AI on the edge: a comprehensive review

W Su, L Li, F Liu, M He, X Liang - Artificial Intelligence Review, 2022 - Springer
With the advent of the Internet of Everything, the proliferation of data has put a huge burden
on data centers and network bandwidth. To ease the pressure on data centers, edge …

Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning

M Sponner, B Waschneck, A Kumar - ACM Computing Surveys, 2024 - dl.acm.org
Adaptive optimization methods for deep learning adjust the inference task to the current
circumstances at runtime to improve the resource footprint while maintaining the model's …

YOLO-GD: a deep learning-based object detection algorithm for empty-dish recycling robots

X Yue, H Li, M Shimizu, S Kawamura, L Meng - Machines, 2022 - mdpi.com
Due to the workforce shortage caused by the declining birth rate and aging population,
robotics is one of the solutions to replace humans and overcome this urgent problem. This …

Vabus: Edge-cloud real-time video analytics via background understanding and subtraction

H Wang, Q Li, H Sun, Z Chen, Y Hao… - IEEE Journal on …, 2022 - ieeexplore.ieee.org
Edge-cloud collaborative video analytics is transforming the way data is being handled,
processed, and transmitted from the ever-growing number of surveillance cameras around …

Blockchain-based distributed multi-agent reinforcement learning for collaborative multi-object tracking framework

J Shen, H Sheng, S Wang, R Cong… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
With the development of smart cities, video surveillance has become more prevalent in
urban areas. The rapid growth of data brings challenges to video processing and analysis …

A surveillance video real-time analysis system based on edge-cloud and fl-yolo cooperation in coal mine

Z Xu, J Li, M Zhang - IEEE Access, 2021 - ieeexplore.ieee.org
Video monitoring is an important means to ensure production safety in coal mine. However,
the currently intelligent video surveillance is difficult to respond in real-time due to the …

A novel efficient algorithm for duplicate video comparison in surveillance video storage systems

NM Balamurugan, TKS Rathish babu… - Journal of Ambient …, 2021 - Springer
Video surveillance system is playing an inevitable role in monitoring the world in
uncountable and unimaginable aspects. There are numerous systems has been adopted to …

Crucio: End-to-End Coordinated Spatio-Temporal Redundancy Elimination for Fast Video Analytics

A Zhu, S Zhang, X Shi, K Cheng… - IEEE INFOCOM 2024 …, 2024 - ieeexplore.ieee.org
Video Analytics Pipeline (VAP) usually relies on traditional codecs to stream video content
from clients to servers. However, such analytics-agnostic codecs preserve considerable …

Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques

R Xu, S Razavi, R Zheng - IEEE Communications Surveys & …, 2023 - ieeexplore.ieee.org
Video, as a key driver in the global explosion of digital information, can create tremendous
benefits for human society. Governments and enterprises are deploying innumerable …

Self-supervised Video Summarization Guided by Semantic Inverse Optimal Transport

Y Wang, H Xu, D Luo - Proceedings of the 31st ACM International …, 2023 - dl.acm.org
Video summarization is a critical task in video analysis that aims to create a brief yet
informative summary of the original video (ie, a set of keyframes) while retaining its primary …