no code implementations • 20 May 2020 • Nan Rong, Joseph Y. Halpern, Ashutosh Saxena
Doing this results in a family of systems, each of which has an extremely large action space, although only a few actions are "interesting".
no code implementations • 17 May 2017 • Jaeyong Sung, J. Kenneth Salisbury, Ashutosh Saxena
The sense of touch, being the earliest sensory system to develop in a human body [1], plays a critical part of our daily interaction with the environment.
no code implementations • NeurIPS 2016 • Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese
Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition.
no code implementations • 12 Jun 2016 • Chenxia Wu, Jiemi Zhang, Ashutosh Saxena, Silvio Savarese
Co-segmentation is the automatic extraction of the common semantic regions given a set of images.
no code implementations • 11 May 2016 • Ozan Sener, Amir Roshan Zamir, Chenxia Wu, Silvio Savarese, Ashutosh Saxena
Our method can also provide a textual description for each of the identified semantic steps and video segments.
no code implementations • 11 Mar 2016 • Chenxia Wu, Jiemi Zhang, Ozan Sener, Bart Selman, Silvio Savarese, Ashutosh Saxena
For evaluation, we contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacting with different objects.
no code implementations • 10 Feb 2016 • Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese
We incorporate the domain shift and the transductive target inference into our framework by jointly solving for an asymmetric similarity metric and the optimal transductive target label assignment.
no code implementations • 12 Jan 2016 • Jaeyong Sung, Seok Hyun Jin, Ian Lenz, Ashutosh Saxena
There is a large variety of objects and appliances in human environments, such as stoves, coffee dispensers, juice extractors, and so on.
no code implementations • 5 Jan 2016 • Ashesh Jain, Hema S. Koppula, Shane Soh, Bharad Raghavan, Avi Singh, Ashutosh Saxena
We introduce a diverse data set with 1180 miles of natural freeway and city driving, and show that we can anticipate maneuvers 3. 5 seconds before they occur in real-time with a precision and recall of 90. 5\% and 87. 4\% respectively.
no code implementations • 5 Jan 2016 • Ashesh Jain, Shikhar Sharma, Thorsten Joachims, Ashutosh Saxena
We consider the problem of learning preferences over trajectories for mobile manipulators such as personal robots and assembly line robots.
no code implementations • 14 Dec 2015 • Chenxia Wu, Jiemi Zhang, Bart Selman, Silvio Savarese, Ashutosh Saxena
We show that our approach not only improves the unsupervised action segmentation and action cluster assignment performance, but also effectively detects the forgotten actions on a challenging human activity RGB-D video dataset.
no code implementations • 26 Nov 2015 • Matthew Long, Aditya Jami, Ashutosh Saxena
In this paper, we attempt to classify tweets into root categories of the Amazon browse node hierarchy using a set of tweets with browse node ID labels, a much larger set of tweets without labels, and a set of Amazon reviews.
no code implementations • 25 Nov 2015 • Amit Garg, Jonathan Noyola, Romil Verma, Ashutosh Saxena, Aditya Jami
This paper attempts multi-label classification by extending the idea of independent binary classification models for each output label, and exploring how the inherent correlation between output labels can be used to improve predictions.
2 code implementations • CVPR 2016 • Ashesh Jain, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena
The proposed method is generic and principled as it can be used for transforming any spatio-temporal graph through employing a certain set of well defined steps.
Ranked #4 on Skeleton Based Action Recognition on CAD-120
no code implementations • 25 Sep 2015 • Jaeyong Sung, Ian Lenz, Ashutosh Saxena
A robot operating in a real-world environment needs to perform reasoning over a variety of sensor modalities such as vision, language and motion trajectories.
no code implementations • 16 Sep 2015 • Ashesh Jain, Avi Singh, Hema S. Koppula, Shane Soh, Ashutosh Saxena
We introduce a sensory-fusion architecture which jointly learns to anticipate and fuse information from multiple sensory streams.
no code implementations • ICCV 2015 • Ozan Sener, Amir Zamir, Silvio Savarese, Ashutosh Saxena
The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps.
no code implementations • CVPR 2015 • Chenxia Wu, Jiemi Zhang, Silvio Savarese, Ashutosh Saxena
For evaluation, we also contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacted with different objects.
no code implementations • 13 Apr 2015 • Jaeyong Sung, Seok Hyun Jin, Ashutosh Saxena
We formulate the manipulation planning as a structured prediction problem and design a deep learning model that can handle large noise in the manipulation demonstrations and learns features from three different modalities: point-clouds, language and trajectory.
no code implementations • ICCV 2015 • Ashesh Jain, Hema S. Koppula, Bharad Raghavan, Shane Soh, Ashutosh Saxena
We evaluate our approach on a diverse data set with 1180 miles of natural freeway and city driving and show that we can anticipate maneuvers 3. 5 seconds before they occur with over 80\% F1-score in real-time.
no code implementations • 1 Dec 2014 • Ashutosh Saxena, Ashesh Jain, Ozan Sener, Aditya Jami, Dipendra K. Misra, Hema S. Koppula
In this paper we introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks.
no code implementations • 27 Jul 2014 • Joseph Y. Halpern, Nan Rong, Ashutosh Saxena
We define a new framework, MDPs with unawareness (MDPUs) to deal with the possibilities that a DM may not be aware of all possible actions.
no code implementations • 10 Jun 2014 • Ashesh Jain, Debarghya Das, Jayesh K. Gupta, Ashutosh Saxena
We represent trajectory preferences using a cost function that the robot learns and uses it to generate good trajectories in new environments.
no code implementations • NeurIPS 2013 • Ashesh Jain, Brian Wojcik, Thorsten Joachims, Ashutosh Saxena
In this paper, we propose a co-active online learning framework for teaching robots the preferences of its users for object manipulation tasks.
no code implementations • 24 Jun 2013 • Jaeyong Sung, Bart Selman, Ashutosh Saxena
Many tasks in human environments require performing a sequence of navigation and manipulation steps involving objects.
no code implementations • CVPR 2013 • Yun Jiang, Hema Koppula, Ashutosh Saxena
Given only a dataset of scenes containing objects but not humans, we show that our algorithm can recover the human object relationships.
no code implementations • CVPR 2013 • Zhaoyin Jia, Andrew Gallagher, Ashutosh Saxena, Tsuhan Chen
Our algorithm incorporates the intuition that a good 3D representation of the scene is the one that fits the data well, and is a stable, self-supporting (i. e., one that does not topple) arrangement of objects.
no code implementations • Proceedings of Machine Learning Research volume 28 2013 • Hema S. Koppula, Ashutosh Saxena
However, because of the ambiguity in the temporal segmentation of the sub-activities that constitute an activity, in the past as well as in the future, multiple graph structures are possible.
Ranked #2 on Skeleton Based Action Recognition on CAD-120
no code implementations • 16 Jan 2013 • Ian Lenz, Honglak Lee, Ashutosh Saxena
We consider the problem of detecting robotic grasps in an RGB-D view of a scene containing objects.
Ranked #7 on Robotic Grasping on Cornell Grasp Dataset
no code implementations • 4 Oct 2012 • Hema Swetha Koppula, Rudhir Gupta, Ashutosh Saxena
Given a RGB-D video, we jointly model the human activities and object affordances as a Markov random field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time.
Ranked #3 on Skeleton Based Action Recognition on CAD-120
1 code implementation • 2012 IEEE International Conference on Robotics and Automation 2012 • Jaeyong Sung, Colin Ponce, Bart Selman, Ashutosh Saxena
Being able to detect and recognize human activities is essential for several applications, including personal assistive robotics.
no code implementations • NeurIPS 2011 • Cong-Cong Li, Ashutosh Saxena, Tsuhan Chen
For most scene understanding tasks (such as object detection or depth estimation), the classifiers need to consider contextual information in addition to the local features.
no code implementations • NeurIPS 2011 • Hema S. Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena
In our experiments over a total of 52 3D scenes of homes and offices (composed from about 550 views, having 2495 segments labeled with 27 object classes), we get a performance of 84. 06% in labeling 17 object classes for offices, and 73. 38% in labeling 17 object classes for home scenes.
no code implementations • NeurIPS 2010 • Cong-Cong Li, Adarsh Kowdle, Ashutosh Saxena, Tsuhan Chen
In many machine learning domains (such as scene understanding), several related sub-tasks (such as scene categorization, depth estimation, object detection) operate on the same raw data and provide correlated outputs.
no code implementations • NeurIPS 2008 • Geremy Heitz, Stephen Gould, Ashutosh Saxena, Daphne Koller
We demonstrate the effectiveness of our method on a large set of natural images by combining the subtasks of scene categorization, object detection, multiclass image segmentation, and 3d scene reconstruction.