Feature Extraction
By Matthew Henderson, Milica Gasic, Blaise Thomson, Pirros Tsiakoulis, Kai Yu, Susannah Young. 2021
313 citations recorded by the source corpus.
This technical memo is part of a study to develop and test tools and techniques for improved accuracy, reliability and automation of shoreline delineation and feature extraction, with particular emphasis on the arctic environment. This memo details the RADARSAT imagery and extensive ground truth collected during the spring and summer of 2002 in CFS Alert, Nunavut. The ground truth includes deployment of four radar comer reflectors, measurement of several shorelines and a large variety of other tracks, measurement of a large variety of permanent scatterers and targets of opportunity, extensive photographic record, comparison of the measured and modeled tide at CFS Alert, and plots of the weather during the time period concerned.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Milica Gasic
- Susannah Young
- Tsung-Hsien Wen
- Pei-hao Su
- Giorgio Giacinto
- Davide Maiorca
- Nikola Mrksic
- Dongho Kim
Citations in the corpus
- Towards Adversarial Malware Detection (2018, background): “However, as such objects are also widely used in benign files, it may be quite hard to establish the maliciousness of the file by only inspecting them.”
- Learning from real users: rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems (2015, methodology): “The shared core components of the SDS used over all experiments were a domain independent ASR, a confusion network (CNet) semantic input decoder [28], the BUDS [19] belief state tracker that factorises the dialogue state using a dynamic Bayesian network and a template based NLG of the systems semant”
- Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems (2015, methodology): “The shared core components of the SDS in all experiments were a domain independent ASR, a confusion network (CNet) semantic input decoder (Henderson et al., 2012), the BUDS (Thomson and Young, 2010) belief state tracker that factorises the dialogue state using a dynamic Bayesian network and a templa”
- The third Dialog State Tracking Challenge (2014, methodology): “Labelling of the dialog state is facilitated by first labelling each user utterance with its semantic representation, in the dialog act format described in [13].”