86 citations · 184 across the 7 of their papers we have counts for
7 papers
Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling
Kavisha Vidanapathirana, Peyman Moghadam, Ben Harwood +3
Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper…
Delta Descriptors: Change-Based Place Representation for Robust Visual Localization
Sourav Garg, Ben Harwood, Gaurangi Anand +1
Visual place recognition is challenging because there are so many factors that can cause the appearance of a place to change, from day-night cycles to seasonal change to atmospheri…
Temporally Coherent Embeddings for Self-Supervised Video Representation Learning
Joshua Knights, Ben Harwood, Daniel Ward +3
This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data t…
Generalised Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space
Rafael Felix, Ben Harwood, Michele Sasdelli +1
Generalised zero-shot learning (GZSL) is a classification problem where the learning stage relies on a set of seen visual classes and the inference stage aims to identify both the…
Generalised Zero-Shot Learning with a Classifier Ensemble over Multi-Modal Embedding Spaces
Rafael Felix, Ben Harwood, Michele Sasdelli +1
Generalised zero-shot learning (GZSL) methods aim to classify previously seen and unseen visual classes by leveraging the semantic information of those classes. In the context of G…
Deep Metric Learning and Image Classification with Nearest Neighbour Gaussian Kernels
Benjamin J. Meyer, Ben Harwood, Tom Drummond
We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classifi…
Smart Mining for Deep Metric Learning
Ben Harwood, Vijay Kumar B G, Gustavo Carneiro +2
To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples f…