hash codes. Specifically, we first propose a Local Semantic Interaction (LSI) module based on masked language modeling to achieve the interaction of multi-modal fine-grained semantic features. Second, a relation-aware hashing learning scheme is designed to simultaneously explore the intrinsic semantic relationships and the global semantic information based on proxies. This is achieved by minimizing the reconstruction error between the multi-modal affinity matrices derived from learned features and the cross-modal similarity matrix of the hash codes. The proposed framework is able to learn more discriminative hash codes and achieves superior performance to many baselines on three public datasets.
- 21 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (6) , 1-24
Open AccessRelation-Aware Proxy Hashing for Cross-Modal Retrieval
Proxy hashing methods have attracted increasing attention in cross-modal retrieval, because they are able to learn the mapping of different modalities into a common low-dimensional hash space by leveraging global proxies. However, existing approaches typically suffer from two limitations: (1) They solely utilize prior labels to capture the global semantic information, and hence lack the ability to explore necessary fine-grained semantic information to bridge the modality gap effectively. (2) They seldom consider the guidance information of intrinsic semantic similarity on proxy-centered space, and thus fail to leverage the similarity relations among instances sufficiently. To mitigate these limitations, we propose RAPH, a novel Relation-Aware Proxy Hashing framework that learns the semantic relations between different modalities and different semantic levels to enhance the discriminative capability of hash codes. Specifically, we first propose a Local Semantic Interaction (LSI) module based on masked language modeling to achieve the interaction of multi-modal fine-grained semantic features. Second, a relation-aware hashing learning scheme is designed to simultaneously explore the intrinsic semantic relationships and the global semantic information based on proxies. This is achieved by minimizing the reconstruction error between the multi-modal affinity matrices derived from learned features and the cross-modal similarity matrix of the hash codes. The proposed framework is able to learn more discriminative hash codes and achieves superior performance to many baselines on three public datasets.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2149-2159
SDR-CIR: Semantic Debias Retrieval Framework for Training-Free Zero-Shot Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve a target image from a query composed of a reference image and modification text. Recent training-free zero-shot methods often employ Multimodal Large Language Models (MLLMs) with Chain-of-Thought (CoT) to compose a target image description for retrieval. However, due to the fuzzy matching nature of ZS-CIR, the generated description is prone to semantic bias relative to the target image. We propose SDR-CIR, a training-free Semantic Debias Ranking method based on CoT reasoning. First, Selective CoT guides the MLLM to extract visual content relevant to the modification text during image understanding, thereby reducing visual noise at the source. We then introduce a Semantic Debias Ranking with two steps, Anchor and Debias, to mitigate semantic bias. In the Anchor step, we fuse reference image features with target description features to reinforce useful semantics and supplement omitted cues. In the Debias step, we explicitly model the visual semantic contribution of the reference image to the description and incorporate it into the similarity score as a penalty term. By supplementing omitted cues while suppressing redundancy, SDR-CIR mitigates semantic bias and improves retrieval performance. Experiments on three standard CIR benchmarks show that SDR-CIR achieves state-of-the-art results among one-stage methods while maintaining high efficiency. The code is publicly available at https://github.com/suny105/SDR-CIR.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2149-2159
Open AccessSDR-CIR: Semantic Debias Retrieval Framework for Training-Free Zero-Shot Composed Image Retrieval
Composed Image Retrieval (CIR) aims to retrieve a target image from a query composed of a reference image and modification text. Recent training-free zero-shot methods often employ Multimodal Large Language Models (MLLMs) with Chain-of-Thought (CoT) to compose a target image description for retrieval. However, due to the fuzzy matching nature of ZS-CIR, the generated description is prone to semantic bias relative to the target image. We propose SDR-CIR, a training-free Semantic Debias Ranking method based on CoT reasoning. First, Selective CoT guides the MLLM to extract visual content relevant to the modification text during image understanding, thereby reducing visual noise at the source. We then introduce a Semantic Debias Ranking with two steps, Anchor and Debias, to mitigate semantic bias. In the Anchor step, we fuse reference image features with target description features to reinforce useful semantics and supplement omitted cues. In the Debias step, we explicitly model the visual semantic contribution of the reference image to the description and incorporate it into the similarity score as a penalty term. By supplementing omitted cues while suppressing redundancy, SDR-CIR mitigates semantic bias and improves retrieval performance. Experiments on three standard CIR benchmarks show that SDR-CIR achieves state-of-the-art results among one-stage methods while maintaining high efficiency. The code is publicly available at https://github.com/suny105/SDR-CIR.
- 12 March 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (4) , 201
Enhancing image vectorization fidelity and editability through adaptive layered techniques
- 12 March 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (4) , 201
Enhancing image vectorization fidelity and editability through adaptive layered techniques
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
Enhancing Fine-Grained Sketch-based Image Retrieval through Contextual Information
Fine-grained sketch-based image retrieval aims to retrieve matched natural photos at instance level based on hand-drawn sketches. Understanding sketches and aligning them with photos in the joint embedding space are the primary challenges. Previous works have attempted to improve the understanding and alignment of fine-grained semantics by leveraging a selected subset of local features based on the local matching strategy. However, these approaches rely heavily on local features to capture regional visual details, which introduces unavoidable uncertainty and noise in the matching process. In addition, existing works lack the ability to effectively separate unmatched pairs with similar overall semantics in the common space, which may disrupt fine-grained semantic alignment. In this paper, we present CIGSPA: a Contextual Information Guided Sketch-Photo Alignment framework that leverages latent contextual information to enhance sketch understanding and sketch-photo matching without additional knowledge and prior supervision. Specifically, we first design an Adaptive Local Feature Filter module to refine feature similarity based on the context of local features and select more appropriate features, which ensure the semantic fidelity and spatial compactness of salient features. Secondly, we design a Contextual Weighted Contrastive loss to guide global sketch-photo matching by leveraging discriminative contextual information from photos, and hence aligns the sketch and photo at the instance level. Our comprehensive experiments on six public datasets demonstrate the effectiveness of our proposed CIGSPA. The code is available at https://github.com/jinyuxu-whut/CIGSPA4FG-SBIR.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
Enhancing Fine-Grained Sketch-based Image Retrieval through Contextual Information
Fine-grained sketch-based image retrieval aims to retrieve matched natural photos at instance level based on hand-drawn sketches. Understanding sketches and aligning them with photos in the joint embedding space are the primary challenges. Previous works have attempted to improve the understanding and alignment of fine-grained semantics by leveraging a selected subset of local features based on the local matching strategy. However, these approaches rely heavily on local features to capture regional visual details, which introduces unavoidable uncertainty and noise in the matching process. In addition, existing works lack the ability to effectively separate unmatched pairs with similar overall semantics in the common space, which may disrupt fine-grained semantic alignment. In this paper, we present CIGSPA: a Contextual Information Guided Sketch-Photo Alignment framework that leverages latent contextual information to enhance sketch understanding and sketch-photo matching without additional knowledge and prior supervision. Specifically, we first design an Adaptive Local Feature Filter module to refine feature similarity based on the context of local features and select more appropriate features, which ensure the semantic fidelity and spatial compactness of salient features. Secondly, we design a Contextual Weighted Contrastive loss to guide global sketch-photo matching by leveraging discriminative contextual information from photos, and hence aligns the sketch and photo at the instance level. Our comprehensive experiments on six public datasets demonstrate the effectiveness of our proposed CIGSPA. The code is available at https://github.com/jinyuxu-whut/CIGSPA4FG-SBIR.
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
TOVect: Topology-Optimized Vectorization for Intangible Cultural Heritage Thangka Element Line Art
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessTOVect: Topology-Optimized Vectorization for Intangible Cultural Heritage Thangka Element Line Art
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Robust Dual Embedding Contrastive Learning for Text-to-Image Person Re-identification with Noisy Correspondence
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessRobust Dual Embedding Contrastive Learning for Text-to-Image Person Re-identification with Noisy Correspondence
- Open Access
- 13 October 2025
- Published by Springer Nature in Research Square
Enhancing Image Vectorization Fidelity and Editability through Adaptive Layered Techniques
Image vectorization transforms raster images into scalable vector graphics, offering advantages in resolution independence and compact representation. Traditional and modern machine learning-based methods face challenges in redundancy, structural clarity, computational costs, and editability. To address these, we propose ALIV (Adaptive Layered Image Vectorization), a novel two-step framework combining comprehensive color quantization pretreatment with a machine learning vectorization process. ALIV enhances shape representation through adaptive polygonal primitive initialization and employs structural and curve loss functions to maintain clear boundaries and reduce disordered curves. Our approach achieves high fidelity, superior structural quality, and enhanced editability while maintaining computational efficiency. Experiments demonstrate ALIV's superiority over state-of-the-art methods, significantly reducing computational overhead and ensuring better vectorization results. This work contributes to the field of computer graphics by providing a practical and efficient solution for image vectorization. The source code for ALIV are publicly available at https://github.com/SamEr32/ALIV (DOI:10.5281/zenodo.17311513).
- 13 October 2025
- Published by Springer Nature in Research Square
Open AccessEnhancing Image Vectorization Fidelity and Editability through Adaptive Layered Techniques
Image vectorization transforms raster images into scalable vector graphics, offering advantages in resolution independence and compact representation. Traditional and modern machine learning-based methods face challenges in redundancy, structural clarity, computational costs, and editability. To address these, we propose ALIV (Adaptive Layered Image Vectorization), a novel two-step framework combining comprehensive color quantization pretreatment with a machine learning vectorization process. ALIV enhances shape representation through adaptive polygonal primitive initialization and employs structural and curve loss functions to maintain clear boundaries and reduce disordered curves. Our approach achieves high fidelity, superior structural quality, and enhanced editability while maintaining computational efficiency. Experiments demonstrate ALIV's superiority over state-of-the-art methods, significantly reducing computational overhead and ensuring better vectorization results. This work contributes to the field of computer graphics by providing a practical and efficient solution for image vectorization. The source code for ALIV are publicly available at https://github.com/SamEr32/ALIV (DOI:10.5281/zenodo.17311513).
- 26 July 2025
- Published by Springer Nature
- p. 406-417
PKI-SSM: Prior Knowledge Integrated Self-supervised Model for Point Cloud Completing
- 26 July 2025
- Published by Springer Nature
- p. 406-417
PKI-SSM: Prior Knowledge Integrated Self-supervised Model for Point Cloud Completing