Peeking into the Future: Predicting Future Person Activities and Locations in Videos
Abstract
Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in many applications. Motivated by this idea, this paper studies predicting a pedestrians future path jointly with future activities. We propose an end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 16, 2019
- Accession Number
- AD1152117
Entities
People
- Alexander Hauptmann
- Fei-Fei Li
- Juan Carlos Niebles
- Junwei Liang
- Lu Jiang
Organizations
- Carnegie Mellon University
- Stanford University