Club ideas and exertions: Aggregating local predictions for action recognition

C Cao, J Li, R Xi, Y Zhang - … on Circuits and Systems for Video …, 2020 - ieeexplore.ieee.org
Recognizing the actions performed in a video is challenging for an intelligent system since
there are wide variations and enormous information in the video. Attention mechanism pays …

[PDF][PDF] 基于压缩激励残差网络与特征融合的行人重识别

邬可, 张宝华, 吕晓琪, 谷宇, 王月明, 刘新… - Laser & …, 2020 - researching.cn
摘要为解决现有基于深度学习的行人重识别算法中网络深度过深, 网络层间的特征关系利用率,
时间效率低等问题, 提出了一种基于压缩激励残差网络(SE-ResNet) 与特征融合的改进算法 …