22 October 2020
Three papers published at CLEF 2020 Working Notes
Three papers have been published in the CLEF (Conference and Labs of Evaluation Forum) 2020 Working Notes. The “Overview of the ImageCLEFmed 2020 Concept Prediction Task: Medical Image Understanding” by Obioma Pelka, Christoph M. Friedrich, Alba García Seco De Herrera and Henning Müller; The “Overview of the ImageCLEFcoral 2020 Task: Automated Coral Reef Image Annotation” by Jon Chamberlain, Antonio Campello, Jessica Wright, Louis Clift, Adrian Clark and Alba García Seco De Herrera; and the “Essex at ImageCLEFcaption 2020 Task” by Alba García Seco De Herrera, Francisco Parrilla Andrade, Luke Bentley and Arely Aceves Compean. They are avalaible here.
19 October 2020
Our study on Thai Syllable Recognition is accepted in IEEE Journal of Biomedical and Health Informatics
Our paper entitled “Multimodal Data Fusion of Electromyography and Acoustic Signals for Thai Syllable Recognition” by Nida Sae Jong, Alba G. Seco de Herrera and Pornchai Phukpattaranont has been accepted for publication in the IEEE Journal of Biomedical and Health Informatics (J-BHI). This work is the result of the research visit of Nida Sae Jong at University of Essex and the collaboration with the Prince of Songkla University.
6 October 2020
University of Essex Innovation Voucher approved
The University of Essex Innovation Voucher has granted £9,906.28 to work on a “Check4Cancer skin cancer AI model” project to use Artificial Intelligence for Diagnosis of Skin Cancer. Dr Haider Raza, Prof. John Gan and Dr Alba García Seco de Herrera are involve in this project.
22 September 2020
Jon Chamberlain talked at CLEF 2020
14 September 2020
A paper on “Multimodal Deep Features Fusion For Video Memorability Prediction” is been published in MediaEval 2019 – Multimedia Benchmark Workshop
Our paper entitled “Multimodal Deep Features Fusion For Video Memorability Prediction” by Roberto Leyva, Faiyaz Doctor, Alba G. Seco de Herrera and Sohail Sahab has been published in MediaEval 2019 – Multimedia Benchmark Workshop. Available here.
10 August 2020
Registration for the MediaEval2020 Predicting Media Memorability Task is now open
The NLIP group, in collaboration with international institutions, is organising the MediaEval2020 Predicting Media Memorability task.
MediaEval2020 Predicting Media Memorability Task https://multimediaeval.github.io/editions/2020/tasks/memorability/ requires participants to automatically predict memorability scores for videos, which reflect the probability of a video being remembered. In contrast to previous work on visual memorability prediction, where memorability was measured a few minutes after memorization, the task requires both ‘short-term’ and ‘long-term’ memorability predictions.New for 2020 is the data set composed of 6,000 short videos retrieved from TRECVid 2019 Video to Text data set. Each video consists of a coherent unit in terms of meaning. In comparison to the videos used in this task in 2018 and 2019, the TRECVid videos have much more action happening in them and thus are more interesting for subjects to view.Participants to the task are invited to present their results during the annual MediaEval Workshop, which will be held online in early December 2020. Working notes proceedings are to appear with CEUR Workshop Proceedings (ceur-ws.org).
Register here to participate: https://multimediaeval.github.io/editions/2020/
If you are willing to help us with the annotations, use the following link: https://annotator.uk/mediaeval/
16 June 2020
4 members of the NLIP group are the winners of Early Career Researcher Award
Jon Chamberlain, Jessica Wright, Alba García Seco de Herrera and Louis Clift are the winners of the Early Career Researcher Award, for the Faculty of Science and Health, for the University of Essex’s Celebrating Excellence in Research and Impact Awards 2020.
12 June 2020
Essex team ranked 3rd in the ImageCLEFcaption 2020 challenge
ImageCLEF is an evaluation campaign that is being organized as part of the CLEF initiative labs. The campaign offers several research tasks that welcome participation from teams around the world. Based on the visual image content, ImageCLEFcaption 2020 task provides the building blocks for medical image understanding step by identifying the individual components from which captions are composed. The concepts can be further applied for context-based image and information retrieval purposes. The approach developed by the Essex team identifies the presence of relevant concepts in a large corpus of medical images with an image retrieval methodology using features extracted via DenseNet-121 model. The Essex team, consisting of Francisco Parrilla Andrade, Luke Bentley, Arely Aceves Compean and Alba García Seco de Herrera, ranked 3rd in the ImageCLEFcaption 2020 challenge.
11 May 2020
“Coronavirus has revealed the power of social networks in a crisis” has been published on The Conversation.
An article by Jon Chamberlain entitled “Coronavirus has revealed the power of social networks in a crisis” has been published on The Conversation. The article discusses how community resilience is facilitated by social networks, enabling them to respond much faster and more effectively than centrally coordinated systems.
4 May 2020
A paper on lexical data augmentation for text classification is been published in Canadian AI 2020
Our paper entitled “Lexical Data Augmentation for Text Classification in Deep Learning” by Rong Xiang, Emmanuele Chersoni, Yunfei Long, Qin Lu and Chu-Ren Huang has been published in Canadian AI 2020 (Canadian Conference on Artificial Intelligence). Available here.
22 April 2020
Congrats. on CBMS 2020 paper acceptance
Congrats. on Ekin’s paper, titled “3D Convolutional Neural Networks for Diagnosis of Alzheimer’s Disease via structural MRI” by Ekin Yagis, Luca Citi, Stefano Diciotti, Chiara Merzi, Selamawet Workalemahu Atnafu and Alba G. Seco De Herrera has been accepted for presentation at CBMS 2020, the IEEE 33rd International Symposium on Computer Based Medical Systems.
2 April 2020
A review paper on segmentation of knee articular cartilage accepted in Artificial Intelligence In Medicine
Our paper entitled “A review on segmentation of knee articular cartilage: from conventional methods towards deep learning” by Somayeh Ebrahimkhania, Mohamed Hisham Jawardb, Flavia M. Cicuttinic, Anuja Dharmaratnea, Yuanyuan Wangc and Alba G. Seco de Herrera has been accepted for publication in Artificial Intelligence In Medicine. Available here.