TY - GEN
T1 - First-person activity recognition based on three-stream deep features
AU - Kim, Ye Ji
AU - Lee, Dong Gyu
AU - Lee, Seong Whan
N1 - Funding Information:
This work was supported by Institute for Information & communications Technology Promotion(IITP) grant funded by the Korea government(MSIT)(2014-0-00059, Development of Predictive Visual Intelligence Technology).
Publisher Copyright:
© ICROS.
PY - 2018/12/10
Y1 - 2018/12/10
N2 - In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human’s movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.
AB - In this paper, we present a novel three-stream deep feature fusion technique to recognize interaction-level human activities from a first-person viewpoint. Specifically, the proposed approach distinguishes human motion and camera ego-motion to focus on human’s movement. The features of human and camera ego-motion information are extracted from the three-stream architecture. These features are fused by considering a relationship of human action and camera ego-motion. To validate the effectiveness of our approach, we perform experiments on UTKinect-FirstPerson dataset, and achieve state-of-the-art performance.
KW - First-person activity recognition
KW - Human-robot interaction
KW - Robot surveillance.
KW - Three-stream deep features
UR - http://www.scopus.com/inward/record.url?scp=85060468167&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85060468167
T3 - International Conference on Control, Automation and Systems
SP - 297
EP - 299
BT - International Conference on Control, Automation and Systems
PB - IEEE Computer Society
T2 - 18th International Conference on Control, Automation and Systems, ICCAS 2018
Y2 - 17 October 2018 through 20 October 2018
ER -