International Journal of Computer Vision最新文献

{"title":"OscVision: Oscillator Networks for Low Power Vision Inference","authors":"Wenxiao Cai, Zongru Li, Ali Keshavarzi, Thomas H. Lee","doi":"10.1007/s11263-026-03044-2","DOIUrl":"https://doi.org/10.1007/s11263-026-03044-2","url":null,"abstract":"Low-power computer vision on edge devices is increasingly constrained by the energy floor of von Neumann processors. In this paper, we explore oscillator networks that exhibit properties analogous to those observed in neural systems for efficient computer vision processing. The dynamical oscillator networks properties of timing-based representations and large-scale synchronization are exploited for designing a family of algorithms for coupled-oscillator networks for vision inference. Our formulations for vision tasks are designed to be compatible with CMOS oscillator-based fabrics, where coupled phase dynamics can converge toward low-energy phase-locked states. Based on published oscillator-network hardware demonstrations, such fabrics offer a potential path toward orders-of-magnitude energy reduction compared with conventional von Neumann implementations which motivates this work in evaluating OscVision through software simulations rather than fabricated hardware. We show how to map four representative vision tasks into a unified energy-minimization objectives framework that can be realized by coupled oscillator dynamics. Algorithms for these vision tasks span (a) image denoising, (b) image segmentation, (c) seam-driven image stitching, and (d) Hopfield-style image classification. Furthermore, since practical oscillator fabrics operate with limited phase and weight resolution (2–3 bits), we introduce encoding strategies that represent pixel information jointly through phase, coupling weight, local neighborhood interaction, and auxiliary image attribute to handle 8-bit image inputs. Our formulation instantiates three hardware-motivated oscillator network architectures of (i) locally connected pixel-oscillator grids, (ii) multi-oscillator-per-pixel encodings for higher bit depth, and (iii) sparse global couplings for associative retrieval. Our Kuramoto-dynamics simulations demonstrate competitive accuracy against conventional algorithmic baselines across multiple tasks, while the accompanying energy analysis indicates the potential energy benefits of mapping these workloads to oscillator-based hardware.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"94 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Focus Depth Anything: Towards Robust Depth from Focus in the Wild","authors":"Jiangfeng Zhang, Yuhua Qian, Tao Yan, Shen Hu, Yayu Zhang, Jinwen Liu","doi":"10.1007/s11263-026-03006-8","DOIUrl":"https://doi.org/10.1007/s11263-026-03006-8","url":null,"abstract":"Depth from Focus (DfF) estimates scene depth from multi-focus images. However, continuous depth is observed only through discrete focus responses, yielding an ill-posed inverse problem with multiple plausible solutions. Existing DfF methods mainly improve the accuracy of focus measurements, yet rarely address the discretization-induced ambiguity when mapping local focus responses back to continuous depth, which limits robustness in the wild. Therefore, we introduce Focus Depth Anything (FDA), a Bayesian-inspired posterior-refinement framework. Specifically, FDA treats a pretrained depth estimation foundation model as a strong depth prior and leverages multi-focus consistency as physics-grounded cues to locally correct this prior, thereby suppressing spurious solutions that fit the discrete focus cues equally well. To make the posterior correction sensitive to subtle focus variations, we propose the Semantic–Focus Disentanglement (SFD) module, which disentangles focus and semantic representations and produces multi-focus consistency residuals. Moreover, to reinforce the coupling between the depth prior and focus responses, we develop a physically based Point Spread Function (PSF) simulator that generates large-scale multi-focus images to effectively support model learning. Extensive experiments demonstrate that FDA achieves robust depth estimation in the wild, consistently outperforming existing DfF methods. The code and dataset are available at <ext-link ext-link-type=\"uri\" xlink:href=\"https://github.com/jiangfeng-Z/Focus-Depth-Anything\">https://github.com/jiangfeng-Z/Focus-Depth-Anything</ext-link>.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"26 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models","authors":"Xucong Wang, Pengkun Wang, Zhe Zhao, Liheng Yu, Yang Wang","doi":"10.1007/s11263-026-03013-9","DOIUrl":"https://doi.org/10.1007/s11263-026-03013-9","url":null,"abstract":"Prompt Learning (PL) has sparked growing interest as an efficient method for adapting large Vision-Language Models (VLMs) to downstream tasks. While most existing PL methods are designed for (nearly) balanced data, real-world datasets always exhibit a long-tailed distribution, which necessitates the design of PL methods specifically for imbalanced scenarios. This paper introduces our LAMP framework to enable VLMs better to learn from the long-tailed base classes and achieve non-biased predictions for both base and new classes. LAMP is integrated into specific intermediate layers of the frozen VLM, where for each layer we introduce three co-designed mechanisms: Multi-modal Prompt Pool (MPP), Modality-Shared Prompts (MSP) and Load Balancing Optimization (LBO). MPP is motivated by the goal of boosting feature clustering to foster the mutual learning of head and tail classes, in which we introduce separated multi-modal prompts that are dynamically combined into the model via similarity metrics. In addition to the prompts retrieved by MPP, we introduce globally shared MSPs to better adapt to cross-modal semantics and enhance the training robustness. Furthermore, to promote tight and discernible feature clustering via prompts, we treat each prompt as an expert and adopt a load-balancing technique from mixture-of-experts in LLMs, named LBO. LBO dynamically adjusts attention weights with an externally optimized bias, thereby making the activation of each prompt more evenly distributed and preventing the overfitting of head classes. Extensive experiments under various long-tailed settings demonstrate that our LAMP consistently outperforms other state-of-the-art methods.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"94 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unveiling Representation Expansion: A New Lens on Out-of-Distribution Detection","authors":"Boxuan Zhang, Jianing Zhu, Zengmao Wang, Tongliang Liu, Bo Du, Bo Han","doi":"10.1007/s11263-026-03036-2","DOIUrl":"https://doi.org/10.1007/s11263-026-03036-2","url":null,"abstract":"Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes during inference, which ensures the reliable deployment of machine learning models in the open world scenario. It shows promising results with various advanced scoring functions for estimating model uncertainty to distinguish OOD data from in-distribution (ID) data. However, existing methods mainly focus on excavating such discriminative information from the model based on a single input, which implicitly limits the expressiveness of the differences between OOD and ID data, leading some overconfident OOD inputs still being falsely detected. In this paper, we introduce a novel perspective to address the pessimism, i.e., <italic>exploring representation expansion</italic> for OOD detection. Firstly, we present data-level expansion by employing different common corruptions in the input space. Compared with the original data, we reveal an intriguing phenomenon termed <italic>confidence mutation</italic>, where the confidence of OOD data can decrease significantly under the corruption, while ID data show a higher confidence expectation regarding the resistance of semantic features. It uncovers the distinguishable information through the generalization of model knowledge on both data. Based on the observation, we formalize a new scoring method, namely, <bold><italic>Co</italic></bold><italic>nfidence a</italic><bold><italic>Ver</italic></bold><italic>age</italic> (CoVer), which can capture the dynamic differences by simply averaging the scores obtained from different input variants. Secondly, we consider model-level expansion by feeding the inputs to different well-trained models. Even with the same training data, the different backbones further enlarge the discrepancy of the OOD and ID ones with the same dynamic differences, then we extend the overall scoring framework to <italic>CoVer+</italic> with multiple expansion levels for the OOD detection task. Extensive experiments and analyses have been conducted to verify the effectiveness of our proposed methods.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"11 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149086486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion Model-Based Video Editing: A Survey","authors":"Wenhao Sun, Rong-Cheng Tu, Jingyi Liao, Dacheng Tao","doi":"10.1007/s11263-026-03040-6","DOIUrl":"https://doi.org/10.1007/s11263-026-03040-6","url":null,"abstract":"The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making \"what you want is what you see\" a reality. Among these, video editing has gained substantial attention and seen a swift rise in research activity, necessitating a comprehensive and systematic review of the existing literature. This paper reviews diffusion model-based video editing techniques, including theoretical foundations and practical applications. We begin by overviewing the mathematical formulation and image domain’s key methods. Subsequently, we categorize video editing approaches by the inherent connections of their core technologies, depicting evolutionary trajectory. This paper also dives into novel applications, including point-based and pose-guided human video editing. Additionally, we present a comprehensive comparison using our newly introduced V2VBench. Building on the progress achieved to date, the paper concludes with ongoing challenges and potential directions for future research. A project related to this paper can be found at <ext-link ext-link-type=\"uri\" xlink:href=\"https://github.com/wenhao728/awesome-diffusion-v2v\">https://github.com/wenhao728/awesome-diffusion-v2v</ext-link>.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"207 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NeuraLeaf: Disentangled Neural Parametric Modeling of Leaf Shape, Deformation, and Appearance","authors":"Yang Yang, Risa Shinoda, Hiroaki Santo, Yasuyuki Matsushita, Fumio Okura","doi":"10.1007/s11263-026-03024-6","DOIUrl":"https://doi.org/10.1007/s11263-026-03024-6","url":null,"abstract":"We develop a neural parametric model of 3D leaves for plant modeling and reconstruction that are essential for agriculture and computer graphics. While neural parametric models are actively studied for humans and animals, plant leaves present unique challenges due to their thin surface geometry and flexible deformation. To address this problem, we introduce a neural parametric model for leaves, NeuraLeaf. Capitalizing on the fact that flattened leaf shapes can be approximated as a 2D plane, NeuraLeaf disentangles the leaves’ geometry into their 2D base shapes (i.e., flattened leaves) and 3D deformations. This representation allows learning from rich sources of 2D leaf image datasets for the base shapes, and also has the advantage of simultaneously learning textures aligned with the geometry. To obtain a disentangled and controllable appearance space, NeuraLeaf also introduces a learnable appearance space with self-supervised objectives, enabling both appearance fitting to observations and appearance-conditioned texture generation. To model the 3D deformation, we propose a novel skeleton-free skinning model and create a newly captured 3D leaf dataset called DeformLeaf. We demonstrate that NeuraLeaf successfully generates a diverse range of leaf shapes with high-fidelity appearance and deformation, resulting in accurate model fitting to RGB-D observations. Our implementation is available at <ext-link ext-link-type=\"uri\" xlink:href=\"https://github.com/Yrainy0615/NeuraLeaf-APP\">https://github.com/Yrainy0615/NeuraLeaf-APP</ext-link>.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"29 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IterRF: Iterative and Interpretable Mutual Enhancement for Joint Multi-Modal Image Registration and Fusion","authors":"Han Xu, Jiajun Chen, Xunpeng Yi, Peili Li, Jiayi Ma","doi":"10.1007/s11263-026-03043-3","DOIUrl":"https://doi.org/10.1007/s11263-026-03043-3","url":null,"abstract":"Unaligned multi-modal image fusion necessitates addressing the optimization problems of registration and fusion in tandem. Existing methods employ a cascaded “register-then-fuse” pipeline without enhancement or optimize two tasks in isolation with only single-step feedback. These decoupled structures hinder the synergistic co-optimization necessary to drive both tasks toward the global optimum. To address this challenge, we propose IterRF, an iterative mutual enhancement framework for joint multi-modal image registration and fusion based on an optimization-interpretable unfolding network. It first tackles two tasks within a unified optimization formulation, facilitating a joint and co-optimization of both tasks. The unified formulation is then unfolded into alternating registration- and fusion-related subproblems and solved iteratively for bidirectional iterative enhancement, thereby ensuring convergence toward a better joint solution. For the solution of subproblems, we design a fusion-driven registration network for progressive alignment under fused guidance, an iterative unfolding fusion network for high-fidelity fusion while facilitating subsequent registration refinement, and an adaptive weight estimation network for scene-specific fusion matrices. Experiments validate that IterRF achieves superior registration and fusion performances across multiple datasets and generalizes effectively to real-world scenarios. The code is publicly available at <ext-link ext-link-type=\"uri\" xlink:href=\"https://github.com/ChenDoubleJ/IterRF\">https://github.com/ChenDoubleJ/IterRF</ext-link>.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"4 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching","authors":"Xin Xu, Shuhao Zhan, Wei Liu, Zheng Wang, Kui Jiang, Chia-Wen Lin","doi":"10.1007/s11263-026-03016-6","DOIUrl":"https://doi.org/10.1007/s11263-026-03016-6","url":null,"abstract":"Visible-Infrared Person Re-Identification (VI-ReID) conventionally operates under a closed-world assumption, where queries and galleries are from heterogeneous modalities. However, in open-world scenarios, both sets are likely to contain a mixture of homogeneous and heterogeneous modality images. A query may consist of visible-only, infrared-only, or mixed-modality images, while galleries present multi-modal images over long-term collection. Under these conditions, existing VI-ReID methods, built on a heterogeneous-modality retrieval paradigm, suffer from three trustworthiness challenges: matching conflicts due to high homogeneous-modality similarity, interference from modality uncertainty, and robustness degradation induced by unknown modality combinations. Consequently, they fail to meet the requirements of trustworthy visual recognition in reliability, consistency, and dynamic adaptability. To address these challenges, we formalize the Visible-Infrared Modality-Incomplete Re-Identification (VIMI-ReID) task. We reorganize existing datasets to construct the SYSU-VIMI and RegDB-VIMI benchmarks for evaluation. The unpredictable modality combinations and inherent similarity of homogeneous-modality samples in VIMI-ReID cause a significant performance drop in existing VI-ReID methods. To this end, we propose the Modality Adaptive Matching Transformer (MAMT). It employs a Divergence Transformer Module (DTM) and a Shared Transformer Module (STM) to extract modality-specific and modality-shared features, respectively. Guided by a divergence loss, the DTM enriches modality-specific features with modality-style information to enhance discriminability within the same modality. Meanwhile, a Modality Adaptive Matching Module (MAM) dynamically fuses features according to the query-gallery modality relationship, enabling stable matching under arbitrary and uncertain modality conditions. Extensive experiments on the VIMI benchmarks demonstrate the effectiveness and adaptability of MAMT.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"47 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MICTracker: Modality Informativeness Controlled Multi-modal Fusion for Adaptive RGB-D Visual Tracking","authors":"Xuefeng Zhu, Tianyang Xu, Yifan Pan, Xiao-Jun Wu, Josef Kittler","doi":"10.1007/s11263-026-03048-y","DOIUrl":"https://doi.org/10.1007/s11263-026-03048-y","url":null,"abstract":"In multi-modal vision studies, depth channels have complemented the representation capacity of RGB signals with extended spatial awareness, which has led to dedicated research in the RGB-D tracking field. In general, to reflect the information conveyed by the depth modality, the most essential topic for RGB-D tracking is how to perform multi-modal fusion. Current solutions employ elaborate fusion modules to model the interactions between RGB and depth channels in a fixed manner. These approaches tend to default to involving the depth modality in tracking every single frame. However, the utility and complementarity of the depth channel with respect to RGB vary across scenarios. To address this, we propose a modality informativeness controlled RGB-D tracking (MICTracker) framework that enables adaptive fusion via performing depth data quality assessment. Specifically, we design a tracking gain prediction framework to measure the depth channel quality given an RGB-D image pair. To enable the training of our framework, we measure the difference between the losses obtained by forward-passing RGB-only and RGB-D inputs through our RGB-D tracker. After quantifying such difference in terms of tracking gain, we can train our predictor, which then controls the fusion of the depth channel with RGB signals in the test phase. Explicitly equipped with the tracking gain prediction framework, an evidential RGB-D tracker is constructed with improved interpretability when performing RGB-D fusion. Extensive experimental results on standard benchmarking datasets, which outperform the state-of-the-art RGB-D trackers, demonstrate the merits of our MICTracker.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"14 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Source-Free Domain Adaptation with Vision-Language Prior","authors":"Song Tang, Yunxiang Bai, Wenxin Su, Mao Ye, Jianwei Zhang, Xiatian Zhu","doi":"10.1007/s11263-026-03023-7","DOIUrl":"https://doi.org/10.1007/s11263-026-03023-7","url":null,"abstract":"Source-Free Domain Adaptation (SFDA) seeks to adapt a source model, which is pre-trained on a supervised source domain, for a target domain, with only access to unlabeled target training data. Relying on pseudo labeling and/or auxiliary supervision, conventional methods are inevitably error-prone. To mitigate this limitation, in this work we for the first time explore the potentials of off-the-shelf vision-language (ViL) multimodal models (e.g., CLIP) with rich whilst heterogeneous knowledge. We find that directly applying the ViL model to the target domain in a zero-shot fashion is unsatisfactory, as it is not specialized for this particular task but largely generic. To make it task-specific, we propose a novel DIFO++ approach. Specifically, DIFO++ alternates between two steps during adaptation: (i) Customizing the ViL model by maximizing the mutual information with the target model in a prompt learning manner, (ii) Distilling the knowledge of this customized ViL model to the target model, centering on gap region reduction. During progressive knowledge adaptation, we first identify and focus on the gap region, where enclosed features are entangled and class-ambiguous, as it often captures richer task-specific semantics. Reliable pseudo-labels are then generated by fusing predictions from the target and ViL models, supported by a memory mechanism. Finally, gap region reduction is guided by category attention and predictive consistency for semantic alignment, complemented by referenced entropy minimization to suppress uncertainty. Extensive experiments show that DIFO++ significantly outperforms the state-of-the-art alternatives. Our code and data are available at <ext-link ext-link-type=\"uri\" xlink:href=\"https://github.com/tntek/DIFO-Plus\">https://github.com/tntek/DIFO-Plus</ext-link>.","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"2 1","pages":""},"PeriodicalIF":19.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}