CVPR18: Tutorial: Part 1: Human Activity Recognition

Organizers: Michael S. Ryoo
Greg Mori
Kris Kitani

Description: In the recent years, the field of human activity recognition has grown dramatically, reflecting its importance in many high-impact societal applications including smart surveil-lance, web-video search and retrieval, quality-of-life devices for elderly people, and robot perception. With the initial success of convolutional network models to learn video representations, the field is gradually moving towards detecting and forecasting more complex human activities involving multiple people, objects, and sub-events in various realistic scenarios. New important research topics and problems are appearing as a consequence, including (i) reliable spatio-temporal localization of activities, (ii) end-to-end modeling of activities’ temporal structure and hierarchy, (iii) group activity recognition, (iv) activity forecasting, as well as (v) construction of large-scale datasets and convolutional models. The objective of this tuto-rial is to introduce and overview recent progress in these emerging topics, as well as to discuss, motivate and encourage future research in diverse subfields of activity recognition.
Schedule:
Introduction
Spatio-Temporal Activity Detection, Greg Mori (SFU)
Learning Temporal Hierarchy, Michael Ryoo (Indiana Univ.)
Invited Talk: Kinetics 600, Joao Carreira (DeepMind)
Invited Talk: Observing Humans in their Natural Habitat: Datasets and Models, Gunnar Sigurdsson (CMU)

Group Activity Recognition, Greg Mori (SFU)
Activity Forecasting, Nick Rhinehart (CMU)
Emerging Topics (Including Privacy-Preservation), Michael Ryoo (Indiana Univ.)