The Densely Annotation Video Segmentation dataset (DAVIS) is a high quality and high resolution densely annotated video segmentation dataset under two resolutions, 480p and 1080p. There are 50 video sequences with 3455 densely annotated frames in pixel level. 30 videos with 2079 frames are for training and 20 videos with 1376 frames are for validation.
466 PAPERS • 11 BENCHMARKS
The 100 Days Of Hands Dataset (100DOH) is a large-scale video dataset containing hands and hand-object interactions. It consists of 27.3K Youtube videos from 11 categories with nearly 131 days of footage of everyday interaction. The focus of the dataset is hand contact, and it includes both first-person and third-person perspectives. The videos in 100DOH are unconstrained and content-rich, ranging from records of daily life to specific instructional videos. To enforce diversity, the dataset contains no more than 20 videos from each uploader.
185 PAPERS • 3 BENCHMARKS
DAVIS17 is a dataset for video object segmentation. It contains a total of 150 videos - 60 for training, 30 for validation, 60 for testing
185 PAPERS • 9 BENCHMARKS
DAVIS16 is a dataset for video object segmentation which consists of 50 videos in total (30 videos for training and 20 for testing). Per-frame pixel-wise annotations are offered.
180 PAPERS • 3 BENCHMARKS
Youtube-VOS is a Video Object Segmentation dataset that contains 4,453 videos - 3,471 for training, 474 for validation, and 508 for testing. The training and validation videos have pixel-level ground truth annotations for every 5th frame (6 fps). It also contains Instance Segmentation annotations. It has more than 7,800 unique objects, 190k high-quality manual annotations and more than 340 minutes in duration.
110 PAPERS • 9 BENCHMARKS
Our task is to localize and provide a pixel-level mask of an object on all video frames given a language referring expression obtained either by looking at the first frame only or the full video. To validate our approach we employ two popular video object segmentation datasets, DAVIS16  and DAVIS17 . These two datasets introduce various challenges, containing videos with single or multiple salient objects, crowded scenes, similar looking instances, occlusions, camera view changes, fast motion, etc.
63 PAPERS • 4 BENCHMARKS
BL30K is a synthetic dataset rendered using Blender with ShapeNet's data. We break the dataset into six segments, each with approximately 5K videos. The videos are organized in a similar format as DAVIS and YouTubeVOS, so dataloaders for those datasets can be used directly. Each video is 160 frames long, and each frame has a resolution of 768*512. There are 3-5 objects per video, and each object has a random smooth trajectory -- we tried to optimize the trajectories in a greedy fashion to minimize object intersection (not guaranteed), with occlusions still possible (happen a lot in reality). See MiVOS for details.
5 PAPERS • NO BENCHMARKS YET
VOT2020 is a Visual Object Tracking benchmark for short-term tracking in RGB.
5 PAPERS • 1 BENCHMARK
We randomly selected three videos from the Internet, that are longer than 1.5K frames and have their main objects continuously appearing. Each video has 20 uniformly sampled frames manually annotated for evaluation.
2 PAPERS • 1 BENCHMARK
We randomly selected three videos from the Internet, that are longer than 1.5K frames and have their main objects continuously appearing. Each video has 20 uniformly sampled frames manually annotated for evaluation. Each video has been played back and forth to generate videos that are three times as long.
2 PAPERS • 1 BENCHMARK