JXJinyu Xu

Jinyu Xu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jinyu Xu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Sketch+Text Composed Image Retrieval Dataset for Thangka

    by Jinyu Xu, Yi Sun, Jiangling Zhang, Qing Xie, Daomin Ji, Zhifeng Bao, Jiachen Li, Yanchun Ma, Yongjian Liu

  • Open Access

    Relation-Aware Proxy Hashing for Cross-Modal Retrieval

    by Jinyu Xu, Qing Xie, Jiachen Li, Yanchun Ma, Yongjian Liu, Zhifeng Bao

    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

    SDR-CIR: Semantic Debias Retrieval Framework for Training-Free Zero-Shot Composed Image Retrieval

    by Yi Sun, Jinyu Xu, Qing Xie, Jiachen Li, Yanchun Ma, Yongjian Liu

    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.


  • Enhancing image vectorization fidelity and editability through adaptive layered techniques

    by Qing Xie, Guixiang Nie, Anshu Hu, Yanchun Ma, Jinyu Xu, Jiachen Li


  • Enhancing Fine-Grained Sketch-based Image Retrieval through Contextual Information

    by Jinyu Xu, Qing Xie, Jiachen Li, Zhifeng Bao, Yanchun Ma, Yongjian Liu

    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

    Enhancing Image Vectorization Fidelity and Editability through Adaptive Layered Techniques

    by Guixiang Nie, Qing Xie, Anshu Hu, Yanchun Ma, Jiachen Li, Jinyu Xu

    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).

  • Open Access

    Dlpp-Net: Degradation Location Prior Prediction Network for Image Restoration

    by Yongjian Liu, Shunwei Zhang, Jinyu Xu, Jiachen Li, Yanchun Ma, Qing Xie


  • Open Access

    Mutually-Guided Hierarchical Multi-Modal Feature Learning for Referring Image Segmentation

    by Jiachen Li, Qing Xie, Xiaojun Chang, Jinyu Xu, Yongjian Liu

    Referring image segmentation aims to locate and segment the target region based on a given textual expression query. The primary challenge is to understand semantics from visual and textual modalities and achieve alignment and matching. Prior works have attempted to address this challenge by leveraging separately pretrained unimodal models to extract global visual and textual features and perform straightforward fusion to establish cross-modal semantic associations. However, these methods often concentrate solely on the global semantics, disregarding the hierarchical semantics of expression and image and struggling with complex and open real scenarios, thus failing to capture critical cross-modal information. To address these limitations, this article introduces an innovative mutually-guided hierarchical multi-modal feature learning scheme. By leveraging the guidance of global visual features, the model mines hierarchical text features from different stages of the text encoder. Simultaneously, the guidance of global textual features is leveraged to aggregate multi-scale visual features. This mutually guided hierarchical feature learning effectively addresses the semantically inaccurate cause by free-form text and naturally occurring scale variations. Furthermore, a Segment Detail Refinement (SDR) module is designed to enhance the model’s spatial detail awareness through attention mapping of low-level visual features and cross-modal features. To evaluate the effectiveness of the proposed approach, extensive experiments are conducted on three widely used referring image object segmentation datasets. The results demonstrate the superiority of the presented method in accurately locating and segmenting objects in images.