Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
15,996 datasets
A dataset titled 'yolomobilenetshopee11' is hosted on Kaggle. The title suggests a focus on object detection, likely using the YOLO and MobileNet architectures, potentially for e-commerce imagery from Shopee. Metadata is minimal; actual content requires verification after download.
Kaggle hosts this computer vision dataset, likely containing images for object detection tasks. The title references YOLO and Swin Transformer models, suggesting a focus on object detection benchmarks. Its specific content and scale require verification after download.
Vehicle Damage Instance Segmentation is a dataset for automating vehicle insurance claims by isolating damage areas with pixel-level accuracy. The model is a YOLOv8-seg model fine-tuned from a foundation model using the Ultralytics framework. It was created by cvtechniques and last updated on 2026-03-17.
AqSolDB contains curated experimental aqueous solubility values for 9,982 unique compounds, aggregated from 9 publicly available sources. The dataset was created by the Autonomous Energy Materials Discovery research group and includes calculated topological and physico-chemical 2D descriptors alongside validated molecular representations. It is described as the largest dataset of its kind for training data-driven models.
HYDRA-SR is a dataset for super-resolution tasks based on the ImageNet collection. It was published on Kaggle, but its specific size, creation date, and author are unknown. The dataset likely contains pairs of low-resolution and high-resolution images for training enhancement models.
UAV-captured images of soybean leaves, likely intended for agricultural computer vision tasks. The dataset is hosted on Kaggle, but its specific scale, collection dates, and creator are unspecified. Columns and sample data are unavailable, limiting immediate assessment of its content.
A set of pre-trained model weights for the YOLO object detection framework, published on Kaggle. The specific architecture version, training data, and performance metrics are unknown. The author, organization, and last update date are not provided.
RSNA Prepped YOLO Dataset is a collection of medical images formatted for object detection tasks. It was published on Kaggle. The dataset's specific content, size, and creation details are not provided in the available metadata.
Kaggle hosts a collection of YOLO model checkpoints. The dataset likely contains pre-trained weights for object detection models combining YOLO architectures with ResNet backbones. Specific details on the number of checkpoints, training data, or creation date are not provided in the metadata.
Kaggle hosts a collection of model checkpoints for the YOLO FashionCLIP project. The checkpoints likely contain trained weights for a computer vision model combining object detection and image-text understanding. The specific architecture, training data, and performance metrics require verification after download.
Experimental results from a study evaluating the antimicrobial effect of yerba mate extract against Escherichia coli and Proteus mirabilis isolated from chicken breast meat. The data likely contains measurements of inhibition zones from the disk diffusion method for three extract concentrations tested in triplicate. The study was conducted by Débora Euclydes Mariano Costa at Universidade de Brasília.
An updated version of the CIRCL Images AIL Dataset, last updated on 2026-03-19. It is an image dataset enriched with derived metadata, including LLM-generated descriptions and Open Alleged PhotoDNA fingerprints. The dataset is authored by CIRCL and is intended to support research on image classification and content analysis.
REPID is a large-scale benchmark for Image Rendering Quality Assessment (IRQA) designed to model subjective human aesthetic preferences for different rendering styles of the same scene. It was created by author vsevolodpl and was last updated in March 2026.
January 2015 to April 2022 vertical ground displacement measurements for over 200 high-use groundwater basins in California. Data is derived from Sentinel-1A satellite InSAR and processed by TRE ALTAMIRA for the California Department of Water Resources. It includes point data for 100m x 100m areas and interpolated GIS rasters for total and annual displacement.
A dataset for computer vision tasks, likely containing images annotated for object detection and pose estimation. It is hosted on Kaggle, but its specific content, size, and creation details are not described. The dataset's author, organization, and last update date are unknown.
Philip Powell's 1970s book 'Tree of Hate' analyzes the historical 'Black Legend' myth and its impact on U.S. relations with the Hispanic world. The work explores the origins and effects of Hispanophobia on American education, textbooks, religion, and foreign policy. It was published by Philip Wayne Powell of the University of Reading.
Jason W. Stevens authored a book analyzing the role of religion in American cultural life during the Cold War. The work examines narrative and cultural forms, including writings and art, to explore themes of innocence, power, and ideology. It is sourced from the paperswithcode platform.
At least 30,000 lives were claimed by political strife from 1992 to 1994, with the number of victims rising through 1995. The text analyzes Algeria's flawed political transition from a single-party state, focusing on the conflict between Islamists, the military, and secular democrats following the annulled 1991 elections. It was authored by Robert A. Mortimer and sourced from the paperswithcode platform.
Timothy Mitchell's book 'Carbon Democracy' analyzes the political consequences of global oil dependence. It argues that the transition from coal to oil reshaped democratic politics in the West and governance in the Middle East, creating a system now threatened by ecological and energy crises. The work rethinks the history of energy, the politics of nature, and the theory of democracy.
BioLiP is a semi-manually curated database for biologically relevant ligand-protein binding interactions. The structure data are collected primarily from the Protein Data Bank, with biological insights mined from literature and other databases. It is maintained by the Zhang Lab and is publicly available for academic and research use.