TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/HumanAct12

HumanAct12

ImagesIntroduced 2020-07-30

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

Benchmarks

10-shot image generation/Accuracy10-shot image generation/FID10-shot image generation/Multimodality3D Human Pose Tracking/Accuracy3D Human Pose Tracking/FID3D Human Pose Tracking/MultimodalityActivity Recognition/AccuracyActivity Recognition/DiversityActivity Recognition/FIDActivity Recognition/MultimodalityHuman action generation/AccuracyHuman action generation/DiversityHuman action generation/FIDHuman action generation/MultimodalityMotion Synthesis/AccuracyMotion Synthesis/FIDMotion Synthesis/MultimodalityPose Tracking/AccuracyPose Tracking/FIDPose Tracking/Multimodality

Statistics

Papers
37
Benchmarks
20

Links

Homepage

Tasks

10-shot image generation3D Human Pose TrackingAction GenerationActivity RecognitionHuman action generationMotion SynthesisPose Tracking