Features of Interest Points Based Human Interaction Prediction

2020 ◽  
pp. 305-316
Author(s):  
Xiaofei Ji ◽  
Xuan Xie ◽  
Chenyu Li
Keyword(s):  
Human Interaction ◽  
Interest Points ◽  
Interaction Prediction

Human Interaction Prediction Using Deep Temporal Features

2016 ◽  
pp. 403-414 ◽  
Author(s):  
Qiuhong Ke ◽  
Mohammed Bennamoun ◽  
Senjian An ◽  
Farid Boussaid ◽  
Ferdous Sohel
Keyword(s):  
Human Interaction ◽  
Interaction Prediction ◽  
Temporal Features

Spatial-temporal dual-actor CNN for human interaction prediction in video

2020 ◽  
Vol 79 (27-28) ◽  
pp. 20019-20038
Author(s):  
Mahlagha Afrasiabi ◽  
Hassan Khotanlou ◽  
Theo Gevers
Keyword(s):  
Human Interaction ◽  
Interaction Prediction

DTW-CNN: time series-based human interaction prediction in videos using CNN-extracted features

2019 ◽  
Vol 36 (6) ◽  
pp. 1127-1139 ◽  
Author(s):  
Mahlagha Afrasiabi ◽  
Hassan khotanlou ◽  
Muharram Mansoorizadeh
Keyword(s):  
Time Series ◽  
Human Interaction ◽  
Interaction Prediction

scholarly journals Predicting Human Interaction via Relative Attention Model

2017 ◽  
Author(s):  
Yichao Yan ◽  
Bingbing Ni ◽  
Xiaokang Yang
Keyword(s):  
Prediction Accuracy ◽  
Mutual Influence ◽  
Effective Interaction ◽  
Small Region ◽  
Human Interaction ◽  
Attention Model ◽  
Interaction Prediction ◽  
Partially Observed ◽  
Spatio Temporal ◽  
Public Datasets

Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects. Also, only a small region in the scene is discriminative for identifying the on-going interaction. In this work, we propose a relative attention model to explicitly address these difficulties. Built on a tri-coupled deep recurrent structure representing both interacting subjects and global interaction status, the proposed network collects spatio-temporal information from each subject, rectified with global interaction information, yielding effective interaction representation. Moreover, the proposed network also unifies an attention module to assign higher importance to the regions which are relevant to the on-going action. Extensive experiments have been conducted on two public datasets, and the results demonstrate that the proposed relative attention network successfully predicts informative regions between interacting subjects, which in turn yields superior human interaction prediction accuracy.

scholarly journals Leveraging Structural Context Models and Ranking Score Fusion for Human Interaction Prediction

2018 ◽  
Vol 20 (7) ◽  
pp. 1712-1723 ◽  
Author(s):  
Qiuhong Ke ◽  
Mohammed Bennamoun ◽  
Senjian An ◽  
Ferdous Sohel ◽  
Farid Boussaid
Keyword(s):  
Human Interaction ◽  
Interaction Prediction ◽  
Structural Context ◽  
Ranking Score ◽  
Score Fusion ◽  
Context Models

Human Interaction: Understanding Is Not Enough

1974 ◽  
Vol 19 (7) ◽  
pp. 539-540
Author(s):  
NEWTON MARGULIES
Keyword(s):  
Human Interaction

Review of Interpersonal dynamics: Essays and readings on human interaction.

1975 ◽  
Vol 20 (7) ◽  
pp. 594-595
Author(s):  
ROBERT D. LANGSTON
Keyword(s):  
Human Interaction ◽  
Interpersonal Dynamics
Sign in / Sign up

Export Citation Format

Share Document