Adaptive Multi-Agent Continuous Learning System
This work addresses dynamic clustering for video analysis, but appears incremental as it builds on traditional algorithmic approaches.
The paper tackles the problem of clustering recognition in dynamic environments by proposing an adaptive multi-agent system with self-supervised learning, demonstrating feasibility through video behavior clustering experiments.
We propose an adaptive multi-agent clustering recognition system that can be self-supervised driven, based on a temporal sequences continuous learning mechanism with adaptability. The system is designed to use some different functional agents to build up a connection structure to improve adaptability to cope with environmental diverse demands, by predicting the input of the agent to drive the agent to achieve the act of clustering recognition of sequences using the traditional algorithmic approach. Finally, the feasibility experiments of video behavior clustering demonstrate the feasibility of the system to cope with dynamic situations. Our work is placed here\footnote{https://github.com/qian-git/MAMMALS}.