Reza Khoshkangini of Malmö University, Sweden

Scene classification remains a central challenge in computer vision, requiring models to capture both the local structure and global context of visual environments. As scene understanding grows increasingly relevant across different applications of engineering significance. Ranging from autonomous navigation to environmental monitoring, there is a need for learning frameworks that go beyond isolated category modeling. In this talk, I will explore emerging strategies that incorporate multi-task learning, context-aware representations, and knowledge transfer to improve scene classification performance. As a case study, I will introduce our recent work on Hierarchical Transfer and Multi-task Learning (HTMTL), a framework that exploits inter-scene relationships to enhance classification accuracy. By modeling how contextual cues from one scene type can support recognition in others, HTMTL achieves notable gains on the Places365 dataset and offers insights into the synergistic effect of task grouping and shared representation learning. This talk will highlight the broader direction of leveraging structured learning to advance robust and scalable scene understanding.

Biography:

Address:Canada