Three‐stream network with context convolution module for human–object interaction detection
Human–object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extracto...
Main Authors: | Thomhert S. Siadari, Mikyong Han, Hyunjin Yoon |
---|---|
Format: | Article |
Language: | English |
Published: |
Electronics and Telecommunications Research Institute (ETRI)
2020-02-01
|
Series: | ETRI Journal |
Subjects: | |
Online Access: | https://doi.org/10.4218/etrij.2019-0230 |
Similar Items
-
Three-Stream Convolutional Neural Network for Depression Detection With Ocular Imaging
by: Minqiang Yang, et al.
Published: (2023-01-01) -
An Efficient Bayesian Approach to Exploit the Context of Object-Action Interaction for Object Recognition
by: Sungbaek Yoon, et al.
Published: (2016-06-01) -
MFDANet: Multi-Scale Feature Dual-Stream Aggregation Network for Salient Object Detection
by: Bin Ge, et al.
Published: (2023-06-01) -
DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
by: Beomyeon Hwang, et al.
Published: (2023-01-01) -
Integrating Contextual Information and Attention Mechanisms with Sparse Convolution for the Extraction of Internal Objects within Buildings from Three-Dimensional Point Clouds
by: Mingyang Yu, et al.
Published: (2024-02-01)