S
Selvarajah Thuseethan
Researcher at Deakin University
Publications - 32
Citations - 217
Selvarajah Thuseethan is an academic researcher from Deakin University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 7, co-authored 27 publications receiving 124 citations. Previous affiliations of Selvarajah Thuseethan include Sabaragamuwa University.
Papers
More filters
Journal ArticleDOI
Deep metric learning based citrus disease classification with sparse data
Sivasubramaniam Janarthan,Selvarajah Thuseethan,Sutharshan Rajasegarar,Qiang Lyu,Yongqiang Zheng,John Yearwood +5 more
TL;DR: This work proposes a lightweight, fast, and accurate deep metric learning-based architecture for citrus disease detection from sparse data that comprises an embedding module, a cluster prototype module, and a simple neural network classifier, to detect the citrus diseases accurately.
Journal ArticleDOI
LGAttNet: automatic micro-expression detection using dual-stream local and global attentions
Madhumita A. Takalkar,Selvarajah Thuseethan,Sutharshan Rajasegarar,Zenon Chaczko,Min Xu,John Yearwood +5 more
TL;DR: LGAttNet is one of the first to utilise a dual attention network grouped with 2-dimensional convolutional neural network to perform frame-wise automatic micro-expression detection and demonstrates the robustness and superiority of the LGAttNet when compared to state-of-the-art approaches.
Posted Content
Effective Use of Human Computer Interaction in Digital Academic Supportive Devices
TL;DR: Recommendations to design good human-computer digital academic supportive devices requires applied human computer interaction research and awareness of its issues.
Proceedings ArticleDOI
Emotion Intensity Estimation from Video Frames using Deep Hybrid Convolutional Neural Networks
TL;DR: This work proposes a metric-based intensity estimation mechanism for primary emotions, and a deep hybrid convolutional neural network-based approach to recognise the defined intensities of the primary emotions from spontaneous and posed sequences and extends the intensity estimation approach to detect the basic emotions.
Journal ArticleDOI
Complex emotion profiling: An incremental active learning based approach with sparse annotations
TL;DR: A deep framework to incrementally and actively profile in-the-wild complex emotions, from sparse data, consisting of a pre-processing unit, an optimization unit and an active learning unit is proposed.