1 code implementation • Sensors 2023 • Matthew Aquilina, Keith George Ciantar, Christian Galea, Kenneth P. Camilleri, Reuben A. Farrugia, John Abela
To date, the best-performing blind super-resolution (SR) techniques follow one of two paradigms: A) generate and train a standard SR network on synthetic low-resolution - high-resolution (LR - HR) pairs or B) attempt to predict the degradations an LR image has suffered and use these to inform a customised SR network.
1 code implementation • IEEE Signal Processing Letters 2021 • Matthew Aquilina, Christian Galea, John Abela, Kenneth P. Camilleri, Reuben A. Farrugia
While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information, the ill-posed nature of SR can make it difficult to accurately super-resolve an image which has undergone multiple different degradations.
1 code implementation • 9 Nov 2019 • Marc Tanti, Albert Gatt, Kenneth P. Camilleri
We also observe that the merge architecture can have its recurrent neural network pre-trained in a text-only language model (transfer learning) rather than be initialised randomly as usual.
1 code implementation • 1 Jan 2019 • Marc Tanti, Albert Gatt, Kenneth P. Camilleri
When designing a neural caption generator, a convolutional neural network can be used to extract image features.
1 code implementation • 12 Oct 2018 • Marc Tanti, Albert Gatt, Kenneth P. Camilleri
This paper addresses the sensitivity of neural image caption generators to their visual input.
1 code implementation • LREC 2018 • Albert Gatt, Marc Tanti, Adrian Muscat, Patrizia Paggio, Reuben A. Farrugia, Claudia Borg, Kenneth P. Camilleri, Mike Rosner, Lonneke van der Plas
To gain a better understanding of the variation we find in face description and the possible issues that this may raise, we also conducted an annotation study on a subset of the corpus.
4 code implementations • WS 2017 • Marc Tanti, Albert Gatt, Kenneth P. Camilleri
This view suggests that the RNN should only be used to encode linguistic features and that only the final representation should be `merged' with the image features at a later stage.
12 code implementations • 27 Mar 2017 • Marc Tanti, Albert Gatt, Kenneth P. Camilleri
When a recurrent neural network language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN -- conditioning the language model by `injecting' image features -- or in a layer following the RNN -- conditioning the language model by `merging' image features.