Human action recognition and retrieval using sole depth information

By Yan-Ching Lin, Min-Chun Hu, Wen-Huang Cheng, Yung-Huan Hsieh, Hong-Ming Chen. 2012

106 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

RGB-D-based action recognition datasets: A survey (2016, background): “Depth-included Human Action video dataset (DHA) [18]( http://mclab.citi.sinica.edu.tw/dataset/ dha/dha.html ) was created by CITI in Academia Sinica.”
Single/multi-view human action recognition via regularized multi-task learning (2015, methodology): “(3) More action samples: MV-TJU with 160 samples per action contains much more samples for model learning compared to the popular datasets, like MSRDailyActivity3D [65] and DHA [66].”
A Vision-Based System for Intelligent Monitoring: Human Behaviour Analysis and Privacy by Context (2014, methodology): “The depth-included human action video dataset (DHA) [48] is aimed at providing a large dataset for human action recognition relying on single-view depth data, which is consistent with the traditional motion-based human action datasets, like Weizmann [34].”
Human Action Recognition From Various Data Modalities: A Review (2020, unknown): “Dataset Year Modality #Class #Subject #Sample #View KTH [347] 2004 RGB 6 25 2,391 1 Weizmann [40] 2005 RGB 10 9 90 1 IXMAS [348] 2006 RGB 11 10 330 5 HDM05 [349] 2007 RGB,S 130 5 2,337 1 Hollywood [350] 2008 RGB 8 - 430 Hollywood2 [351] 2009 RGB 12 - 3,669 MSR-Action3D [217] 2010 S,D 20 10 567 1 Oly”
Dual Contrastive Prediction for Incomplete Multi-View Representation Learning (2022, background): “DHA (Depth-included Human Action dataset) [58]: The dataset contains 483 video clips of 23 categories with RGB and depth features.”