Yongjian Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yongjian Liu has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Qing Xie
Wuhan University of Technology, Wuhan, Hubei, China
18 shared publications - Jiachen Li
Wuhan University of Technology, Wuhan, China
10 shared publications - Yanchun Ma
Wuhan Vocational College of Software and Engineering, Wuhan, Hubei, China
9 shared publications - Yuhan Wang
Wuhan University of Technology, Wuhan, Hubei, China
7 shared publications - Jinyu Xu
Wuhan University of Technology, Wuhan, China
6 shared publications - Lin Li
Wuhan University of Technology, Wuhan, China
6 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 173-181
Do We Really Need LLMs to Augment All? A Selective Augmentation Framework with Lightweight Language Models for Multimodal CTR Prediction
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 173-181
Open AccessDo We Really Need LLMs to Augment All? A Selective Augmentation Framework with Lightweight Language Models for Multimodal CTR Prediction
- 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.
- 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
How Does TMT Heterogeneity Affect Firm Digital Innovation Resilience?
In the digital economy era characterized by heightened uncertainty, strengthening internal governance to bolster firm adaptability and sustain digital innovation resilience has become crucial. As a key strategic resource, top management team (TMT) heterogeneity holds significant theoretical and practical value for enhancing firms’ digital innovation resilience. Using a sample of Chinese manufacturing listed firms, this study examines how TMT heterogeneity affects digital innovation resilience and the underlying mechanisms. The findings indicate that: (1) Greater TMT heterogeneity strengthens firms’ digital innovation resilience. (2) This effect operates primarily through alleviating financing constraints and improving investment efficiency. (3) The impact varies across firm types: it is stronger for small and medium-sized firms than for large firms; more pronounced in state-owned firms than in non-state-owned firms; more significant in low-monopoly firms than in high-monopoly firms; and notably greater for firms in eastern China than for those in central and western regions. (4) Government subsidies can strengthen the positive impact of TMT heterogeneity on firm digital innovation resilience. This study provides theoretical insights and practical guidance for enterprises to build effective TMTs, alleviate financing constraints, and improve investment efficiency, and for the government to provide subsidies, with the ultimate aim of fostering digital innovation resilience.
Open AccessHow Does TMT Heterogeneity Affect Firm Digital Innovation Resilience?
In the digital economy era characterized by heightened uncertainty, strengthening internal governance to bolster firm adaptability and sustain digital innovation resilience has become crucial. As a key strategic resource, top management team (TMT) heterogeneity holds significant theoretical and practical value for enhancing firms’ digital innovation resilience. Using a sample of Chinese manufacturing listed firms, this study examines how TMT heterogeneity affects digital innovation resilience and the underlying mechanisms. The findings indicate that: (1) Greater TMT heterogeneity strengthens firms’ digital innovation resilience. (2) This effect operates primarily through alleviating financing constraints and improving investment efficiency. (3) The impact varies across firm types: it is stronger for small and medium-sized firms than for large firms; more pronounced in state-owned firms than in non-state-owned firms; more significant in low-monopoly firms than in high-monopoly firms; and notably greater for firms in eastern China than for those in central and western regions. (4) Government subsidies can strengthen the positive impact of TMT heterogeneity on firm digital innovation resilience. This study provides theoretical insights and practical guidance for enterprises to build effective TMTs, alleviate financing constraints, and improve investment efficiency, and for the government to provide subsidies, with the ultimate aim of fostering digital innovation resilience.
- 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
- 13 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (9) , 1-2
Erratum: A Dual Perspective Framework of Knowledge-correlation for Cross-domain Recommendation
This is an erratum for the article "A Dual Perspective Framework of Knowledge-correlation for Cross-domain Recommendation" published in ACM Trans. Knowl. Discov. Data 18(6): 152:1-152:28 (2024).
- 13 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (9) , 1-2
Open AccessErratum: A Dual Perspective Framework of Knowledge-correlation for Cross-domain Recommendation
This is an erratum for the article "A Dual Perspective Framework of Knowledge-correlation for Cross-domain Recommendation" published in ACM Trans. Knowl. Discov. Data 18(6): 152:1-152:28 (2024).
- Open Access
KGBridge: Knowledge-Guided Prompt Learning for Non-overlapping Cross-Domain Recommendation
Knowledge Graphs (KGs), as structured knowledge bases that organize relational information across diverse domains, provide a unified semantic foundation for cross-domain recommendation (CDR). By integrating symbolic knowledge with user-item interactions, KGs enrich semantic representations, support reasoning, and enhance model interpretability. Despite this potential, existing KG-based methods still face major challenges in CDR, particularly under non-overlapping user scenarios. These challenges arise from: (C1) sensitivity to KG sparsity and popularity bias, (C2) dependence on overlapping users for domain alignment and (C3) lack of explicit disentanglement between transferable and domain-specific knowledge, which limit effective and stable knowledge transfer. To this end, we propose KGBridge, a knowledge-guided prompt learning framework for cross-domain sequential recommendation under non-overlapping user scenarios. KGBridge comprises two core components: a KG-enhanced Prompt Encoder, which models relation-level semantics as soft prompts to provide structured and dynamic priors for user sequence modeling (addressing C1), and a Two-stage Training Paradigm, which combines cross-domain pretraining and privacy-preserving fine-tuning to enable knowledge transfer without user overlap (addressing C2). By combining relation-aware semantic control with correspondence-driven disentanglement, KGBridge explicitly separates and balances domain-shared and domain-specific semantics, thereby maintaining complementarity and stabilizing adaptation during fine-tuning (addressing C3). Extensive experiments on benchmark datasets demonstrate that KGBridge consistently outperforms state-of-the-art baselines and remains robust under varying KG sparsity, highlighting its effectiveness in mitigating structural imbalance and semantic entanglement in KG-enhanced cross-domain recommendation.
Open AccessKGBridge: Knowledge-Guided Prompt Learning for Non-overlapping Cross-Domain Recommendation
Knowledge Graphs (KGs), as structured knowledge bases that organize relational information across diverse domains, provide a unified semantic foundation for cross-domain recommendation (CDR). By integrating symbolic knowledge with user-item interactions, KGs enrich semantic representations, support reasoning, and enhance model interpretability. Despite this potential, existing KG-based methods still face major challenges in CDR, particularly under non-overlapping user scenarios. These challenges arise from: (C1) sensitivity to KG sparsity and popularity bias, (C2) dependence on overlapping users for domain alignment and (C3) lack of explicit disentanglement between transferable and domain-specific knowledge, which limit effective and stable knowledge transfer. To this end, we propose KGBridge, a knowledge-guided prompt learning framework for cross-domain sequential recommendation under non-overlapping user scenarios. KGBridge comprises two core components: a KG-enhanced Prompt Encoder, which models relation-level semantics as soft prompts to provide structured and dynamic priors for user sequence modeling (addressing C1), and a Two-stage Training Paradigm, which combines cross-domain pretraining and privacy-preserving fine-tuning to enable knowledge transfer without user overlap (addressing C2). By combining relation-aware semantic control with correspondence-driven disentanglement, KGBridge explicitly separates and balances domain-shared and domain-specific semantics, thereby maintaining complementarity and stabilizing adaptation during fine-tuning (addressing C3). Extensive experiments on benchmark datasets demonstrate that KGBridge consistently outperforms state-of-the-art baselines and remains robust under varying KG sparsity, highlighting its effectiveness in mitigating structural imbalance and semantic entanglement in KG-enhanced cross-domain recommendation.
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 104-113
Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 104-113
Open AccessEnhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement