132 datasets found

CamVid dataset is a benchmark dataset for semantic segmentation. It consists of 700 images with 11 object classes.

BDD100K Dataset is a large-scale dataset for autonomous driving, containing 100,000 images, with 20,000 images for training and 80,000 images for testing.

The DAVIS-2017 dataset is a benchmark for video object segmentation

The dataset used for object detection on streaming video from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2015.

A large-scale benchmark called LiveVideos for the video object of interest segmentation task.

A new computer vision task named video object of interest segmentation (VOIS). Given a video and a target image of interest, the objective is to simultaneously segment and track...

A dance dataset with multi-genre, multi-dancer, and multi-camera videos

Charades-STA dataset contains 12,408/3720 segment-sentence pairs and 5338/1334 videos in training and test set, respectively.

UCSD background subtraction dataset contains videos with moving camera sequences.

Change Detection (CDNet2014) is a benchmark dataset for change detection in videos.

A dataset of real videos for action categorization, including HMDB-51 and UCF-101.

The Kinetics dataset is a large-scale action recognition dataset. It contains videos of various actions performed by humans, with annotations of the actions performed.

The Every Moment Counts dataset contains 1,000 hours of video footage of various activities.

The Hollywood in Homes dataset contains 9,848 videos of daily activities across 157 classes.

The THUMOS Challenge dataset contains 413 sports videos of 65 classes.

Temporal Action Detection (TAD) aims to identify the action boundaries and the corresponding category within untrimmed videos.

The SD-MATH dataset is a public dataset for engagement detection from videos. It contains 20 videos and 20 subjects.

The HBCU dataset is a public dataset for engagement detection from videos. It contains 120 videos and 34 subjects.

The DAiSEE dataset is a public dataset for engagement detection from videos. It contains 9068 videos and 112 subjects.

The WACV dataset is a public dataset for engagement detection from videos. It contains 4424 3-channel images of varying sizes.