HumanML3D is a 3D human motion-language dataset that originates from a combination of HumanAct12 and Amass dataset. It covers a broad range of human actions such as daily activities (e.g., 'walking', 'jumping'), sports (e.g., 'swimming', 'playing golf'), acrobatics (e.g., 'cartwheel') and artistry (e.g., 'dancing'). Overall, HumanML3D dataset consists of 14,616 motions and 44,970 descriptions composed by 5,371 distinct words. The total length of motions amounts to 28.59 hours. The average motion length is 7.1 seconds, while average description length is 12 words.

The KIT Motion-Language is a dataset linking human motion and natural language. Source: The KIT Motion-Language Dataset

HumanAct12 is a new 3D human motion dataset adopted from the polar image and 3D pose dataset PHSPD, with proper temporal cropping and action annotating. Statistically, there are 1191 3D motion clips(and 90,099 poses in total) which are categorized into 12 action classes, and 34 fine-grained sub-classes. The action types includes daily actions such as walk, run, sit down, jump up, warm up, etc. Fine-grained action types contain more specific information like Warm up by bowing left side, Warm up by pressing left leg, etc. Source: Action2Motion: Conditioned Generation of 3D Human Motions

InterHuman is a multimodal dataset, named InterHuman. It consists of about 107M frames for diverse two-person interactions, with accurate skeletal motions and 16,756 natural language descriptions. Source: InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions Image Source: GitHub Repo: InterGen

ARCTIC is a dataset of free-form interactions of hands and articulated objects. ARCTIC has 1.2M images paired with accurate 3D meshes for both hands and for objects that move and deform over time. The dataset also provides hand-object contact information.

Motion-X is a large-scale 3D expressive whole-body motion dataset, which comprises 15.6M precise 3D whole-body pose annotations (i.e., SMPL-X) covering 81.1K motion sequences from massive scenes, meanwhile providing corresponding semantic labels and pose descriptions.

AIST++ is a 3D dance dataset which contains 3D motion reconstructed from real dancers paired with music. The AIST++ Dance Motion Dataset is constructed from the AIST Dance Video DB. With multi-view videos, an elaborate pipeline is designed to estimate the camera parameters, 3D human keypoints and 3D human dance motion sequences: - It provides 3D human keypoint annotations and camera parameters for 10.1M images, covering 30 different subjects in 9 views. These attributes makes it the largest and richest existing dataset with 3D human keypoint annotations. - It also contains 1,408 sequences of 3D human dance motion, represented as joint rotations along with root trajectories. The dance motions are equally distributed among 10 dance genres with hundreds of choreographies. Motion durations vary from 7.4 sec. to 48.0 sec. All the dance motions have corresponding music.

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

Inter-X is a large-scale dataset containing ~11K interaction sequences, more than 8.1M frames and 34K fine-grained human textual descriptions.

AIOZ-GDANCE comprises 16.7 hours of whole-body motion and music audio of group dancing. The duration of each video in our dataset is ranging from 15 to 60 seconds.

Ubisoft La Forge Animation Dataset ("LAFAN1") Ubisoft La Forge Animation dataset and accompanying code for the SIGGRAPH 2020 paper Robust Motion In-betweening. Shot in May 2017. This dataset can be used under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License (see license.txt). If you use this dataset or transition benchmarking code, please consider citing the paper: @article{harvey2020robust, author = {Félix G. Harvey and Mike Yurick and Derek Nowrouzezahrai and Christopher Pal}, title = {Robust Motion In-Betweening}, booktitle = {ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH)}, publisher = {ACM}, volume = {39}, number = {4}, year = {2020} } You may also want to consider the following papers, as they also use this dataset (or parts of it): * Learned Motion Matching (Holden et al., 2020) * Subspace Neural Physics: Fast Data-Driven Interactive Simulation (Holden et al., 2019) * DReCon: Data-Driven Responsive Control of Physics-Based Characters (Bergamin et al., 2019) * Robust Solving of Optical Motion Capture Data by Denoising (Holden, 2018) * Recurrent Transition Networks for Character Locomotion (Harvey et al., 2018) ## Data The animation data is contained in the lafan1.zip file. All the animation sequences are in the BVH file format. There are 5 subjects in the dataset, 77 sequences, and 496,672 motion frames at 30fps (~4.6 hours). Every BVH file is named with the following convention: \[*theme*\]\[*take number*\]_\[*subject ID*\].bvh. Any sequences sharing the same theme and take_number were recorded at the same time in the studio. Themes are high level indicators of the actions in the sequences. The following themes are present in the LaFAN1 dataset: | Theme | Description |Number of sequences| |:----------------|:------------------------------------------ |:-----------------:| | Obstacles | Locomotion on uneven terrain |17 | | Walk | Walking locomotion, with different styles |12 | | Dance | Free dancing |8 | | Fall and get up | Falling on the ground and getting back up |6 | | Aiming | Locomotion while handling or aiming a gun |5 | | Ground | Locomotion while crawling and crouching |5 | | Multiple actions| Miscellaneous/multiple movements per sequence|4 | | Run | Jogging/Running locomotion |4 | | Fight | Various fight movements |3 | | Jumps | Locomotion with one and two-leg jumps |3 | | Fight and sports| Fight and sports movements |2 | | Push and stumble| Pushing, stumbling and recovery |3 | | Push and fall | Pushing, falling, and getting up |2 | | Sprint | Sprinting locomotion |2 | | Push | Pushing adversary |1 | © [2018] Ubisoft Entertainment. All Rights Reserved

BRACE is a dataset for audio-conditioned dance motion synthesis challenging common assumptions for this task: - strong music-dance correlation - controlled motion data - simple poses and movements To address these issues: - We focus on breakdancing which features acrobatic moves, tangled postures and weaker dance-music correlation. - We adopt a hybrid labelling pipeline leveraging estimation models as well as manual annotations to obtain good quality keypoint sequences at a reduced cost. - Our efforts produced the BRACE dataset, which contains over 3 hours and 30 minutes of densely annotated poses. - BRACE is also useful to fine-tune pose-estimation models thanks to its high quality keypoint annotations for complicated and uncommon poses.

A large-scale and diverse duet interactive dance dataset. Recording about 117 minutes of professional dancers' performances.

CHAIRS is a large-scale motion-captured f-AHOI dataset, consisting of 17.3 hours of versatile interactions between 46 participants and 81 articulated and rigid sittable objects. CHAIRS provides 3D meshes of both humans and articulated objects during the entire interactive process, as well as realistic and physically plausible full-body interactions. Source: CHAIRS: Towards Full-Body Articulated Human-Object Interaction Image Source: https://arxiv.org/pdf/2212.10621v1.pdf

The Text-Music-Dance (TMD) dataset establishes a pioneering benchmark comprising 2,153 text-music-motion pairs. Dance motions and corresponding text annotations are sourced from Motion-X, incorporating AIST++ and other datasets. For motion-text pairs lacking music, corresponding music is generated using Stable Audio Open with beat adjustment and validated through expert assessments, ensuring inter-rater reliability.

Trinity Gesture Dataset includes 23 takes, totalling 244 minutes of motion capture and audio of a male native English speaker producing spontaneous speech on different topics. The actor’s motion was captured with 20 Viconcameras at 59.94 frames per second(fps), and the skeleton includes 69 joints. Source: https://trinityspeechgesture.scss.tcd.ie/data/

Data used for the paper SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data It contains over 1GB of high-quality motion capture data recorded with an Xsens Awinda system while using a variety of VR applications in Meta Quest devices.

BOTH57M is a body-hand dataset with body-level text prompts and finger-level text prompts.

Diverse guitar-playing motions about 1 hour long, including: • 12 major scales, • chromatic scales, • diverse chords, • arpeggios, • strumming and picking, • bends, • sliding, • vibrato, • palm mute, • natural harmonics, • artificial harmonics, • hammer-ons and pull-offs. All notes were played as 1/8th and mostly at 100BPM. All data were collected from a professional guitarist. The instrument is a Fender American Deluxe Stratocaster guitar with 6 strings and 22 frets. The scale length is 25.5 inches. All the motions are general practical motions rather than the recording of playing any specific songs.