Guest speaker Ramy Mounir discusses his recent work on networks that can learn robust representations in an online, streaming task-setting, demonstrating impressive results by taking inspiration from neuroscience and cognitive psychology. His paper 'STREAMER: Streaming Representation Learning and Event Segmentation in a Hierarchical Manner' was recently accepted at NeurIPS 2023. To learn more about Ramy's work, visit https://ramymounir.com/
Papers: "STREAMER: Streaming Representation Learning and Event Segmentation in a Hierarchical Manner": https://openreview.net/pdf?id=EfTMRQn00d "Towards Automated Ethogramming: Cognitively-Inspired Event Segmentation for Streaming Wildlife Video Monitoring": https://link.springer.com/article/10.1007/s11263-023-01781-2