Search Results for author:
Found 20 papers, 6 papers with code
LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping
We evaluate our object pose estimation approach on the ShapeNet dataset and show improvements over the state of the art.
Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysis
This, in turn, requires optimization over the permutation group, made challenging by differences in nodes (in terms of numbers, locations) and edges (in terms of shapes, placements, and sizes) across objects.
Reducing Training Demands for 3D Gait Recognition with Deep Koopman Operator Constraints
Deep learning research has made many biometric recognition solution viable, but it requires vast training data to achieve real-world generalization.
Actor-centered Representations for Action Localization in Streaming Videos
We tackle the problem of learning actor-centered representations through the notion of continual hierarchical predictive learning to localize actions in streaming videos without the need for training labels and outlines for the objects in the video.
Measuring economic activity from space: a case study using flying airplanes and COVID-19
This work introduces a novel solution to measure economic activity through remote sensing for a wide range of spatial areas.
Spatio-Temporal Event Segmentation and Localization for Wildlife Extended Videos
We present a self-supervised perceptual prediction framework capable of temporal event segmentation by building stable representations of objects over time and demonstrate it on long videos, spanning several days.
Measuring Human and Economic Activity from Satellite Imagery to Support City-Scale Decision-Making during COVID-19 Pandemic
We also show results on real examples of different sites before and after the COVID-19 outbreak to illustrate different measurable indicators.
Action Localization through Continual Predictive Learning
It does not require any training annotations in terms of frame-level bounding boxes.
A Quotient Space Formulation for Generative Statistical Analysis of Graphical Data
Complex analyses involving multiple, dependent random quantities often lead to graphical models - a set of nodes denoting variables of interest, and corresponding edges denoting statistical interactions between nodes.
Abductive Reasoning as Self-Supervision for Common Sense Question Answering
We find that large amounts of training data are necessary, both for pre-training as well as fine-tuning to a task, for the models to perform well on the designated task.
The Unconstrained Ear Recognition Challenge 2019 - ArXiv Version With Appendix
The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i. e. gender and ethnicity.
A Perceptual Prediction Framework for Self Supervised Event Segmentation
We also show that the proposed approach is able to learn highly discriminative features that help improve action recognition when used in a representation learning paradigm.
Resource-Constrained Simultaneous Detection and Labeling of Objects in High-Resolution Satellite Images
We describe a strategy for detection and classification of man-made objects in large high-resolution satellite photos under computational resource constraints.
A method to Suppress Facial Expression in Posed and Spontaneous Videos
We address the problem of suppressing facial expressions in videos because expressions can hinder the retrieval of important information in applications such as face recognition.
Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification
With this framework, we were able to reduce the training time while maintaining the classification performance of the ensemble.
Employing Fusion of Learned and Handcrafted Features for Unconstrained Ear Recognition
We used the results generated to perform a geometric image normalization that boosted the performance of all evaluated descriptors.
Going Deeper with Semantics: Video Activity Interpretation using Semantic Contextualization
Through extensive experiments, we show that the use of commonsense knowledge from ConceptNet allows the proposed approach to handle various challenges such as training data imbalance, weak features, and complex semantic relationships and visual scenes.
Learning camera viewpoint using CNN to improve 3D body pose estimation
The objective of this work is to estimate 3D human pose from a single RGB image.
Temporally Coherent Interpretations for Long Videos Using Pattern Theory
Graph-theoretical methods have successfully provided semantic and structural interpretations of images and videos.
Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition
We apply this framework to the problem of speech recognition using both audio and visual components.
