NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

• Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of large-scale training samples, realistic number of distinct class categories, diversity in camera views, varied environmental conditions, and variety of human subjects. In this work, we introduce a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames. This dataset contains 120 different action classes including daily, mutual, and health-related activities. We evaluate the performance of a series of existing 3D activity analysis methods on this dataset, and show the advantage of applying deep learning methods for 3D-based human action recognition. Furthermore, we investigate a novel one-shot 3D activity recognition problem on our dataset, and a simple yet effective Action-Part Semantic Relevance-aware (APSR) framework is proposed for this task, which yields promising results for recognition of the novel action classes. We believe the introduction of this large-scale dataset will enable the community to apply, adapt, and develop various data-hungry learning techniques for depth-based and RGB+D-based human activity understanding.

Subject headings

SAMHÄLLSVETENSKAP  -- Psykologi -- Psykologi (hsv//swe)

SOCIAL SCIENCES  -- Psychology -- Psychology (hsv//eng)

MEDICIN OCH HÄLSOVETENSKAP  -- Hälsovetenskap -- Arbetsterapi (hsv//swe)

MEDICAL AND HEALTH SCIENCES  -- Health Sciences -- Occupational Therapy (hsv//eng)

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)

Keyword

Skeleton

Cameras

3D action recognition

large-scale benchmark

RGB plus D vision

Activity understanding

Benchmark testing

deep learning

Three-dimensional displays

Lighting

Semantics

video analysis

Deep learning

Publication and Content Type

art (subject category)

ref (subject category)