Xuemeng Song
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
Xuemeng Song has a total of 156 co-authors. Here are the top co-authors by number of shared publications:
- Liqiang Nie
Harbin Institute of Technology (Shenzhen), Shenzhen, China
43 shared publications - Weili Guan
Harbin Institute of Technology (Shenzhen), Shenzhen, China
13 shared publications - Yinwei Wei
Shandong University
13 shared publications - Haokun Wen
Harbin Institute of Technology (Shenzhen), Shenzhen, China
12 shared publications - Meng Liu
School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China
12 shared publications - Xiaolin Chen
School of Software, Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University, Jinan, China
8 shared publications
Latest Publications
- Open Access
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44  (8) , 1-36
Prompt-Guided Graph Contrastive Learning with Controllable Augmentation and Fine-Grained Preference Modeling for Recommendation
Graph contrastive learning (GCL) is a promising approach for improving collaborative filtering (CF), especially in sparse interaction settings. Despite their effectiveness, most existing GCL-based recommendation methods risk disrupting meaningful collaborative signals by relying on uncontrollable graph augmentations. Besides, these methods fail to explicitly capture and integrate diverse fine-grained preferences because they model user–item interactions at a coarse level. To address these issues, we propose Prompt-Guided Graph Contrastive Learning (PGCL) , a novel framework that introduces learnable prompt nodes to construct controllable augmented graphs and enable fine-grained preference modeling. Specifically, these prompt nodes serve as latent fine-grained preferences and can be dynamically connected to user and item nodes in the graph based on semantic relevance. With this prompt-guided augmented graph, PGCL then incorporates two modules: the prompt-guided and the interaction-enhanced contrastive learning. The former adaptively aligns users and items with their most semantically relevant prompt nodes, enabling the model to capture and distinguish multi-dimensional preference signals. The latter incorporates real user–item interaction pairs as supervision, mitigating potential bias from prompt semantics and reinforcing collaborative signal learning. Together, these designs enable PGCL to model fine-grained preferences via a more semantically guided augmentation process. Extensive experiments across five public datasets demonstrate that PGCL consistently outperforms state-of-the-art baselines, thereby validating its effectiveness for recommendation tasks.
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44  (8) , 1-36
Open AccessPrompt-Guided Graph Contrastive Learning with Controllable Augmentation and Fine-Grained Preference Modeling for Recommendation
Graph contrastive learning (GCL) is a promising approach for improving collaborative filtering (CF), especially in sparse interaction settings. Despite their effectiveness, most existing GCL-based recommendation methods risk disrupting meaningful collaborative signals by relying on uncontrollable graph augmentations. Besides, these methods fail to explicitly capture and integrate diverse fine-grained preferences because they model user–item interactions at a coarse level. To address these issues, we propose Prompt-Guided Graph Contrastive Learning (PGCL) , a novel framework that introduces learnable prompt nodes to construct controllable augmented graphs and enable fine-grained preference modeling. Specifically, these prompt nodes serve as latent fine-grained preferences and can be dynamically connected to user and item nodes in the graph based on semantic relevance. With this prompt-guided augmented graph, PGCL then incorporates two modules: the prompt-guided and the interaction-enhanced contrastive learning. The former adaptively aligns users and items with their most semantically relevant prompt nodes, enabling the model to capture and distinguish multi-dimensional preference signals. The latter incorporates real user–item interaction pairs as supervision, mitigating potential bias from prompt semantics and reinforcing collaborative signal learning. Together, these designs enable PGCL to model fine-grained preferences via a more semantically guided augmentation process. Extensive experiments across five public datasets demonstrate that PGCL consistently outperforms state-of-the-art baselines, thereby validating its effectiveness for recommendation tasks.
- Open Access
- 8 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (10) , 1-21
MMGRec: Multimodal Generative Recommendation with Transformer Model
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonly employ an embed-and-retrieve paradigm: learning user and item representations in the same embedding space, then retrieving similar candidate items for a user via embedding inner product. However, this paradigm suffers from inference cost, interaction modeling, and false-negative issues. Toward this end, we propose a new MMGRec model to introduce a generative paradigm into multimodal recommendation. Specifically, we first devise a hierarchical quantization method Graph RQ-VAE to assign a Rec-ID for each item from its multimodal and CF information. Consisting of a tuple of semantically meaningful tokens, Rec-ID serves as the unique identifier of each item. Afterward, we train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences. The generative paradigm is qualified since this model systematically predicts the tuple of tokens identifying the recommended item in an autoregressive manner. Moreover, a relation-aware self-attention mechanism is devised for the Transformer to handle non-sequential interaction sequences, which explores the element–pairwise relation to replace absolute positional encoding. Extensive experiments evaluate MMGRec’s effectiveness compared with state-of-the-art methods.
- 8 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (10) , 1-21
Open AccessMMGRec: Multimodal Generative Recommendation with Transformer Model
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonly employ an embed-and-retrieve paradigm: learning user and item representations in the same embedding space, then retrieving similar candidate items for a user via embedding inner product. However, this paradigm suffers from inference cost, interaction modeling, and false-negative issues. Toward this end, we propose a new MMGRec model to introduce a generative paradigm into multimodal recommendation. Specifically, we first devise a hierarchical quantization method Graph RQ-VAE to assign a Rec-ID for each item from its multimodal and CF information. Consisting of a tuple of semantically meaningful tokens, Rec-ID serves as the unique identifier of each item. Afterward, we train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences. The generative paradigm is qualified since this model systematically predicts the tuple of tokens identifying the recommended item in an autoregressive manner. Moreover, a relation-aware self-attention mechanism is devised for the Transformer to handle non-sequential interaction sequences, which explores the element–pairwise relation to replace absolute positional encoding. Extensive experiments evaluate MMGRec’s effectiveness compared with state-of-the-art methods.
- 10 September 2026
- Published by Elsevier in Information Processing & Management
- Vol. 64  (2)
CA2: Context-Adaptive and Consistency-Aware Multi-Modal Outfit Compatibility Modeling
- 10 September 2026
- Published by Elsevier in Information Processing & Management
- Vol. 64  (2)
CA2: Context-Adaptive and Consistency-Aware Multi-Modal Outfit Compatibility Modeling
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 980-990
DA 2 -Unlearn: Dual-Adaptive Forget-Repair-Based Recommendation Unlearning
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 980-990
Open AccessDA 2 -Unlearn: Dual-Adaptive Forget-Repair-Based Recommendation Unlearning
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 532-543
A Non-parametric Multi-view Model for Short Text Clustering
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 532-543
Open AccessA Non-parametric Multi-view Model for Short Text Clustering
- Open Access
- 24 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (7) , 1-23
Dual Alignment-Enhanced Fashion Vision-Language Pre-Training
Fashion vision-language pre-training (VLP) models have demonstrated remarkable capabilities in excelling at a wide range of fashion cross-modal tasks. However, current models still face three notable limitations (1) an inability to discern varying levels of consistency between textual descriptions and multi-view images, (2) a deficiency in explicit fine-grained alignment between images and text, and (3) a lack of specific supervision mechanisms for facilitating global joint embedding learning. To address these limitations, we propose a novel dual alignment-enhanced fashion VLP model. This model delves deeply into the rich resources of multi-view images and semantic attributes associated with each fashion item. Notably, we introduce two novel pre-training tasks: Multi-grained Adaptive Image-Text Alignment (MAITA) and Joint Embedding-oriented Alignment (JEA). MAITA focuses on optimizing the text/image encoder by orchestrating adaptive alignment between multi-view images and input text. This encompasses both coarse-grained and fine-grained alignment strategies to enrich semantic understanding, while JEA is devised to supervise the fine-grained semantic learning process of the global multimodal joint embedding. Experimental results spanning four diverse downstream tasks, including cross-modal retrieval, text-guided image retrieval, category recognition, and subcategory recognition, substantiate the significant performance superiority of our model over prior state-of-the-art fashion VLP models.
- 24 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (7) , 1-23
Open AccessDual Alignment-Enhanced Fashion Vision-Language Pre-Training
Fashion vision-language pre-training (VLP) models have demonstrated remarkable capabilities in excelling at a wide range of fashion cross-modal tasks. However, current models still face three notable limitations (1) an inability to discern varying levels of consistency between textual descriptions and multi-view images, (2) a deficiency in explicit fine-grained alignment between images and text, and (3) a lack of specific supervision mechanisms for facilitating global joint embedding learning. To address these limitations, we propose a novel dual alignment-enhanced fashion VLP model. This model delves deeply into the rich resources of multi-view images and semantic attributes associated with each fashion item. Notably, we introduce two novel pre-training tasks: Multi-grained Adaptive Image-Text Alignment (MAITA) and Joint Embedding-oriented Alignment (JEA). MAITA focuses on optimizing the text/image encoder by orchestrating adaptive alignment between multi-view images and input text. This encompasses both coarse-grained and fine-grained alignment strategies to enrich semantic understanding, while JEA is devised to supervise the fine-grained semantic learning process of the global multimodal joint embedding. Experimental results spanning four diverse downstream tasks, including cross-modal retrieval, text-guided image retrieval, category recognition, and subcategory recognition, substantiate the significant performance superiority of our model over prior state-of-the-art fashion VLP models.
- 22 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 5377-5392
COMBINER: Composed Image Retrieval Guided by Attribute-Based Neighbor Relations
Composed Image Retrieval (CIR) represents a challenging retrieval task that targets locating specific images through multimodal inputs. Despite recent progress in CIR techniques, prior approaches often overlook cases where images appear visually alike yet differ in attributes, potentially undermining both multimodal feature fusion and similarity modeling. To mitigate this limitation, we design a unified representation of cross-modal features based on attribute prototypes. Nevertheless, the task is far from straightforward, owing to three core issues: (1) entangle ment in attribute-level semantics, (2) inconsistency across modalities, and (3) supervised signal missing. To tackle the above obstacles, we introduce a COMposed image retrieval network guided By attrIbute-based NEighbor Relations (COMBINER). Specifically, we first design an Adaptive Semantic Disentanglement module, which is capable of disentangling attribute features based on multimodal primitive features. Secondly, we propose a Unified Prototype-based Composition module, which can construct cross-modal unified prototypes (CUP) and facilitate multimodal feature composition. Finally, we introduce a Dual Relations Modeling module, which can mine pairwise and neighbor relations based on attribute similarity. Compared to traditional neighbor relations modeling CIR methods, COMBINER represents the first study addressing the phenomenon of visually similar but attribute unrelated samples. It achieves a more accurate understanding of the semantic relations among samples by employing an attribute prototype-based similarity metric. Comprehensive experiments conducted on three benchmark datasets confirm the effectiveness of our proposed COMBINER. The implementation of our method will be accessed at https://github.com/Lee-zixu/COMBINER.
- 22 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 5377-5392
COMBINER: Composed Image Retrieval Guided by Attribute-Based Neighbor Relations
Composed Image Retrieval (CIR) represents a challenging retrieval task that targets locating specific images through multimodal inputs. Despite recent progress in CIR techniques, prior approaches often overlook cases where images appear visually alike yet differ in attributes, potentially undermining both multimodal feature fusion and similarity modeling. To mitigate this limitation, we design a unified representation of cross-modal features based on attribute prototypes. Nevertheless, the task is far from straightforward, owing to three core issues: (1) entangle ment in attribute-level semantics, (2) inconsistency across modalities, and (3) supervised signal missing. To tackle the above obstacles, we introduce a COMposed image retrieval network guided By attrIbute-based NEighbor Relations (COMBINER). Specifically, we first design an Adaptive Semantic Disentanglement module, which is capable of disentangling attribute features based on multimodal primitive features. Secondly, we propose a Unified Prototype-based Composition module, which can construct cross-modal unified prototypes (CUP) and facilitate multimodal feature composition. Finally, we introduce a Dual Relations Modeling module, which can mine pairwise and neighbor relations based on attribute similarity. Compared to traditional neighbor relations modeling CIR methods, COMBINER represents the first study addressing the phenomenon of visually similar but attribute unrelated samples. It achieves a more accurate understanding of the semantic relations among samples by employing an attribute prototype-based similarity metric. Comprehensive experiments conducted on three benchmark datasets confirm the effectiveness of our proposed COMBINER. The implementation of our method will be accessed at https://github.com/Lee-zixu/COMBINER.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (10) , 1
Video Corpus Moment Retrieval via Decoupled Multimodal Modeling and Unified Localization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (10) , 1
Video Corpus Moment Retrieval via Decoupled Multimodal Modeling and Unified Localization
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Multi-modal Recommendation with Joint Content and Interaction Augmentation
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessMulti-modal Recommendation with Joint Content and Interaction Augmentation
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44  (1) , 1-54
A Comprehensive Survey on Composed Image Retrieval
Composed Image Retrieval (CIR) is an emerging yet challenging task that allows users to search for target images using a multimodal query, comprising a reference image and a modification text specifying the user’s desired changes to the reference image. Given its significant academic and practical value, CIR has become a rapidly growing area of interest in the computer vision and machine learning communities, particularly with the advances in deep learning. To the best of our knowledge, there is currently no comprehensive review of CIR to provide a timely overview of this field. Therefore, we synthesize insights from over 150 publications in top conferences and journals, including ACM TOIS, SIGIR, and CVPR. In particular, we systematically categorize existing supervised CIR and zero-shot CIR models using a fine-grained taxonomy. For a comprehensive review, we also briefly discuss approaches for tasks closely related to CIR, such as attribute-based CIR and dialog-based CIR. Additionally, we summarize benchmark datasets for evaluation and analyze existing supervised and zero-shot CIR methods by comparing experimental results across multiple datasets. Furthermore, we present promising future directions in this field, offering practical insights for researchers interested in further exploration.
- 14 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44  (1) , 1-54
Open AccessA Comprehensive Survey on Composed Image Retrieval
Composed Image Retrieval (CIR) is an emerging yet challenging task that allows users to search for target images using a multimodal query, comprising a reference image and a modification text specifying the user’s desired changes to the reference image. Given its significant academic and practical value, CIR has become a rapidly growing area of interest in the computer vision and machine learning communities, particularly with the advances in deep learning. To the best of our knowledge, there is currently no comprehensive review of CIR to provide a timely overview of this field. Therefore, we synthesize insights from over 150 publications in top conferences and journals, including ACM TOIS, SIGIR, and CVPR. In particular, we systematically categorize existing supervised CIR and zero-shot CIR models using a fine-grained taxonomy. For a comprehensive review, we also briefly discuss approaches for tasks closely related to CIR, such as attribute-based CIR and dialog-based CIR. Additionally, we summarize benchmark datasets for evaluation and analyze existing supervised and zero-shot CIR methods by comparing experimental results across multiple datasets. Furthermore, we present promising future directions in this field, offering practical insights for researchers interested in further exploration.