Dinesh Jayaraman
Dinesh Jayaraman
Home
Research Group
Publications
Teaching
Active Perception
Look-Ahead Before You Leap: End-to-End Active Recognition By Forecasting the Effect of Motion
Active visual perception with realistic and complex imagery can be formulated as an end-to-end reinforcement learning problem, the solution to which benefits from additionally exploiting the auxiliary task of action-conditioned future prediction.
Dinesh Jayaraman
,
Kristen Grauman
Pano2Vid: Automatic Cinematography For Watching 360-degree Videos
By exploiting human-uploaded web videos as weak supervision, we may train a system that learns what good videos look like, and tries to automatically direct a virtual camera through precaptured 360-degree videos to try to produce human-like videos.
Yu-Chuan Su
,
Dinesh Jayaraman
,
Kristen Grauman
Learning Image Representations Tied to Egomotion
An agent’s continuous visual observations include information about how the world responds to its actions. This can provide an effective source of self-supervision for learning visual representations.
Dinesh Jayaraman
,
Kristen Grauman
«
Cite
×