Search Results for author:
Found 36 papers, 3 papers with code
MDPs with Unawareness in Robotics
Doing this results in a family of systems, each of which has an extremely large action space, although only a few actions are "interesting".
Learning to Represent Haptic Feedback for Partially-Observable Tasks
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.
Learning Transferrable Representations for Unsupervised Domain Adaptation
Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition.
Human Centred Object Co-Segmentation
Co-segmentation is the automatic extraction of the common semantic regions given a set of images.
Unsupervised Semantic Action Discovery from Video Collections
Our method can also provide a textual description for each of the identified semantic steps and video segments.
Watch-n-Patch: Unsupervised Learning of Actions and Relations
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.
Unsupervised Transductive Domain Adaptation
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.
Robobarista: Learning to Manipulate Novel Objects via Deep Multimodal Embedding
There is a large variety of objects and appliances in human environments, such as stoves, coffee dispensers, juice extractors, and so on.
Brain4Cars: Car That Knows Before You Do via Sensory-Fusion Deep Learning Architecture
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.
Learning Preferences for Manipulation Tasks from Online Coactive Feedback
We consider the problem of learning preferences over trajectories for mobile manipulators such as personal robots and assembly line robots.
Watch-Bot: Unsupervised Learning for Reminding Humans of Forgotten Actions
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.
Hierarchical classification of e-commerce related social media
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.
Exploring Correlation between Labels to improve Multi-Label Classification
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.
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
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
Deep Multimodal Embedding: Manipulating Novel Objects with Point-clouds, Language and Trajectories
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.
Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture
We introduce a sensory-fusion architecture which jointly learns to anticipate and fuse information from multiple sensory streams.
Unsupervised Semantic Parsing of Video Collections
The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps.
Watch-n-Patch: Unsupervised Understanding of Actions and Relations
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.
Robobarista: Object Part based Transfer of Manipulation Trajectories from Crowd-sourcing in 3D Pointclouds
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.
Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models
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.
RoboBrain: Large-Scale Knowledge Engine for Robots
In this paper we introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks.
MDPs with Unawareness
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.
PlanIt: A Crowdsourcing Approach for Learning to Plan Paths from Large Scale Preference Feedback
We represent trajectory preferences using a cost function that the robot learns and uses it to generate good trajectories in new environments.
Learning Trajectory Preferences for Manipulators via Iterative Improvement
In this paper, we propose a co-active online learning framework for teaching robots the preferences of its users for object manipulation tasks.
Synthesizing Manipulation Sequences for Under-Specified Tasks using Unrolled Markov Random Fields
Many tasks in human environments require performing a sequence of navigation and manipulation steps involving objects.
3D-Based Reasoning with Blocks, Support, and Stability
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.
Learning Spatio-Temporal Structure from RGB-D Videos for Human Activity Detection and Anticipation
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
Deep Learning for Detecting Robotic Grasps
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
Learning Human Activities and Object Affordances from RGB-D Videos
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
Unstructured Human Activity Detection from RGBD Images
Being able to detect and recognize human activities is essential for several applications, including personal assistive robotics.
\theta-MRF: Capturing Spatial and Semantic Structure in the Parameters for Scene Understanding
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.
Semantic Labeling of 3D Point Clouds for Indoor Scenes
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.
Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models
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.
Cascaded Classification Models: Combining Models for Holistic Scene Understanding
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.
