• Publications
  • Influence
Deep learning for detecting robotic grasps
TLDR
We consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects. Expand
  • 883
  • 98
  • PDF
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
TLDR
We develop a scalable method for casting an arbitrary spatio-temporal graph as a rich RNN mixture that is feedforward, fully differentiable, and jointly trainable. Expand
  • 518
  • 96
  • PDF
Learning human activities and object affordances from RGB-D videos
TLDR
We consider the problem of extracting a descriptive labeling of the sequence of sub-activities being performed by a human, and more importantly, of their interactions with the objects in the form of associated affordances. Expand
  • 538
  • 70
  • PDF
Unstructured human activity detection from RGBD images
TLDR
We perform detection and recognition of human activity in unstructured environments using a hierarchical maximum entropy Markov model based on a two-layered graph structure. Expand
  • 485
  • 63
  • PDF
Learning Depth from Single Monocular Images
TLDR
We consider the task of depth estimation from a single monocular image. Expand
  • 828
  • 56
  • PDF
A dynamic ID-based remote user authentication scheme
TLDR
We present a dynamic ID-based remote user authentication scheme using smart cards, which allows the users to choose and change their passwords freely. Expand
  • 565
  • 35
  • PDF
Human Activity Detection from RGBD Images
TLDR
We perform activity recognition using an inexpensive RGBD sensor (Microsoft Kinect) as the input sensor, and present learning algorithms to infer the activities. Expand
  • 308
  • 33
  • PDF
Robotic Grasping of Novel Objects using Vision
TLDR
We consider the problem of grasping novel objects, specifically objects that are being seen for the first time through vision. Expand
  • 831
  • 26
  • PDF
3-D Depth Reconstruction from a Single Still Image
TLDR
We apply a supervised learning approach to the problem of 3-d depth estimation from a single image. Expand
  • 575
  • 22
  • PDF
Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models
TLDR
We propose an Autoregressive Input-Output Hidden Markov Model (AIO-HMM) to model the contextual information alongwith the maneuvers. Expand
  • 154
  • 22
  • PDF