[Seminar] Representation Learning for Vision and Language

Samira’s work spans across several areas in deep learning research including multi-modal learning, knowledge distillation, deep reinforcement learning, and applications. She made significant contributions to the field of human computer interaction with her work on multi-modal learning for emotion recognition in videos. She also worked on visual reasoning at the intersection of vision and text. She contributed to the creation of several large-scale benchmarks including FigureQA (visual reasoning on mathematical plots), Something-Something (fine-grained video captioning) and ReDial (conversational movie recommendation). On the application side she works on machine learning for disaster response with focus on modeling of extreme weather events.