Search Results for author:
Found 19 papers, 4 papers with code
Regressing Transformers for Data-efficient Visual Place Recognition
Visual place recognition is a critical task in computer vision, especially for localization and navigation systems.
Data-efficient Large Scale Place Recognition with Graded Similarity Supervision
Motivated by the fact that two images of the same place only partially share visual cues due to camera pose differences, we deploy an automatic re-annotation strategy to re-label VPR datasets.
Ranked #1 on
Visual Place Recognition
on MSLS
Generalized Contrastive Optimization of Siamese Networks for Place Recognition
We propose a Generalized Contrastive loss (GCL) function that relies on image similarity as a continuous measure, and use it to train a siamese CNN.
Ranked #3 on
Visual Place Recognition
on Mapillary test
Inhibition-augmented ConvNets
The rectified responses of the push and pull filter pairs are then combined by a linear function.
MTStereo 2.0: improved accuracy of stereo depth estimation withMax-trees
Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems.
Place recognition in gardens by learning visual representations: data set and benchmark analysis
In this paper we propose an extended version of the TB-Places data set, which is designed for testing algorithms for visual place recognition.
Unsupervised routine discovery in egocentric photo-streams
The routine of a person is defined by the occurrence of activities throughout different days, and can directly affect the person's health.
Towards Unsupervised Familiar Scene Recognition in Egocentric Videos
Nowadays, there is an upsurge of interest in using lifelogging devices.
Towards Emotion Retrieval in Egocentric PhotoStream
The availability and use of egocentric data are rapidly increasing due to the growing use of wearable cameras.
Towards Egocentric Person Re-identification and Social Pattern Analysis
We propose a model that enables us to evaluate and visualize social traits obtained by analysing social interactions appearance within egocentric photostreams.
Hierarchical approach to classify food scenes in egocentric photo-streams
Recent studies have shown that the environment where people eat can affect their nutritional behaviour.
A Push-Pull Layer Improves Robustness of Convolutional Neural Networks
We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images.
Learning sound representations using trainable COPE feature extractors
We construct a set of COPE feature extractors, configured on a number of training patterns.
Brain-inspired robust delineation operator
This type of inhibition allows for sharper detection of the patterns of interest and improves the quality of delineation especially in images with spurious texture.
Action recognition by learning pose representations
Starting from this consideration, we propose a trainable pose detector, that can be configured on a prototype skeleton in an automatic configuration process.
Detection of curved lines with B-COSFIRE filters: A case study on crack delineation
The detection of curvilinear structures is an important step for various computer vision applications, ranging from medical image analysis for segmentation of blood vessels, to remote sensing for the identification of roads and rivers, and to biometrics and robotics, among others.
Delineation of line patterns in images using B-COSFIRE filters
Delineation of line patterns in images is a basic step required in various applications such as blood vessel detection in medical images, segmentation of rivers or roads in aerial images, detection of cracks in walls or pavements, etc.
Sentiment Recognition in Egocentric Photostreams
Lifelogging is a process of collecting rich source of information about daily life of people.
Training a Convolutional Neural Network for Appearance-Invariant Place Recognition
In order for the network to learn the desired invariances, we train it with triplets of images selected from datasets which present a challenging variability in visual appearance.
