Search Results for author:
Found 35 papers, 8 papers with code
3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization
This paper presents a novel system designed for 3D mapping and visual relocalization using 3D Gaussian Splatting.
SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images
This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera.
Ranked #1 on
Monocular Depth Estimation
on Cityscapes
BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
Following the success of Proximal Policy Optimization (PPO) for Reinforcement Learning from Human Feedback (RLHF), new techniques such as Sequence Likelihood Calibration (SLiC) and Direct Policy Optimization (DPO) have been proposed that are offline in nature and use rewards in an indirect manner.
eipy: An Open-Source Python Package for Multi-modal Data Integration using Heterogeneous Ensembles
In this paper, we introduce eipy--an open-source Python package for developing effective, multi-modal heterogeneous ensembles for classification.
RGB-X Object Detection via Scene-Specific Fusion Modules
Multimodal deep sensor fusion has the potential to enable autonomous vehicles to visually understand their surrounding environments in all weather conditions.
Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network
In this paper, we present a Stereo Visual Odometry (StereoVO) technique based on point and line features which uses a novel feature-matching mechanism based on an Attention Graph Neural Network that is designed to perform well even under adverse weather conditions such as fog, haze, rain, and snow, and dynamic lighting conditions such as nighttime illumination and glare scenarios.
Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras
We propose a novel and pragmatic framework for traffic scene perception with roadside cameras.
Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems
The rapidly growing market demand for automatic dialogue agents capable of goal-oriented behavior has caused many tech-industry leaders to invest considerable efforts into task-oriented dialog systems.
Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings
In this paper, we combine the best of both worlds by proposing a scalable model that can learn complex relationships between context-response pairs.
Variational Learning for Unsupervised Knowledge Grounded Dialogs
Recent methods for knowledge grounded dialogs generate responses by incorporating information from an external textual document.
Developing parsimonious ensembles using predictor diversity within a reinforcement learning framework
Heterogeneous ensembles that can aggregate an unrestricted number and variety of base predictors can effectively address challenging prediction problems.
Real Time Incremental Foveal Texture Mapping for Autonomous Vehicles
We propose an end-to-end real time framework to generate high resolution graphics grade textured 3D map of urban environment.
Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions
Popular dialog datasets such as MultiWOZ are created by providing crowd workers an instruction, expressed in natural language, that describes the task to be accomplished.
Ford Highway Driving RTK Dataset: 30,000 km of North American Highways
There is a growing need for vehicle positioning information to support Advanced Driver Assistance Systems (ADAS), Connectivity (V2X), and Autonomous Driving (AD) features.
Agent Assist through Conversation Analysis
Customer support agents play a crucial role as an interface between an organization and its end-users.
Unravelling the Architecture of Membrane Proteins with Conditional Random Fields
In this paper, we will show that the recently introduced graphical model: Conditional Random Fields (CRF) provides a template to integrate micro-level information about biological entities into a mathematical model to understand their macro-level behavior.
SEIR and Regression Model based COVID-19 outbreak predictions in India
In this study, outbreak of this disease has been analysed for India till 30th March 2020 and predictions have been made for the number of cases for the next 2 weeks.
Aerial Imagery based LIDAR Localization for Autonomous Vehicles
This paper presents a localization technique using aerial imagery maps and LIDAR based ground reflectivity for autonomous vehicles in urban environments.
Ford Multi-AV Seasonal Dataset
This paper presents a challenging multi-agent seasonal dataset collected by a fleet of Ford autonomous vehicles at different days and times during 2017-18.
Mask & Focus: Conversation Modelling by Learning Concepts
The proposed model, referred to as Mask \& Focus maps the input context to a sequence of concepts which are then used to generate the response concepts.
Deep-Geometric 6 DoF Localization from a Single Image in Topo-metric Maps
We describe a Deep-Geometric Localizer that is able to estimate the full 6 Degree of Freedom (DoF) global pose of the camera from a single image in a previously mapped environment.
DHSGAN: An End to End Dehazing Network for Fog and Smoke
In this paper we propose a novel end-to-end convolution dehazing architecture, called De-Haze and Smoke GAN (DHSGAN).
Deep Discriminative Learning for Unsupervised Domain Adaptation
In contrast, we propose an approach that directly addresses the problem of learning a classifier in the unlabeled target domain.
Unsupervised Learning of Interpretable Dialog Models
However these states need to be handcrafted and annotated in the data.
Developing parsimonious ensembles using ensemble diversity within a reinforcement learning framework
Ensemble selection is an especially promising approach here, not only for improving prediction performance, but also because of its ability to select a collectively predictive subset, often a relatively small one, of the base predictors.
Motion Guided LIDAR-camera Self-calibration and Accelerated Depth Upsampling for Autonomous Vehicles
This work proposes a novel motion guided method for target-less self-calibration of a LiDAR and camera and use the re-projection of LiDAR points onto the image reference frame for real-time depth upsampling.
Compact Environment-Invariant Codes for Robust Visual Place Recognition
The modified system learns (in a supervised setting) compact binary codes from image feature descriptors.
Unsupervised feature learning with discriminative encoder
How can one use the same discriminative models for learning useful features in the absence of labels?
Learning to segment with image-level supervision
In this paper, we propose a model that generates auxiliary labels for each image, while simultaneously forcing the output of the CNN to satisfy the mean-field constraints imposed by a conditional random field.
Discriminative Neural Topic Models
We propose a neural network based approach for learning topics from text and image datasets.
Variational methods for Conditional Multimodal Deep Learning
We use the proposed model to generate faces from attributes.
On collapsed representation of hierarchical Completely Random Measures
The aim of the paper is to provide an exact approach for generating a Poisson process sampled from a hierarchical CRM, without having to instantiate the infinitely many atoms of the random measures.
To go deep or wide in learning?
To achieve acceptable performance for AI tasks, one can either use sophisticated feature extraction methods as the first layer in a two-layered supervised learning model, or learn the features directly using a deep (multi-layered) model.
A Comparative Analysis of Ensemble Classifiers: Case Studies in Genomics
The combination of multiple classifiers using ensemble methods is increasingly important for making progress in a variety of difficult prediction problems.
Generative Maximum Entropy Learning for Multiclass Classification
In this paper, we introduce a maximum entropy classification method with feature selection for large dimensional data such as text datasets that is generative in nature.
