Learning Local Descriptors with Multi-Level Feature Aggregation and Spatial Context Pyramid

2021 ◽  
Author(s):  
Pengpeng Liang ◽  
Haoxuanye Ji ◽  
Erkang Cheng ◽  
Yumei Chai ◽  
Liming Wang ◽  
...  
Keyword(s):  
Spatial Context ◽  
Local Descriptors ◽  
Feature Aggregation ◽  
Multi Level

A multi-scale and multi-level feature aggregation network for crowd counting

2021 ◽  
Vol 423 ◽  
pp. 46-56
Author(s):  
Fushun Zhu ◽  
Hua Yan ◽  
Xinyue Chen ◽  
Tong Li ◽  
Zhengyu Zhang
Keyword(s):  
Crowd Counting ◽  
Multi Scale ◽  
Feature Aggregation ◽  
Multi Level

Point cloud up-sampling network with multi-level spatial local feature aggregation

2021 ◽  
Vol 94 ◽  
pp. 107337
Author(s):  
Guang Zeng ◽  
Haisheng Li ◽  
Xiaochuan Wang ◽  
Nan Li
Keyword(s):  
Point Cloud ◽  
Local Feature ◽  
Sampling Network ◽  
Feature Aggregation ◽  
Multi Level

scholarly journals Deeply-Supervised CNN Model for Action Recognition with Trainable Feature Aggregation

2018 ◽  
Author(s):  
Yang Li ◽  
Kan Li ◽  
Xinxin Wang
Keyword(s):  
Action Recognition ◽  
Temporal Evolution ◽  
State Of The Art ◽  
Temporal Structure ◽  
Spatial Location ◽  
Semantic Space ◽  
Feature Aggregation ◽  
Promising Solution ◽  
Multi Level ◽  
Hierarchical Features

In this paper, we propose a deeply-supervised CNN model for action recognition that fully exploits powerful hierarchical features of CNNs. In this model, we build multi-level video representations by applying our proposed aggregation module at different convolutional layers. Moreover, we train this model in a deep supervision manner, which brings improvement in both performance and efficiency. Meanwhile, in order to capture the temporal structure as well as preserve more details about actions, we propose a trainable aggregation module. It models the temporal evolution of each spatial location and projects them into a semantic space using the Vector of Locally Aggregated Descriptors (VLAD) technique. This deeply-supervised CNN model integrating the powerful aggregation module provides a promising solution to recognize actions in videos. We conduct experiments on two action recognition datasets: HMDB51 and UCF101. Results show that our model outperforms the state-of-the-art methods.

MFA: Multi-level Feature Aggregation for Video Recognition

2021 ◽  
Author(s):  
Na Li ◽  
Kuangang Fan ◽  
Ouyang Qinghua ◽  
Yahui Liu
Keyword(s):  
Feature Aggregation ◽  
Video Recognition ◽  
Multi Level
Sign in / Sign up

Export Citation Format

Share Document