Search Results for author:
Found 59 papers, 19 papers with code
Personalized Search-based Query Rewrite System for Conversational AI
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect.
Contextual Rephrase Detection for Reducing Friction in Dialogue Systems
Rephrase detection is used to identify the rephrases and has long been treated as a task with pairwise input, which does not fully utilize the contextual information (e. g. users’ implicit feedback).
BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization
Most of these adversarial attack strategies assume that the adversary has access to the training data, the model parameters, and the input during deployment, hence, focus on perturbing the pixel level information present in the input image.
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation.
Opening Cabinets and Drawers in the Real World using a Commodity Mobile Manipulator
In this work, we build an end-to-end system that enables a commodity mobile manipulator (Stretch RE2) to pull open cabinets and drawers in diverse previously unseen real world environments.
Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning
The Dataset Aggregation, or DAgger approach to this problem simply collects more data to cover these failure states.
Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops
Objects undergo varying amounts of perspective distortion as they move across a camera's field of view.
3D Hand Pose Estimation in Egocentric Images in the Wild
We present WildHands, a method for 3D hand pose estimation in egocentric images in the wild.
Bootstrapping Autonomous Driving Radars with Self-Supervised Learning
The perception of autonomous vehicles using radars has attracted increased research interest due its ability to operate in fog and bad weather.
ContactGen: Generative Contact Modeling for Grasp Generation
This paper presents a novel object-centric contact representation ContactGen for hand-object interaction.
Push Past Green: Learning to Look Behind Plant Foliage by Moving It
We use self-supervision to train SRPNet, a neural network that predicts what space is revealed on execution of a candidate action on a given plant.
Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds
We build rearticulable models for arbitrary everyday man-made objects containing an arbitrary number of parts that are connected together in arbitrary ways via 1 degree-of-freedom joints.
Learning Hand-Held Object Reconstruction from In-The-Wild Videos
Prior works for reconstructing hand-held objects from a single image rely on direct 3D shape supervision which is challenging to gather in real world at scale.
Predicting Motion Plans for Articulating Everyday Objects
Our key insight is to cast it as a learning problem to leverage past experience of solving similar planning problems to directly predict motion plans for mobile manipulation tasks in novel situations at test time.
One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation
In this paper, we analyze the behavior of existing techniques and design new solutions for the problem of one-shot visual imitation.
TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
We introduce TIDEE, an embodied agent that tidies up a disordered scene based on learned commonsense object placement and room arrangement priors.
Learning Value Functions from Undirected State-only Experience
We show that LAQ can recover value functions that have high correlation with value functions learned using ground truth actions.
Detection of Distracted Driver using Convolution Neural Network
With over 50 million car sales annually and over 1. 3 million deaths every year due to motor accidents we have chosen this space.
Human Hands as Probes for Interactive Object Understanding
Analyzing the hands shows what we can do to objects and how.
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency
The observations gathered by this exploration policy are labelled using 3D consistency and used to improve the perception model.
Learned Visual Navigation for Under-Canopy Agricultural Robots
We describe a system for visually guided autonomous navigation of under-canopy farm robots.
Viable Threat on News Reading: Generating Biased News Using Natural Language Models
Recent advancements in natural language generation has raised serious concerns.
imdpGAN: Generating Private and Specific Data with Generative Adversarial Networks
With experiments on MNIST dataset, we show that imdpGAN preserves the privacy of the individual data point, and learns latent codes to control the specificity of the generated samples.
Multi-objective Reinforcement Learning based approach for User-Centric Power Optimization in Smart Home Environments
We experiment on real-world smart home data, and show that the multi-objective approaches: i) establish trade-off between the two objectives, ii) achieve better combined user satisfaction and power consumption than single-objective approaches.
Aligning Videos in Space and Time
During training, given a pair of videos, we compute cycles that connect patches in a given frame in the first video by matching through frames in the second video.
Semantic Visual Navigation by Watching YouTube Videos
Semantic cues and statistical regularities in real-world environment layouts can improve efficiency for navigation in novel environments.
Semantic Curiosity for Active Visual Learning
Instead, we explore a self-supervised approach for training our exploration policy by introducing a notion of semantic curiosity.
Neural Topological SLAM for Visual Navigation
This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment.
Learning to Explore using Active Neural SLAM
The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation (in local policies).
Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
Our quantitative and qualitative results show that (a) we can predict meaningful forces from videos whose effects lead to accurate imitation of the motions observed, (b) by jointly optimizing for contact point and force prediction, we can improve the performance on both tasks in comparison to independent training, and (c) we can learn a representation from this model that generalizes to novel objects using few shot examples.
Intrinsic Motivation for Encouraging Synergistic Behavior
Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own.
Learning to Move with Affordance Maps
In this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners.
Making Smart Homes Smarter: Optimizing Energy Consumption with Human in the Loop
Rapid advancements in the Internet of Things (IoT) have facilitated more efficient deployment of smart environment solutions for specific user requirement.
DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning
DeepRacer is a platform for end-to-end experimentation with RL and can be used to systematically investigate the key challenges in developing intelligent control systems.
FineText: Text Classification via Attention-based Language Model Fine-tuning
Training deep neural networks from scratch on natural language processing (NLP) tasks requires significant amount of manually labeled text corpus and substantial time to converge, which usually cannot be satisfied by the customers.
Efficient Bimanual Manipulation Using Learned Task Schemas
Our insight is that for many tasks, the learning process can be decomposed into learning a state-independent task schema (a sequence of skills to execute) and a policy to choose the parameterizations of the skills in a state-dependent manner.
Hashtags are (not) judgemental: The untold story of Lok Sabha elections 2019
In the political context, hashtags on Twitter are used by users to campaign for their parties, spread news, or to get followers and get a general idea by following a discussion built around a hashtag.
PyRobot: An Open-source Robotics Framework for Research and Benchmarking
This paper introduces PyRobot, an open-source robotics framework for research and benchmarking.
Learning Navigation Subroutines from Egocentric Videos
We demonstrate our proposed approach in context of navigation, and show that we can successfully learn consistent and diverse visuomotor subroutines from passive egocentric videos.
Combining Optimal Control and Learning for Visual Navigation in Novel Environments
Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories.
Learning Exploration Policies for Navigation
Numerous past works have tackled the problem of task-driven navigation.
Visual Memory for Robust Path Following
Equipped with this abstraction, a second network observes the world and decides how to act to retrace the path under noisy actuation and a changing environment.
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data
We train a variant of Mask R-CNN with domain randomization on the generated dataset to perform category-agnostic instance segmentation without any hand-labeled data and we evaluate the trained network, which we refer to as Synthetic Depth (SD) Mask R-CNN, on a set of real, high-resolution depth images of challenging, densely-cluttered bins containing objects with highly-varied geometry.
Ranked #1 on
Unseen Object Instance Segmentation
on WISDOM
On Evaluation of Embodied Navigation Agents
Skillful mobile operation in three-dimensional environments is a primary topic of study in Artificial Intelligence.
Unifying Map and Landmark Based Representations for Visual Navigation
This works presents a formulation for visual navigation that unifies map based spatial reasoning and path planning, with landmark based robust plan execution in noisy environments.
Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene
The goal of this paper is to take a single 2D image of a scene and recover the 3D structure in terms of a small set of factors: a layout representing the enclosing surfaces as well as a set of objects represented in terms of shape and pose.
Cognitive Mapping and Planning for Visual Navigation
The accumulated belief of the world enables the agent to track visited regions of the environment.
Learning With Side Information Through Modality Hallucination
Thus, our method transfers information commonly extracted from depth training data to a network which can extract that information from the RGB counterpart.
Exploring Person Context and Local Scene Context for Object Detection
In this paper we explore two ways of using context for object detection.
Cross Modal Distillation for Supervision Transfer
In this work we propose a technique that transfers supervision between images from different modalities.
Aligning 3D Models to RGB-D Images of Cluttered Scenes
The goal of this work is to represent objects in an RGB-D scene with corresponding 3D models from a library.
Exploring Nearest Neighbor Approaches for Image Captioning
We explore a variety of nearest neighbor baseline approaches for image captioning.
Visual Semantic Role Labeling
In this paper we introduce the problem of Visual Semantic Role Labeling: given an image we want to detect people doing actions and localize the objects of interaction.
Language Models for Image Captioning: The Quirks and What Works
Two recent approaches have achieved state-of-the-art results in image captioning.
Microsoft COCO Captions: Data Collection and Evaluation Server
In this paper we describe the Microsoft COCO Caption dataset and evaluation server.
Inferring 3D Object Pose in RGB-D Images
The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library.
From Captions to Visual Concepts and Back
The language model learns from a set of over 400, 000 image descriptions to capture the statistics of word usage.
Ranked #1 on
Image Captioning
on COCO Captions test
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features.
Ranked #6 on
Object Detection In Indoor Scenes
on SUN RGB-D
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
We address the problems of contour detection, bottomup grouping and semantic segmentation using RGB-D data.
