Pub Date : 2022-07-05DOI: 10.48550/arXiv.2207.02182
J. Baik, In Young Yoon, J. Choi
Modern deep learning has achieved great success in various fields. However, it requires the labeling of huge amounts of data, which is expensive and labor-intensive. Active learning (AL), which identifies the most informative samples to be labeled, is becoming increasingly important to maximize the efficiency of the training process. The existing AL methods mostly use only a single final fixed model for acquiring the samples to be labeled. This strategy may not be good enough in that the structural uncertainty of a model for given training data is not considered to acquire the samples. In this study, we propose a novel acquisition criterion based on temporal self-ensemble generated by conventional stochastic gradient descent (SGD) optimization. These self-ensemble models are obtained by capturing the intermediate network weights obtained through SGD iterations. Our acquisition function relies on a consistency measure between the student and teacher models. The student models are given a fixed number of temporal self-ensemble models, and the teacher model is constructed by averaging the weights of the student models. Using the proposed acquisition criterion, we present an AL algorithm, namely student-teacher consistency-based AL (ST-CoNAL). Experiments conducted for image classification tasks on CIFAR-10, CIFAR-100, Caltech-256, and Tiny ImageNet datasets demonstrate that the proposed ST-CoNAL achieves significantly better performance than the existing acquisition methods. Furthermore, extensive experiments show the robustness and effectiveness of our methods.
{"title":"ST-CoNAL: Consistency-Based Acquisition Criterion Using Temporal Self-Ensemble for Active Learning","authors":"J. Baik, In Young Yoon, J. Choi","doi":"10.48550/arXiv.2207.02182","DOIUrl":"https://doi.org/10.48550/arXiv.2207.02182","url":null,"abstract":"Modern deep learning has achieved great success in various fields. However, it requires the labeling of huge amounts of data, which is expensive and labor-intensive. Active learning (AL), which identifies the most informative samples to be labeled, is becoming increasingly important to maximize the efficiency of the training process. The existing AL methods mostly use only a single final fixed model for acquiring the samples to be labeled. This strategy may not be good enough in that the structural uncertainty of a model for given training data is not considered to acquire the samples. In this study, we propose a novel acquisition criterion based on temporal self-ensemble generated by conventional stochastic gradient descent (SGD) optimization. These self-ensemble models are obtained by capturing the intermediate network weights obtained through SGD iterations. Our acquisition function relies on a consistency measure between the student and teacher models. The student models are given a fixed number of temporal self-ensemble models, and the teacher model is constructed by averaging the weights of the student models. Using the proposed acquisition criterion, we present an AL algorithm, namely student-teacher consistency-based AL (ST-CoNAL). Experiments conducted for image classification tasks on CIFAR-10, CIFAR-100, Caltech-256, and Tiny ImageNet datasets demonstrate that the proposed ST-CoNAL achieves significantly better performance than the existing acquisition methods. Furthermore, extensive experiments show the robustness and effectiveness of our methods.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83987885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and unseen actions and intend to directly learn a mapping from a visual space to the semantic space. This approach has been challenged by the semantic gap between the visual space and semantic space. This paper presents a novel method that uses object semantics as privileged information to narrow the semantic gap and, hence, effectively, assist the learning. In particular, a simple hallucination network is proposed to implicitly extract object semantics during testing without explicitly extracting objects and a cross-attention module is developed to augment visual feature with the object semantics. Experiments on the Olympic Sports, HMDB51 and UCF101 datasets have shown that the proposed method outperforms the state-of-the-art methods by a large margin.
{"title":"Learning Using Privileged Information for Zero-Shot Action Recognition","authors":"Zhiyi Gao, Wanqing Li, Zihui Guo, Ting Yu, Yonghong Hou","doi":"10.48550/arXiv.2206.08632","DOIUrl":"https://doi.org/10.48550/arXiv.2206.08632","url":null,"abstract":"Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and unseen actions and intend to directly learn a mapping from a visual space to the semantic space. This approach has been challenged by the semantic gap between the visual space and semantic space. This paper presents a novel method that uses object semantics as privileged information to narrow the semantic gap and, hence, effectively, assist the learning. In particular, a simple hallucination network is proposed to implicitly extract object semantics during testing without explicitly extracting objects and a cross-attention module is developed to augment visual feature with the object semantics. Experiments on the Olympic Sports, HMDB51 and UCF101 datasets have shown that the proposed method outperforms the state-of-the-art methods by a large margin.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82891807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-29DOI: 10.48550/arXiv.2205.14575
L. Tiong, Dick Sigmund, A. Teoh
Recently, the transformer model has been successfully employed for the multi-view 3D reconstruction problem. However, challenges remain on designing an attention mechanism to explore the multiview features and exploit their relations for reinforcing the encoding-decoding modules. This paper proposes a new model, namely 3D coarse-to-fine transformer (3D-C2FT), by introducing a novel coarse-to-fine(C2F) attention mechanism for encoding multi-view features and rectifying defective 3D objects. C2F attention mechanism enables the model to learn multi-view information flow and synthesize 3D surface correction in a coarse to fine-grained manner. The proposed model is evaluated by ShapeNet and Multi-view Real-life datasets. Experimental results show that 3D-C2FT achieves notable results and outperforms several competing models on these datasets.
{"title":"3D-C2FT: Coarse-to-fine Transformer for Multi-view 3D Reconstruction","authors":"L. Tiong, Dick Sigmund, A. Teoh","doi":"10.48550/arXiv.2205.14575","DOIUrl":"https://doi.org/10.48550/arXiv.2205.14575","url":null,"abstract":"Recently, the transformer model has been successfully employed for the multi-view 3D reconstruction problem. However, challenges remain on designing an attention mechanism to explore the multiview features and exploit their relations for reinforcing the encoding-decoding modules. This paper proposes a new model, namely 3D coarse-to-fine transformer (3D-C2FT), by introducing a novel coarse-to-fine(C2F) attention mechanism for encoding multi-view features and rectifying defective 3D objects. C2F attention mechanism enables the model to learn multi-view information flow and synthesize 3D surface correction in a coarse to fine-grained manner. The proposed model is evaluated by ShapeNet and Multi-view Real-life datasets. Experimental results show that 3D-C2FT achieves notable results and outperforms several competing models on these datasets.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74834622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-27DOI: 10.48550/arXiv.2205.14212
Viresh Ranjan, Minh Hoai
We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a fully automated setting, and require computationally expensive test time adaptation. To address these challenges, we propose a visual counter which operates in a fully automated setting and does not require any test time adaptation. Our proposed approach first identifies exemplars from repeating objects in an image, and then counts the repeating objects. We propose a novel region proposal network for identifying the exemplars. After identifying the exemplars, we obtain the corresponding count by using a density estimation based Visual Counter. We evaluate our proposed approach on FSC-147 dataset, and show that it achieves superior performance compared to the existing approaches.
{"title":"Exemplar Free Class Agnostic Counting","authors":"Viresh Ranjan, Minh Hoai","doi":"10.48550/arXiv.2205.14212","DOIUrl":"https://doi.org/10.48550/arXiv.2205.14212","url":null,"abstract":"We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a fully automated setting, and require computationally expensive test time adaptation. To address these challenges, we propose a visual counter which operates in a fully automated setting and does not require any test time adaptation. Our proposed approach first identifies exemplars from repeating objects in an image, and then counts the repeating objects. We propose a novel region proposal network for identifying the exemplars. After identifying the exemplars, we obtain the corresponding count by using a density estimation based Visual Counter. We evaluate our proposed approach on FSC-147 dataset, and show that it achieves superior performance compared to the existing approaches.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86472185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-25DOI: 10.48550/arXiv.2205.12564
Jiaxin Wei, Lige Liu, Ran Cheng, W. Jiang, Minghao Xu, Xinyu Jiang, Tao Sun, S. Schwertfeger, L. Kneip
Recent years have witnessed the surge of learned representations that directly build upon point clouds. Though becoming increasingly expressive, most existing representations still struggle to generate ordered point sets. Inspired by spherical multi-view scanners, we propose a novel sampling model called Spotlights to represent a 3D shape as a compact 1D array of depth values. It simulates the configuration of cameras evenly distributed on a sphere, where each virtual camera casts light rays from its principal point through sample points on a small concentric spherical cap to probe for the possible intersections with the object surrounded by the sphere. The structured point cloud is hence given implicitly as a function of depths. We provide a detailed geometric analysis of this new sampling scheme and prove its effectiveness in the context of the point cloud completion task. Experimental results on both synthetic and real data demonstrate that our method achieves competitive accuracy and consistency while having a significantly reduced computational cost. Furthermore, we show superior performance on the downstream point cloud registration task over state-of-the-art completion methods.
{"title":"Spotlights: Probing Shapes from Spherical Viewpoints","authors":"Jiaxin Wei, Lige Liu, Ran Cheng, W. Jiang, Minghao Xu, Xinyu Jiang, Tao Sun, S. Schwertfeger, L. Kneip","doi":"10.48550/arXiv.2205.12564","DOIUrl":"https://doi.org/10.48550/arXiv.2205.12564","url":null,"abstract":"Recent years have witnessed the surge of learned representations that directly build upon point clouds. Though becoming increasingly expressive, most existing representations still struggle to generate ordered point sets. Inspired by spherical multi-view scanners, we propose a novel sampling model called Spotlights to represent a 3D shape as a compact 1D array of depth values. It simulates the configuration of cameras evenly distributed on a sphere, where each virtual camera casts light rays from its principal point through sample points on a small concentric spherical cap to probe for the possible intersections with the object surrounded by the sphere. The structured point cloud is hence given implicitly as a function of depths. We provide a detailed geometric analysis of this new sampling scheme and prove its effectiveness in the context of the point cloud completion task. Experimental results on both synthetic and real data demonstrate that our method achieves competitive accuracy and consistency while having a significantly reduced computational cost. Furthermore, we show superior performance on the downstream point cloud registration task over state-of-the-art completion methods.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82306037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To further reduce the cost of semi-supervised domain adaptation (SSDA) labeling, a more effective way is to use active learning (AL) to annotate a selected subset with specific properties. However, domain adaptation tasks are always addressed in two interactive aspects: domain transfer and the enhancement of discrimination, which requires the selected data to be both uncertain under the model and diverse in feature space. Contrary to active learning in classification tasks, it is usually challenging to select pixels that contain both the above properties in segmentation tasks, leading to the complex design of pixel selection strategy. To address such an issue, we propose a novel Active Domain Adaptation scheme with Multi-level Contrastive Units (ADA-MCU) for semantic image segmentation. A simple pixel selection strategy followed with the construction of multi-level contrastive units is introduced to optimize the model for both domain adaptation and active supervised learning. In practice, MCUs are constructed from intra-image, cross-image, and cross-domain levels by using both labeled and unlabeled pixels. At each level, we define contrastive losses from center-to-center and pixel-to-pixel manners, with the aim of jointly aligning the category centers and reducing outliers near the decision boundaries. In addition, we also introduce a categories correlation matrix to implicitly describe the relationship between categories, which are used to adjust the weights of the losses for MCUs. Extensive experimental results on standard benchmarks show that the proposed method achieves competitive performance against state-of-the-art SSDA methods with 50% fewer labeled pixels and significantly outperforms state-of-the-art with a large margin by using the same level of annotation cost.
{"title":"Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation","authors":"Hao Zhang, Ruimao Zhang, Zhanglin Peng, Junle Wang, Yanqing Jing","doi":"10.48550/arXiv.2205.11192","DOIUrl":"https://doi.org/10.48550/arXiv.2205.11192","url":null,"abstract":"To further reduce the cost of semi-supervised domain adaptation (SSDA) labeling, a more effective way is to use active learning (AL) to annotate a selected subset with specific properties. However, domain adaptation tasks are always addressed in two interactive aspects: domain transfer and the enhancement of discrimination, which requires the selected data to be both uncertain under the model and diverse in feature space. Contrary to active learning in classification tasks, it is usually challenging to select pixels that contain both the above properties in segmentation tasks, leading to the complex design of pixel selection strategy. To address such an issue, we propose a novel Active Domain Adaptation scheme with Multi-level Contrastive Units (ADA-MCU) for semantic image segmentation. A simple pixel selection strategy followed with the construction of multi-level contrastive units is introduced to optimize the model for both domain adaptation and active supervised learning. In practice, MCUs are constructed from intra-image, cross-image, and cross-domain levels by using both labeled and unlabeled pixels. At each level, we define contrastive losses from center-to-center and pixel-to-pixel manners, with the aim of jointly aligning the category centers and reducing outliers near the decision boundaries. In addition, we also introduce a categories correlation matrix to implicitly describe the relationship between categories, which are used to adjust the weights of the losses for MCUs. Extensive experimental results on standard benchmarks show that the proposed method achieves competitive performance against state-of-the-art SSDA methods with 50% fewer labeled pixels and significantly outperforms state-of-the-art with a large margin by using the same level of annotation cost.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77501476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-11DOI: 10.48550/arXiv.2205.08585
Ruibo Shi, Lili Tao, Rohan Saphal, Fran Silavong, S. Moran
We present CV4Code, a compact and effective computer vision method for sourcecode understanding. Our method leverages the contextual and the structural information available from the code snippet by treating each snippet as a two-dimensional image, which naturally encodes the context and retains the underlying structural information through an explicit spatial representation. To codify snippets as images, we propose an ASCII codepoint-based image representation that facilitates fast generation of sourcecode images and eliminates redundancy in the encoding that would arise from an RGB pixel representation. Furthermore, as sourcecode is treated as images, neither lexical analysis (tokenisation) nor syntax tree parsing is required, which makes the proposed method agnostic to any particular programming language and lightweight from the application pipeline point of view. CV4Code can even featurise syntactically incorrect code which is not possible from methods that depend on the Abstract Syntax Tree (AST). We demonstrate the effectiveness of CV4Code by learning Convolutional and Transformer networks to predict the functional task, i.e. the problem it solves, of the source code directly from its two-dimensional representation, and using an embedding from its latent space to derive a similarity score of two code snippets in a retrieval setup. Experimental results show that our approach achieves state-of-the-art performance in comparison to other methods with the same task and data configurations. For the first time we show the benefits of treating sourcecode understanding as a form of image processing task.
{"title":"CV4Code: Sourcecode Understanding via Visual Code Representations","authors":"Ruibo Shi, Lili Tao, Rohan Saphal, Fran Silavong, S. Moran","doi":"10.48550/arXiv.2205.08585","DOIUrl":"https://doi.org/10.48550/arXiv.2205.08585","url":null,"abstract":"We present CV4Code, a compact and effective computer vision method for sourcecode understanding. Our method leverages the contextual and the structural information available from the code snippet by treating each snippet as a two-dimensional image, which naturally encodes the context and retains the underlying structural information through an explicit spatial representation. To codify snippets as images, we propose an ASCII codepoint-based image representation that facilitates fast generation of sourcecode images and eliminates redundancy in the encoding that would arise from an RGB pixel representation. Furthermore, as sourcecode is treated as images, neither lexical analysis (tokenisation) nor syntax tree parsing is required, which makes the proposed method agnostic to any particular programming language and lightweight from the application pipeline point of view. CV4Code can even featurise syntactically incorrect code which is not possible from methods that depend on the Abstract Syntax Tree (AST). We demonstrate the effectiveness of CV4Code by learning Convolutional and Transformer networks to predict the functional task, i.e. the problem it solves, of the source code directly from its two-dimensional representation, and using an embedding from its latent space to derive a similarity score of two code snippets in a retrieval setup. Experimental results show that our approach achieves state-of-the-art performance in comparison to other methods with the same task and data configurations. For the first time we show the benefits of treating sourcecode understanding as a form of image processing task.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80523458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-29DOI: 10.48550/arXiv.2203.15636
Guillaume Jeanneret, Loïc Simon, F. Jurie
Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable. In this paper, we propose DiME, a method allowing the generation of counterfactual images using the recent diffusion models. By leveraging the guided generative diffusion process, our proposed methodology shows how to use the gradients of the target classifier to generate counterfactual explanations of input instances. Further, we analyze current approaches to evaluate spurious correlations and extend the evaluation measurements by proposing a new metric: Correlation Difference. Our experimental validations show that the proposed algorithm surpasses previous State-of-the-Art results on 5 out of 6 metrics on CelebA.
{"title":"Diffusion Models for Counterfactual Explanations","authors":"Guillaume Jeanneret, Loïc Simon, F. Jurie","doi":"10.48550/arXiv.2203.15636","DOIUrl":"https://doi.org/10.48550/arXiv.2203.15636","url":null,"abstract":"Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable. In this paper, we propose DiME, a method allowing the generation of counterfactual images using the recent diffusion models. By leveraging the guided generative diffusion process, our proposed methodology shows how to use the gradients of the target classifier to generate counterfactual explanations of input instances. Further, we analyze current approaches to evaluate spurious correlations and extend the evaluation measurements by proposing a new metric: Correlation Difference. Our experimental validations show that the proposed algorithm surpasses previous State-of-the-Art results on 5 out of 6 metrics on CelebA.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76474249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-25DOI: 10.1007/978-3-030-69541-5_31
Jaeyoo Park, Junha Kim, Bohyung Han
{"title":"Learning to Adapt to Unseen Abnormal Activities Under Weak Supervision","authors":"Jaeyoo Park, Junha Kim, Bohyung Han","doi":"10.1007/978-3-030-69541-5_31","DOIUrl":"https://doi.org/10.1007/978-3-030-69541-5_31","url":null,"abstract":"","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80105854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：