16 datasets found

The BDD100K MOTS dataset is a subset of the BDD100K dataset, containing 154 videos with annotation for training and validation, and 37 videos for testing.

A benchmark dataset for visual object classes, containing 20 object classes and over 100,000 images.

The SHIMRIE dataset is a new dataset for the Object Segmentation from Manipulation Instructions (OSMI) task. It contains 4341 images and 11371 sentences, with a vocabulary size...

The LM-O dataset consists of 1214 images and is used as a test dataset for 6DoF object pose estimation. The dataset includes 8 objects with partial occlusion.

The CAMO dataset is the first COD dataset, containing 1,250 camouflaged images and 1,250 non-camouflaged images.

The DAVIS dataset contains 60 training sequences and 30 validation sequences, with high-quality densely-annotated segmentation mask annotation for each frame.

The dataset used in the paper is ScanNetV2, a real-world dataset for indoor scenes. It contains 1205 training scenes and 312 testing scenes, with instance-level object bounding...

Camouflaged object segmentation (COS) aims to iden-

The COD10K dataset is currently the largest challenging dataset for COD, containing 10K images with dense annotations.

The Youtube-VIS-2019 dataset, which is a benchmark for video instance segmentation.

The DAVIS-17 dataset, which is a benchmark for video object segmentation.

The BOP Challenge 2022 is the fourth in a series of public challenges that are part of the BOP1 project aiming to continuously report the state of the art in 6D object pose...

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

The dataset used in the paper is ShapeNetPart, a synthetic dataset for 3D object part segmentation. It contains 16,881 models from 16 categories.

A stacked carton dataset for detection and segmentation, containing carton images from three scenarios: comprehensive pharmaceutical logistics company (CPLC), e-commerce...

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...