微软研究峰会2021 | 结束致辞：趋向于类人的视觉学习与推理

Big data-driven deep learning has helped significantly improve the performance of visual tasks in the past few years, but it has also exhibited limitations in scalability and adaptation to real-world scenarios. Researchers and practitioners are working hard to develop architectures and algorithms to address these limitations. In this track, researchers and practitioners share their work and insights and discuss how to effectively move this emerging field forward.

Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit