85 datasets found

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have...

A sports video highlight summarization framework using YOLO v3 and OpenPose.

The HMDB51 dataset is a video dataset for human action recognition. It contains 6,767 videos annotated with 51 categories of human actions.

Ego4d is a large-scale egocentric video dataset that contains 3000 hours of video.

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have...

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have...

Skeleton-based action recognition has attracted considerable attention due to its compact representation of the human body’s skeletal structure. Many recent methods have...

The MSRAction3D dataset contains 567 Kinect depth map sequences from 10 people with 20 actions.

The 50 Salads dataset contains over 4.5 hours of video captures of different actors preparing 2 kinds of mixed salads (with 25 videos for each type of salad). While similar in...

The INRIA YouTube Instructional Videos dataset contains five tasks of different instructional domains: “making coffee”, “changing a car tire”, “CPR”, “jumping a car”, and...

The dataset used in the paper is a dataset of instructional videos, which includes 150 videos depicting 5 daily tasks, with an average of 9.5 actions per video.

The dataset used in the paper is a dataset of instructional videos, which includes 2,750 videos spanning 18 different tasks, with an average of 7.6 actions per video.

The dataset used in the paper is a large-scale instructional video dataset, which includes 11,827 videos involving 180 different tasks, with an average of 3.6 actions per video.

The KTH dataset consists of videos of 25 people performing different activities.

The Moments in Time dataset is a large-scale video action recognition dataset.

A dataset for action recognition, using spatio-temporal features.

The authors used the UCF101, HMDB51, and Diving48 datasets to evaluate the performance of their proposed algorithm.

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.

UCF-101 dataset is a large-scale action recognition dataset, containing 13,320 videos categorized into 101 human action categories.

The Jester dataset is of continuous jokes ratings from -10 to 10, containing the jokes’ texts.