Search Results for author:
Found 29 papers, 1 papers with code
Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture
Current state-of-the-art methods fail to generate realistic animation from any speech on unknown faces due to their poor gen-eralization over different facial characteristics, languages, and accents.
Anticipate & Act : Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments
Assistive agents performing household tasks such as making the bed or cooking breakfast often compute and execute actions that accomplish one task at a time.
MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation
It consists of a training-free action-prior based geometric VO module that estimates a coarse relative pose which is further consumed as a motion prior by a deep-learned VO model, which finally produces a fine relative pose to be used by the navigation policy.
Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos
Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability of annotated data.
Exploring Social Motion Latent Space and Human Awareness for Effective Robot Navigation in Crowded Environments
This work proposes a novel approach to social robot navigation by learning to generate robot controls from a social motion latent space.
Sequence-Agnostic Multi-Object Navigation
The Multi-Object Navigation (MultiON) task requires a robot to localize an instance (each) of multiple object classes.
Object Goal Navigation Based on Semantics and RGB Ego View
This paper presents an architecture and methodology to empower a service robot to navigate an indoor environment with semantic decision making, given RGB ego view.
Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigation
This paper describes a framework for the object-goal navigation task, which requires a robot to find and move to the closest instance of a target object class from a random starting position.
Object Goal Navigation using Data Regularized Q-Learning
Our framework incrementally builds a semantic map of the environment over time, and then repeatedly selects a long-term goal ('where to go') based on the semantic map to locate the target object instance.
DoRO: Disambiguation of referred object for embodied agents
Given an area where the intended object is, DoRO finds all the instances of the object by aggregating observations from multiple views while exploring & scanning the area.
Emotion-Controllable Generalized Talking Face Generation
We propose a graph convolutional neural network that uses speech content feature, along with an independent emotion input to generate emotion and speech-induced motion on facial geometry-aware landmark representation.
Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot
The utility of collocating robots largely depends on the easy and intuitive interaction mechanism with the human.
Simple means Faster: Real-Time Human Motion Forecasting in Monocular First Person Videos on CPU
To the best of our knowledge, we are the first to accurately forecast trajectories at a very high prediction rate of 78 trajectories per second on CPU.
A Novel RF-assisted-Strobe System for Unobtrusive Vibration Detection of Machine Parts
In this paper, we propose a novel non-contact vibration measurement system that is competent in estimating linear and/or rotational motions of machine parts.
Identity-Preserving Realistic Talking Face Generation
The necessary attributes of having a realistic face animation are 1) audio-visual synchronization (2) identity preservation of the target individual (3) plausible mouth movements (4) presence of natural eye blinks.
MOMBAT: Heart Rate Monitoring from Face Video using Pulse Modeling and Bayesian Tracking
We alleviate these issues by proposing a novel face video based HR monitoring method MOMBAT, that is, MOnitoring using Modeling and BAyesian Tracking.
Variational Clustering: Leveraging Variational Autoencoders for Image Clustering
Since we wish to efficiently discriminate between different clusters in the data, we propose a method based on VAEs where we use a Gaussian Mixture prior to help cluster the images accurately.
Integrating Objects into Monocular SLAM: Line Based Category Specific Models
The proposed parameterization associates 3D category-specific CAD model and object under consideration using a dictionary based RANSAC method that uses object Viewpoints as prior and edges detected in the respective intensity image of the scene.
Robotics
Lifting 2d Human Pose to 3d : A Weakly Supervised Approach
Few approaches have utilized training images from both 3d and 2d pose datasets in a weakly-supervised manner for learning 3d poses in unconstrained settings.
Indoor dense depth map at drone hovering
Autonomous Micro Aerial Vehicles (MAVs) gained tremendous attention in recent years.
3D point cloud registration with shape constraint
The proposed algorithm is shown to perform better in the presence of big rotation, structured and unstructured outliers and missing data.
Deep Representation Learning Characterized by Inter-class Separation for Image Clustering
Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks.
Edge SLAM: Edge Points Based Monocular Visual SLAM
Feature based visual SLAMs do not produce reliable camera and structure estimates due to insufficient features in a low-textured environment.
Coupled Analysis Dictionary Learning to inductively learn inversion: Application to real-time reconstruction of Biomedical signals
This work addresses the problem of reconstructing biomedical signals from their lower dimensional projections.
Motion Blur removal via Coupled Autoencoder
In this work, we propose a new formulation that recasts deblurring as a transfer learning problem, it is solved using the proposed coupled autoencoder.
Learning to Prevent Monocular SLAM Failure using Reinforcement Learning
Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment.
Robotics
Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences
The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way.
SfMLearner++: Learning Monocular Depth & Ego-Motion using Meaningful Geometric Constraints
We propose a method using Epipolar constraints to make the learning more geometrically sound.
Constructing Category-Specific Models for Monocular Object-SLAM
These category models are instance-independent and aid in the design of object landmark observations that can be incorporated into a generic monocular SLAM framework.
