Human-object interaction detection based on cascade multi-scale transformer
L Xia, X Ding - Applied Intelligence, 2024 - Springer
Human-object interaction (HOI) detection is an advanced computer vision task for detecting
the relationship between human and surrounding objects. Some methods have emerged to …
the relationship between human and surrounding objects. Some methods have emerged to …
A new bi-level deep human action representation structure based on the sequence of sub-actions
F Akhlaghian Tab, M Ramezani, H Afshoon… - Neural Computing and …, 2024 - Springer
Human action recognition is applicable in different domains. Previously proposed methods
cannot appropriately consider the sequence of sub-actions. Herein, we propose a …
cannot appropriately consider the sequence of sub-actions. Herein, we propose a …
Shape-based 3D human action retrieval using triplet network
H Wang, Y Wei, B Ding, J Song, Z Wang - Multimedia Tools and …, 2024 - Springer
Human action retrieval is a challenging task in computer vision and computer graphics.
Existing action retrieval works are mainly for the human representation of skeleton …
Existing action retrieval works are mainly for the human representation of skeleton …
Spatio-temporal analysis and comparison of 3D videos
S Cammarasana, G Patanè - The Visual Computer, 2023 - Springer
Depth sensors of low-cost acquisition devices (eg Microsoft Kinect, Asus Xtion) are coming
into widespread use; however, 3D acquired data are generally large, heterogeneous, and …
into widespread use; however, 3D acquired data are generally large, heterogeneous, and …
Effective descriptors for human action retrieval from 3D mesh sequences
Two novel methods for fully unsupervised human action retrieval using 3D mesh sequences
are presented. The first achieves high accuracy but is suitable for sequences consisting of …
are presented. The first achieves high accuracy but is suitable for sequences consisting of …
三角形网格序列表示的人体动作识别
王辉， 宋佳豪， 丁铂栩， 何鹏， 曹俊杰 - 计算机辅助设计与图形学学报, 2022 - jcad.cn
鉴于现有的人体动作识别研究工作主要是基于骨架和视频表示的, 提出三角形网格序列表示的
人体动作分类方法. 首先, 选用三角形网格序列中的首帧模型作为模板, 利用形状差异算子计算 …
人体动作分类方法. 首先, 选用三角形网格序列中的首帧模型作为模板, 利用形状差异算子计算 …
Human behaviour recognition with mid‐level representations for crowd understanding and analysis
B Sun, N Yuan, S Li, S Wu, N Wang - IET Image Processing, 2021 - Wiley Online Library
Crowd understanding and analysis have received increasing attention for couples of
decades, and development of human behaviour recognition strongly supports the …
decades, and development of human behaviour recognition strongly supports the …
Spatio-temporal analysis and comparison of 3D videos
C Simone, P Giuseppe - 2023 - dlib.phenikaa-uni.edu.vn
Depth sensors of low-cost acquisition devices (eg Microsoft Kinect, Asus Xtion) are coming
into widespread use; however, 3D acquired data are generally large, heterogeneous, and …
into widespread use; however, 3D acquired data are generally large, heterogeneous, and …
Deep neural networks with distance distributions for gender recognition of 3D human shapes
H Wang, X Lin, N Li, F Meng, J Cao, X Liu - IEEE Access, 2020 - ieeexplore.ieee.org
Automatic human gender recognition is an important and classical problem in artificial
intelligence. Most of the previous gender recognition works are based on vision appearance …
intelligence. Most of the previous gender recognition works are based on vision appearance …
S3GRN: Structural Similar Stepwise Generative Recognizable Network for Human Action Recognition With Limited Training Data
Human action recognition is a hot topic and it has been applied to various fields. Deep
learning is one of the techniques in human action recognition which has achieved good …
learning is one of the techniques in human action recognition which has achieved good …