Jiachen Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiachen Li has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Qing Xie
Wuhan University of Technology, Wuhan, Hubei, China
17 shared publications - Yanchun Ma
Wuhan Vocational College of Software and Engineering, Wuhan, Hubei, China
13 shared publications - Jinyu Xu
Wuhan University of Technology, Wuhan, China
11 shared publications - Yongjian Liu
Wuhan University of Technology, Wuhan, China
10 shared publications - Wenbo Jiang
School of Computer Science and Engineering (School of Cybersecurity), University of Electronic Science and Technology of China, Chengdu, China
4 shared publications - Anshu Hu
Wuhan University of Technology, Wuhan, China
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.
- Top Cited PapersOpen Access
- 6 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 20 (1)
Guided by Principles of Composition: A Domain‐Specific Priors Based Detector for Recognizing Ritual Implements in Thangka
Detecting ritual implements in Thangka paintings—such as swords and scriptures—remains challenging due to their intricate visual composition and symbolic complexity. Existing object detection models, typically trained on natural scenes, tend to perform poorly in this domain. To address this limitation, we summarize the principles of composition in Thangka and identify key spatial and co‐occurrence priors specific to ritual implements. Based on these insights, we propose GPCDet: a guided by principles of composition detector that integrates domain‐specific priors into the detection process. Specifically, we introduce a spatial coordinate attention module to emphasize critical spatial regions where implements frequently appear. In addition, we design a graph convolution network‐auxiliary detection module to model inter‐category co‐occurrence, thereby enhancing feature representation and improving classification performance. Experiments on the newly curated ritual implements in Thangka (RITK) dataset show that GPCDet achieves substantial improvements over existing methods, establishing a new state‐of‐the‐art baseline for this challenging task.
- 6 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 20 (1)
Top Cited PapersOpen AccessGuided by Principles of Composition: A Domain‐Specific Priors Based Detector for Recognizing Ritual Implements in Thangka
Detecting ritual implements in Thangka paintings—such as swords and scriptures—remains challenging due to their intricate visual composition and symbolic complexity. Existing object detection models, typically trained on natural scenes, tend to perform poorly in this domain. To address this limitation, we summarize the principles of composition in Thangka and identify key spatial and co‐occurrence priors specific to ritual implements. Based on these insights, we propose GPCDet: a guided by principles of composition detector that integrates domain‐specific priors into the detection process. Specifically, we introduce a spatial coordinate attention module to emphasize critical spatial regions where implements frequently appear. In addition, we design a graph convolution network‐auxiliary detection module to model inter‐category co‐occurrence, thereby enhancing feature representation and improving classification performance. Experiments on the newly curated ritual implements in Thangka (RITK) dataset show that GPCDet achieves substantial improvements over existing methods, establishing a new state‐of‐the‐art baseline for this challenging task.
- 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. 1-7
When Hallucinated Concepts Cross Modals: Unveiling Backdoor Vulnerability in Multi-modal In-context Learning
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessWhen Hallucinated Concepts Cross Modals: Unveiling Backdoor Vulnerability in Multi-modal In-context Learning
- 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