Title:
TITLE OF THE INVENTION
Document Type and Number:
WIPO Patent Application WO/2019/109972
Kind Code:
A1
Abstract:
A computing device includes a communication interface, a memory, and processing circuitry. The processing circuitry is coupled to the communication interface and to the memory and is configured to execute the operational instructions to perform various functions. The computing device is configured to process a video frame of a video segment on a per-frame basis and based on joint human-object interactive activity (HOIA) to generate a per-frame pairwise human-object interactive (HOI) feature based on a plurality of candidate HOI pairs. The computing device is also configured to process the per-frame pairwise HOI feature to identify a valid HOI pair among the plurality of candidate HOI pairs and to track the valid HOI pair through subsequent frames of the video segment to generate a contextual spatial-temporal feature for the valid HOI pair to be used in activity detection.
Inventors:
JIANG WEI (US)
KENNEDY LYNDON SCOTT (US)
WANG WEI (US)
KENNEDY LYNDON SCOTT (US)
WANG WEI (US)
Application Number:
PCT/CN2018/119516
Publication Date:
June 13, 2019
Filing Date:
December 06, 2018
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06T7/00; G06T7/20
Other References:
AKILA, K. ET AL.: "Discriminative Human Action Recognition using HOI Descriptor and Key Poses", INTERNATIONAL CONFERENCE ON SCIENCE ENGINEERING AND MANAGEMENT RESEARCH (ICSEMR 2014), 31 December 2014 (2014-12-31), XP055617080
ALESSANDRO, PREST ET AL.: "Explicit Modeling of Human-Object Interactions in Realistic Videos", IEEE TRANSCTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 35, no. 4, 30 April 2013 (2013-04-30), XP011494066
CHAO, YU-WEI ET AL.: "HICO: A Benchmark for Recognizing Human-Object Interactions in Images", 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, 31 December 2015 (2015-12-31), XP032866427
ABHINAV, GUPTA ET AL.: "Observing Human-Object Interactions Using Spatial and Functional Compatibility for Recognition", IEEE TRANSCTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 31, no. 10, 31 October 2009 (2009-10-31), XP011268307
S. REN ET AL.: "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", NIPS, 2015
T. LIN ET AL.: "Microsoft COCO: Comment objects in context", ARXIV, Retrieved from the Internet
ALESSANDRO, PREST ET AL.: "Explicit Modeling of Human-Object Interactions in Realistic Videos", IEEE TRANSCTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 35, no. 4, 30 April 2013 (2013-04-30), XP011494066
CHAO, YU-WEI ET AL.: "HICO: A Benchmark for Recognizing Human-Object Interactions in Images", 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, 31 December 2015 (2015-12-31), XP032866427
ABHINAV, GUPTA ET AL.: "Observing Human-Object Interactions Using Spatial and Functional Compatibility for Recognition", IEEE TRANSCTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 31, no. 10, 31 October 2009 (2009-10-31), XP011268307
S. REN ET AL.: "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", NIPS, 2015
T. LIN ET AL.: "Microsoft COCO: Comment objects in context", ARXIV, Retrieved from the Internet
Download PDF:
Previous Patent: METHOD AND DEVICE FOR ADJUSTING DATA TRANSMISSION MODE
Next Patent: MULTI-LEVEL QUADRATURE AMPLITUDE MODULATION WITH GEOMETRIC SHAPING
Next Patent: MULTI-LEVEL QUADRATURE AMPLITUDE MODULATION WITH GEOMETRIC SHAPING