19 datasets found

The dataset used in this paper is the Postures dataset, a collection of motion capture data.

The dataset used for training and testing the model consists of 3D walking motion capture data of three different participants. The data is edited to form a continuous cycle...

Human leg motion tracking by fusing IMUs and RGB camera data using Extended Kalman Filter

The dataset used in this paper for self-avatar animation in virtual reality.

KIT Motion Language (KIT-ML) is a dataset containing 3,911 unique human motion sequences and 6,278 individual text annotations.

The dataset used in the paper is a collection of motion data for the MAX robot, including walking, running, jumping, and sitting motions.

The HDM05 dataset is a large-scale motion capture dataset that contains synchronized video and motion capture data of human performances.

Human motion modeling is a critical component of animating virtual characters to imitate vivid and rich human movements, which has been a vital topic for many applications, such...

Motion capture and magnetoencephalography datasets for evaluating the output interpretable VAE

The Human3.6M dataset is a large-scale dataset for 3D human pose estimation in videos. It consists of 3.6 million frames captured by four 50 Hz cameras.

The KIT Motion Language dataset provides 3911 motion sequences and 6353 sequence-level natural language descriptions.

Motion capture data from the CMU Motion Capture database.

Amass dataset is a motion capture dataset containing 3D human motion data.

A dance dataset with 36,356 sliding sequences of 40 continuous poses, manually labeled with Laban Time Efforts (Low, Medium, High)

AIST++ is a large-scale dance motion dataset built from [31]. It contains 1409 sequences of dance motions, covering 10 different dance genres with hundreds of choreographies.

HumanAct12 dataset is a large-scale 3D human motion dataset with textual descriptions.

HumanML3D is a text-to-motion dataset built upon AMASS dataset and HumanAct12. It provides a wide range of motion-language pairs which cover ordinary activities, such as...

The dataset used in this paper is the BABEL dataset, which contains 10881 motion sequences, with 65926 subsequences and the corresponding textual labels.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a dataset that comprises 24 videos with diverse motion types and contexts.