Papers with Code 아카이브

Image Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
33
평가표
177
보존된 평가 기록
2,906

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

Trailers12k

Trailers12k is a movie trailer dataset comprised of 12,000 titles associated to ten genres. It distinguishes from other datasets by its collection procedure aimed at providing a high-quality publicly available dataset.

Tsinghua Dogs

Tsinghua Dogs is a fine-grained classification dataset for dogs, over 65% of whose images are collected from people's real life. Each dog breed in the dataset contains at least 200 images and a maximum of 7,449 images, basically in proportion to their frequency of occurrence in China, so it significantly increases the diversity for each breed over existing dataset. Furthermore, Tsinghua Dogs annotated bounding boxes of the dog’s whole body and head in each image, which can be used for supervising the training of learning algorithms as well as testing them.

TwinSynths

The TwinSynths dataset is a novel benchmark designed to overcome common limitations found in earlier synthetic image datasets, such as low image quality, inadequate content preservation, and limited class diversity. TwinSynths generates pairs of images where each synthetic image is visually identical to its real counterpart, ensuring that the essential content remains intact while showcasing the unique architectural features of the generative models used. TwinSynths comprises two subsets: TwinSynths-GAN This subset uses a GAN generator architecture which trained from scratch on individual real images using a mean-squared error loss to ensure pixel-level fidelity. By fixing the latent vector input, the method produces synthetic images that closely mirror the original content. The GAN subset consists of 8,000 generated images spanning 80 classes selected from ImageNet. TwinSynths-DM For the diffusion model-based subset, DDIM inversion is used to maintain the content integrity of the original images. By applying a noise-adding forward process followed by a text-conditioned denoising procedure (using class name prompts), this generates synthetic images that are highly similar to their real counterparts. The same set of ImageNet classes is used as in the GAN subset, allowing for a consistent evaluation across different generative methods.

UV6K

UV6K is a high-resolution remote sensing urban vehicle segmentation dataset. - Images: 6,313 - Vehicle: 245,141 - Resolution: 0.1m - Image Size: 1024x1024

Weapon Detection Dataset

About Dataset Context With increasing unrest, security cams should be armed with advance technology. Content This dataset contains weapon disclosure note in pascal VOC format. Each image has its corresponding notes xml file. They are in xmin, ymin, xmax, ymax. Categories has knife,Gun and other weapons etc. The Importance of Weapon Detection in Security: Discussing the significance of accurate weapon detection in add to security measures and avoid potential threats. Data Composition: Providing insights into the composition of the firearm disclosure data, including the types of fire arms covered, diverse environments, and scenarios depicted. Annotated Data for Enhanced Analysis: Explaining the importance of annotated data in facilitating object localization, classification tasks, and algorithm training for weapon detection. Quality Assurance and Validation Processes: Detailing the rigorous quality assurance and validation procedures employed to ensure the accuracy and reliability of the dataset. Applications and Use Cases: Exploring the various applications and use cases of the firearms disclosure data, including training machine learning models, benchmarking algorithms, and evaluating system performance. Future Directions and Impact: Discussing the potential impact of the dataset on advancing fire arms disclosure technology, enhancing security protocols, and contributing to safer communities. This dataset is sourced from Kaggle.

WikiChurches

WikiChurches is a dataset for architectural style classification, consisting of 9,485 images of church buildings. Both images and style labels were sourced from Wikipedia. The dataset can serve as a benchmark for various research fields, as it combines numerous real-world challenges: fine-grained distinctions between classes based on subtle visual features, a comparatively small sample size, a highly imbalanced class distribution, a high variance of viewpoints, and a hierarchical organization of labels, where only some images are labeled at the most precise level. In addition, we provide 631 bounding box annotations of characteristic visual features for 139 churches from four major categories. These annotations can, for example, be useful for research on fine-grained classification, where additional expert knowledge about distinctive object parts is often available.

YFCC100M Fine-Grained Geolocation

The YFCC100M Fine-Grained Geolocation dataset is a subset of 100 a set of 36,146 YFCC100M images that had Flickr tags that could be identified as corresponding to one of the labels in the iNaturalist 2017 dataset. The 36,146 images that were selected so have the following characteristics: the image must have geolocation available, the image must have at most one iNaturalist label, at most ten examples were retained for each label. Source: https://github.com/visipedia/fg_geo Image Source: https://github.com/visipedia/fg_geo

ADFI

ADFI Dataset is an image dataset for anomaly detection methods with a focus on industrial inspection. Each category sub dataset comprises a training set of images and a test set of images with various kinds of defects as well as images without defects. Supplementary information: ADFI provides a cloud service that automatically creates machine learning models for anomaly detection. You can create anomaly detection models with these datasets for free on the ADFI website.

Alpaca Dataset Image Classification

Description: <a href="https://gts.ai/dataset-download/alpaca-dataset-image-classification/" target="_blank">👉 Download the dataset here</a> The Alpaca Dataset is a collection of JPEG images designed for binary image classification tasks, specifically classifying images as “Alpaca” or “Not Alpaca”. This dataset is ideal for training and fine-tuning machine learning models using transfer learning techniques. Download Dataset Context This small dataset is perfect for educational purposes, initial model testing, and developing proof-of-concept applications in image classification. Due to its limited size, it is most beneficial when used in conjunction with transfer learning to leverage pre-trained models for improved accuracy. Content The dataset is organized into two primary directories: Alpaca: Contains images that include alpacas. Not Alpaca: Contains images without alpacas, featuring subjects that may resemble alpacas but are not. Additional Information Format: All images are in JPEG format, ensuring compatibility with a wide range of image processing libraries and tools. Usage: This dataset can be utilized in various machine learning frameworks such as TensorFlow, PyTorch, and Keras for building and testing classification models. Applications: Potential applications include animal recognition systems, educational tools, and development of AI-driven content moderation systems. Data Statistics Total Images: X (Number of images in the dataset) Alpaca Images: Y (Number of images in the Alpaca directory) Not Alpaca Images: Z (Number of images in the Not Alpaca directory) Image Resolution: Varies, with most images having a resolution suitable for quick model training and evaluation. This dataset is sourced from Kaggle.

AppleScabFDs

Dataset contains images with apples infected by scab. The images are grouped in two folders: "Healthy" and "Scab". The collection of digital images were carried out in different locations of Latvia. Digital images with characteristic scab symptoms on fruits were collected by the Institute of Horticulture (LatHort) under project "lzp-2019/1-0094 Application of deep learning and datamining for the study of plant-pathogen interaction: the case of apple and pear scab" with a goal to create mobile application for apple scab detection using convolution neural networks. Devices: smartphone cameras (12 MP, 13 MP, 48 MP) and a digital compact camera (10 MP). The collection of images was carried out in field conditions, in orchards. The images were taken at three different stages of the day - in the morning (9:00-10:00), around noon (12:00-14:00), as well as in the evening (16:00-17:00) to provide a variety of natural light conditions. The images were also taken on both sunny days and overcast days to provide different types of light (soft light and hard light). The leaves were framed so that they occupied the image area as much as possible and were in the center of the image, and the focal point was on the object. The object may have had other leaves or fruits in the background. The same object was photographed from multiple viewpoints. Source: https://www.kaggle.com/projectlzp201910094/applescablds Introduced by: S. Kodors, G. Lacis, O. Sokolova, V. Zhukovs, I. Apeinans and T. Bartulsons. 2021. Apple Scab Detection using CNN and Transfer Learning. Agronomy Research, 19(2), 507–519. doi: 10.15159/AR.21.045

AppleScabLDs

Dataset contains images with apple leaves infected by scab. The images are grouped in two folders: "Healthy" and "Scab". The collection of digital images were carried out in different locations of Latvia. Digital images with characteristic scab symptoms on leaves were collected by the Institute of Horticulture (LatHort) under project "lzp-2019/1-0094 Application of deep learning and datamining for the study of plant-pathogen interaction: the case of apple and pear scab" with a goal to create mobile application for apple scab detection using convolution neural networks. Devices: smartphone cameras (12 MP, 13 MP, 48 MP) and a digital compact camera (10 MP). The collection of images was carried out in field conditions, in orchards. The images were taken at three different stages of the day - in the morning (9:00-10:00), around noon (12:00-14:00), as well as in the evening (16:00-17:00) to provide a variety of natural light conditions. The images were also taken on both sunny days and overcast days to provide different types of light (soft light and hard light). The leaves were framed so that they occupied the image area as much as possible and were in the center of the image, and the focal point was on the object. The object may have had other leaves or fruits in the background. The same object was photographed from multiple viewpoints. Source: https://www.kaggle.com/projectlzp201910094/applescablds Introduced by: S. Kodors, G. Lacis, O. Sokolova, V. Zhukovs, I. Apeinans and T. Bartulsons. 2021. Apple Scab Detection using CNN and Transfer Learning. Agronomy Research, 19(2), 507–519. doi: 10.15159/AR.21.045

CCIC

The dataset contains concrete images having cracks. The data is collected from various METU Campus Buildings. The dataset is divided into two as negative and positive crack images for image classification. Each class has 20000images with a total of 40000 images with 227 x 227 pixels with RGB channels. The dataset is generated from 458 high-resolution images (4032x3024 pixel) with the method proposed by Zhang et al (2016). High-resolution images have variance in terms of surface finish and illumination conditions. No data augmentation in terms of random rotation or flipping is applied. If you use this dataset please cite: 2018 – Özgenel, Ç.F., Gönenç Sorguç, A. “Performance Comparison of Pretrained Convolutional Neural Networks on Crack Detection in Buildings”, ISARC 2018, Berlin. Lei Zhang , Fan Yang , Yimin Daniel Zhang, and Y. J. Z., Zhang, L., Yang, F., Zhang, Y. D., & Zhu, Y. J. (2016). Road Crack Detection Using Deep Convolutional Neural Network. In 2016 IEEE International Conference on Image Processing (ICIP). http://doi.org/10.1109/ICIP.2016.7533052

CEAHB2021-5

Ancient books script identification of Chinese ethnic minorities with deep convolutional neural networks via multi-branch and spatial pyramid pooling Automatic classification of ancient books is an important component of the digital platform of ancient books. In view of the ancient books script identification task of different ethnic minorities in China, we build a dataset of Chinese ethnic ancient handwritten books(Tai Le, Tibet, Naxi, Yi, Shui), crop and standardize preprocessing images of ancient books. Source:CEAHB2021-5

Corn Kernel Images Dataset

Description: The Corn Kernel Images Dataset is a comprehensive collection of 78,881 images of individual corn kernels. These images were captured after the kernels were harvested, processed, and hand-shelled, primarily for agricultural research and data analysis. <a href="https://gts.ai/dataset-download/corn-kernel-images-dataset/" target="_blank">👉 Download the dataset here</a> Download Dataset Image Capture Process: The kernels were singulated using a seed meter and imaged under both front and back lighting conditions, enhancing visual detail. This imaging method ensured high clarity and consistency for each kernel, capturing critical aspects like size, shape, and texture. Applications: Agriculture: The dataset can be used for machine learning models focused on crop health analysis, yield predictions, and kernel classification. Automation: This dataset provides valuable input for automated systems in grain sorting and quality control. Breeding Programs: Plant breeders can utilize the data for phenotypic analysis and crop improvement efforts. Advanced Techniques and Data Augmentation: In addition to the core dataset, users can apply various data augmentation techniques, such as: Rotation and Scaling: This enhances the robustness of AI models by providing variability in kernel orientation. Lighting Adjustments: Simulating different lighting conditions can improve model performance in diverse real-world environments. Texture and Shape Analysis: The high-resolution images allow for detailed texture mapping, which can be integrated into AI training pipelines for accurate kernel identification. Conclusion: This dataset offers extensive opportunities for researchers and professionals in the agriculture and AI domains. By providing high-quality images and comprehensive metadata, it serves as a valuable tool for studying corn kernel morphology, developing AI models, and improving agricultural practices. The potential for further data linkage with the Corn Ear Physical Measurements dataset amplifies its utility, especially for advanced phenotyping studies. This dataset is sourced from Kaggle.

Corn Seeds Dataset

This dataset is the images of corn seeds considering the top and bottom view independently (two images for one corn seed: top and bottom). There are four classes of the corn seed (Broken-B, Discolored-D, Silkcut-S, and Pure-P) 17802 images are labeled by the experts at the AdTech Corp. and 26K images were unlabeled out of which 9k images were labeled using the Active Learning (BatchBALD) We have created three different dataset: (1). Primary dataset: contains the 17802 images labeled by the experts. Top-view(8901) and Bottom-view(8901). (2). Dataset with fake images: We generated fake images using Conditional GAN (BigGAN) as follows: broken-2937, discolored-5823, pure-2937, silkcut-5823 instances and added them into the train set to balance the data set. (3). Balanced dataset: In this case of adding newly captured images labeled using the Batch Active Learning method, new 9000 labeled images are added into the primary dataset. This new dataset contains 26,802 images split into train and validation set 80: 20, respectively. Contains the 17802 images and the 9K images labeled by the Active Learning (BatchBALD).

eAppleScab

The study showed that the apple scab can be detected in the high-resolution RGB images in an early stage of its development. If two datasets, the early and advanced stages, are grouped together, the scab in the early stage is not visible after image resizing for CNN inputs 200-500px. The dataset contains classified images 525x525px saved in three folders: "Background", "Healthy" and "Scab" to identify their categories. Dataset is available: https://www.kaggle.com/datasets/projectlzp201910094/eapplescab Dataset was presented in the paper: S.Kodors, G.Lācis, I.Moročko-Bičevska, I.Zarembo, O.Sokolova, T.Bartulsons, I.Apeināns and V.Žukovs. "Apple Scab Detection in the Early Stage of Disease Using a Convolutional Neural Network" Proceedings of the Latvian Academy of Sciences. Section B. Natural, Exact, and Applied Sciences., vol.76, no.4, 2022, pp.482-487. https://doi.org/10.2478/prolas-2022-0074

Four Shapes

This dataset contains 16,000 images of four shapes; square, star, circle, and triangle. Each image is 200x200 pixels.

Hyper Drive

Towards automated analysis of large environments, hyperspectral sensors must be adapted into a format where they can be operated from mobile robots. In this dataset, we highlight hyperspectral datacubes collected from the Hyper-Drive imaging system. Our system collects and registers datacubes spanning the visible to shortwave infrared (660-1700 nm) in 33 wavelength channels. The system also simultaneously captures the ambient solar spectrum reflected off a white reference tile. The dataset consists of 500 labeled datacubes from on-road and off-road terrain compliant with the ATLAS. This work first appeared at WHISPERS 2023 In Athens, Greece and is a product of the Robotics and Intelligent Vehicles Research Laboratory (RIVeR) at Northeastern University. In addition to the 500 labeled hyperspectral datacubes, raw ROS bagfiles generated of each of the sensor feeds at a higher frame rate are available here. These files are provided as an additional resource and do not contain semantic labels, but contain ~10,000 additional hyperspectral datacubes of in-between frames from the labeled dataset. It also contains additional datatypes for terrain analysis such as inertial measurement unit (IMU) data. To the best of the authors knowledge, it is the largest vehicle-centric hyperspectral dataset currently available! This research was sponsored by the United States Army Core of Engineers (USACE) Engineer Research and Development Center (ERDC) Geospatial Research Laboratory (GRL) and was accomplished under Cooperative Agreement Federal Award Identification Number (FAIN) W9132V-22-2-0001. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of USACE EDRC GRL or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.

Lusitano Fabric Defect Detection Dataset

The Lusitano dataset was collected over a 3-month period, spanning from January to March, from Paulo de Oliveira, S.A., a prominent textile company, based in Covilhã, Portugal, renowned for its innovative contributions to the textile industry. To collect the images for the dataset, we placed one camera in front of a fabric inspection machine, along with a strong and nearly uniform light source. This dataset comprises 4096 × 1024 images, captured by an industrial-grade Teledyne Dalsa Linea camera. The camera’s high resolution and precision ensure the accurate depiction of textile samples, with the level of detail necessary for defect analysis. None of the defects depicted in this dataset are artificially generated; they stem from genuine occurrences observed during this collection period, and thus represent real-world challenges encountered in textile production processes. The dataset also showcases normal images. We announce two folders, train and test in the same folder architecture, a MVTEC AD dataset. The training set contains 32k normal images, while the testing set contains 1646 defect images and 1038 normal images

Mudestreda

Mudestreda Multimodal Device State Recognition Dataset obtained from real industrial milling device with Time Series and Image Data for Classification, Regression, Anomaly Detection, Remaining Useful Life (RUL) estimation, Signal Drift measurement, Zero Shot Flank Took Wear, and Feature Engineering purposes. The official dataset used in the paper "Multimodal Isotropic Neural Architecture with Patch Embedding" ICONIP23. Official Minape repository: https://github.com/hubtru/Minape Official Mudestreda dataset: https://zenodo.org/records/8238653 Conference paper: https://link.springer.com/chapter/10.1007/978-981-99-8079-6_14 Mudestreda (MD) | Size 512 Samples (Instances, Observations)| Modalities 4 | Classes 3 | Future research: Regression, Remaining Useful Life (RUL) estimation, Signal Drift detection, Anomaly Detection, Multivariate Time Series Prediction, and Feature Engineering. ## Overview * Task: Uni/Multi-Modal Classification * Domain: Industrial Flank Tool Wear of the Milling Machine * Input (sample): 4 Images: 1 Tool Image, 3 Spectrograms (X, Y, Z axis) * Output: Machine state classes: Sharp, Used, Dulled * Evaluation: Accuracies, Precision, Recal, F1-score, ROC curve * Each tool's wear is categorized sequentially: Sharp → Used → Dulled. * The dataset includes measurements from ten tools: T1 to T10. * Data splitting options include random or chronological distribution, without shuffling. * Options: * Original data or Augmented data * Random distribution or Tool Distribution ## Use Cases: | Input | Model | Output | |-----------------|---------------|-----------------------| | Use Cases: | | | | 4 Images (1 Tool Image, 3 Spectrograms (X, Y, Z)) | Classification Model | Class (Flank Tool Wear: Sharp, Used, Dulled) | | 3 Spectrograms (X,Y,Z axis) | Classification Model | Class (Flank Tool Wear) | | 1 Tool Image | Classification Model | Image Class (Flank Tool Wear) | | Future Work: | | | | [1, ..., 4] Images | Model | Remaining Useful Life (RUL) estimation | | [1, ..., 4] Images | Monitoring Model | Fault and Anomaly Detection | | [1, ..., 4] Images | Forecasting Model | Multivariate Time Series Prediction | | [1, ..., 3] Spectrograms | Model | Signal Drift measurement | | [1, ..., 4] Images | Regression Model | Zero-Shot Flank Tool Wear (in µm, 10e-6 meter) | | [1, ..., 4] Images | Feature Engineering | Diagnostic Feature Designer If you use Mudestreda dataset cite the work Minape @ ICONIP2023. ## Cite the Paper: If you reference the papr or you use Mudestreda dataset cite the work Minape @ ICONIP2023 @inproceedings{truchan2023multimodal, title={Multimodal Isotropic Neural Architecture with Patch Embedding}, author={Truchan, Hubert and Naumov, Evgenii and Abedin, Rezaul and Palmer, Gregory and Ahmadi, Zahra}, booktitle={International Conference on Neural Information Processing}, pages={173--187}, year={2023}, organization={Springer} }

Portuguese Meals Dataset

Description: <a href="https://gts.ai/dataset-download/portuguese-meals-dataset/" target="_blank">👉 Download the dataset here</a> The Portuguese Meals Dataset is a carefully curated collection of 6,771 images across 23 food categories, designed to assist machine learning systems in recognizing Portuguese meals and performing nutritional calculations. This dataset is particularly valuable for supporting dietary needs, such as guiding diabetic patients toward healthier food choices, while also enriching AI food recognition technologies. Download Dataset Dataset Structure The dataset contains a mix of traditional Portuguese dishes and popular international food items. Dishes like Bacalhau à Brás, Cozido à Portuguesa, and Francesinha represent Portugal’s diverse culinary heritage, while international favorites such as pizza, hamburgers, and donuts offer a broader perspective. Traditional Portuguese Dishes: Aletria (Sweet Vermicelli Dessert) Bacalhau à Brás (Salted Cod with Potatoes) Caldo Verde (Portuguese Kale Soup) Feijoada à Transmontana (Bean Stew) Francesinha (Portuguese Sandwich) Jardineira de Carne (Meat Stew) International Dishes: Pizza Hamburger Ice Cream Hotdog Waffles Data Collection Sources The images in this dataset were collected from a variety of sources: Food-101 Dataset: Contributed categories like fries, chocolate cake, hotdogs, and ice cream. Google Images: Used for capturing authentic images of traditional Portuguese meals. Restaurant Apps: Apps such as Zomato, TripAdvisor, and The Fork helped enrich the dataset with images sourced from local restaurants, ensuring high quality and relevance. Application This dataset is primarily designed for AI and machine learning projects focused on food recognition, nutritional analysis, and health monitoring. It is particularly suited for applications that cater to individuals with specific dietary needs, such as diabetes management. Additionally, the dataset is an excellent resource for cultural studies or AI applications aiming to promote Portuguese gastronomy. Enhancements and Future Prospects Further enhancements to this dataset could include: Adding nutritional data for each dish, allowing for a more comprehensive analysis. Expanding the dataset to cover more local dishes from underrepresented regions in Portugal. Incorporating real-time meal recognition technology through video data capture for more dynamic AI applications. Conclusion The Portuguese Meals Dataset is a versatile and culturally rich resource that bridges the gap between local cuisine and cutting-edge AI technology. By focusing on both traditional and popular dishes, it enables accurate and context-aware food recognition systems, aiding not only in healthcare but also in the promotion of Portuguese culinary heritage. This dataset is sourced from Kaggle.

Railway Track Misalignment Detection Image Dataset

The dataset has railway track images of two types: normal and defective The task is to classify a given image into normal or defective. The defective images have misalignment problems: buckling or hogging If you find this dataset useful in your research, please cite the below paper: @INPROCEEDINGS{9643106, author={Jerripothula, Koteswar Rao and Ansari, Sharik Ali and Nijhawan, Rahul}, booktitle={2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)}, title={A Vision-based Solution for Track Misalignment Detection}, year={2021}, pages={271-277}, keywords={Graphics;Annotations;Railway accidents;Transfer learning;Buildings;Feature extraction;Rail transportation;railway;transfer learning;VGG;Inception;buckling;hogging;misalignment}, doi={10.1109/SIBGRAPI54419.2021.00044} }

Sakha-TB

Sakha-TB is a de-identified image dataset of frontal chest X-rays (CXR), collected through collaboration with several medical institutions in the Republic of Sakha (Yakutia, Russia). The set contains 400 normal X-rays and 400 X-rays with manifestations of pulmonary tuberculosis, balanced to some extent by age and gender, in 16-bit and 8-bit lossless PNG format, converted directly from DICOM files without any changes. Pchelintsev, Y., Khvostikov, A., Buchatskaia, O. et al. Robustness Analysis of Chest X-Ray Computer Tuberculosis Diagnosis. Comput Math Model 33, 472–486 (2022). https://doi.org/10.1007/s10598-023-09587-0

TCMP-300

Traditional Chinese medicinal plants are often used to prevent and treat diseases for the human body. Since various medicinal plants have different therapeutic effects, plant recognition becomes an important topic. Traditional identification of medicinal plants mainly relies on human experts, which does not meet the increased requirements in clinical practice. Artificial Intelligence (AI) research for plant recognition faces challenges due to the lack of a comprehensive medicinal plant dataset. Therefore, we present a Chinese medicinal plant dataset that including 52089 images in 300 categories. Compared to the existing medicinal plant datasets, our dataset has more categories and fine-grained plant parts to facilitate comprehensive plant recognition. The plant images were collected through the Bing search engine and cleaned by a pretrained vision foundation model with human verification. Our dataset promotes the development and validation of advanced AI models for robust and accurate plant recognition.

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.