Convolutional Neural Networks (CNN) are known to exhibit poor generaliza...
Despite progress in vision-based inspection algorithms, real-world indus...
Few-shot object detection, the problem of modelling novel object detecti...
We present StreamDEQ, a method that infers frame-wise representations on...
Data shift robustness has been primarily investigated from a fully super...
This paper tackles the problem of zero-shot sign language recognition
(Z...
Over the last couple of years few-shot learning (FSL) has attracted grea...
Just like other few-shot learning problems, few-shot segmentation aims t...
Image caption generation is one of the most challenging problems at the
...
Multisource image analysis that leverages complementary spectral, spatia...
In many real-world problems, there is typically a large discrepancy betw...
Machine learning (ML) systems have introduced significant advances in va...
Large-scale datasets play a fundamental role in training deep learning
m...
Image caption generation is a long standing and challenging problem at t...
We introduce the problem of zero-shot sign language recognition (ZSSLR),...
In this work, we propose a zero-shot learning method to effectively mode...
In this paper we investigate learning visual models for the steps of ord...
Fine-grained object recognition concerns the identification of the type ...
With the introduction of large-scale datasets and deep learning models
c...
Object detection is considered as one of the most challenging problems i...
Fine-grained object recognition that aims to identify the type of an obj...
We propose a novel approach for unsupervised zero-shot learning (ZSL) of...
The bag-of-words (BoW) model treats images as sets of local descriptors ...
Object category localization is a challenging problem in computer vision...