Search: onr:"swepub:oai:research.chalmers.se:79b6ec79-8de5-457b-8e99-58e164c12964" >
NTU RGB+D 120: A La...
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
-
- Liu, Jun (author)
- Nanyang Technological University
-
- Shahroudy, Amir, 1981 (author)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Perez, Mauricio (author)
- Nanyang Technological University
-
show more...
-
Wang, Gang (author)
-
- Duan, Ling-Yu (author)
- Peng Cheng Laboratory,Beijing University of Technology
-
- Kot, Alex C. (author)
- Nanyang Technological University
-
show less...
-
(creator_code:org_t)
- 2020
- 2020
- English.
-
In: IEEE Transactions on Pattern Analysis and Machine Intelligence. - 1939-3539 .- 0162-8828. ; 42:10, s. 2684-2701
- Related links:
-
https://research.cha...
-
show more...
-
https://doi.org/10.1...
-
https://research.cha...
-
show less...
Abstract
Subject headings
Close
- 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)
Find in a library
To the university's database