Publications
8 journal articles · 27 peer-reviewed conference papers
* denotes equal contribution. For the most up-to-date list, see
Google Scholar.
Journal Articles
-
2024
HairNet2: deep learning to quantify cotton leaf hairiness, a complex genetic and environmental traitPlant Methods, Springer Nature, 20:46, 2024
-
2024
Towards automatic anomaly detection in fisheries using electronic monitoring and automatic identification systemFisheries Research, 272:106939, 2024
-
2023
A benthic substrate classification method for seabed images using deep learning: application to management of deep-sea coral reefsJournal of Applied Ecology, 60(7):1254–1273, 2023
-
2022
HairNet — A deep learning model to score leaf hairiness, a key phenotype for cotton fibre yield, value and insect resistancePlant Methods, Springer Nature, 18(1):8, 2022
-
2021
Accuracy vs. Complexity: A Trade-off in Visual Question Answering ModelsPattern Recognition, Elsevier, 120:108106, 2021
-
2020
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic ConceptsImage and Vision Computing, Elsevier, 103:103985, 2020
-
2012
Intensity Reflection Coefficient based Min-Sum decoding for Low Density Parity Check CodesFrequenz — Journal of RF-Engineering and Telecommunications, 66:229–238, 2012
Conference Papers
-
2025
CAPSTONE: Composable Attribute-Prompted Scene Translation for Zero-Shot Vision–Language ReasoningEMNLP 2025 — Empirical Methods in Natural Language Processing (Industry Track), pp. 2840–2851
-
2025
Label Semantics for Robust Hyperspectral Image ClassificationIJCNN 2025 — International Joint Conference on Neural Networks, IEEE
-
2025
Long-tailed Image Classification on the Specimens of Herbarium DatasetIJCNN 2025 — International Joint Conference on Neural Networks, IEEE
-
2025
Beyond the Pipeline: Analyzing Key Factors in End-to-End Deep Learning for Historical Writer IdentificationDSAA 2025 — IEEE 12th International Conference on Data Science and Advanced Analytics
-
2025
Z-Prunear: Post-Training Pruning of Large Language Models for Efficiency without RetrainingAICCSA 2025 — IEEE/ACS 22nd International Conference on Computer Systems and Applications
-
2025
Multi-Modal Sentiment Analysis with Dynamic Attention FusionAICCSA 2025 — IEEE/ACS 22nd International Conference on Computer Systems and Applications
-
2025
Beyond Stars: Bridging the Gap Between Ratings and Review Sentiment with LLMAICCSA 2025 — IEEE/ACS 22nd International Conference on Computer Systems and Applications
-
2025
Dual-Path Phishing Detection: Integrating Transformer-Based NLP with Structural URL AnalysisAICCSA 2025 — IEEE/ACS 22nd International Conference on Computer Systems and Applications
-
2023
REIN: Reusing ImageNet to Improve Open-set Object DetectionDICTA 2023 — International Conference on Digital Image Computing: Techniques and Applications
-
2023
Improving Zero-Shot Semantic Segmentation using Dynamic KernelsDICTA 2023 — International Conference on Digital Image Computing: Techniques and Applications
-
2023
A generative approach to audio-visual generalized zero-shot learning: Combining contrastive and discriminative techniquesIJCNN 2023 — International Joint Conference on Neural Networks, IEEE
-
2023
How much does initialization affect generalization?ICML 2023 — International Conference on Machine Learning (PMLR), pp. 28637–28655
-
2022
Improving Action Quality Assessment Using Weighted AggregationIbPRIA 2022 — Iberian Conference on Pattern Recognition and Image Analysis, Springer
-
2022
VReBERT: A Simple and Flexible Transformer for Visual Relationship DetectionICPR 2022 — International Conference on Pattern Recognition, Montreal, Canada
-
2021
Rethinking conditional GAN training: An approach using geometrically structured latent manifoldsNeurIPS 2021 — Conference on Neural Information Processing Systems, 34:19487–19499
-
2021
Question-agnostic attention for visual question answeringICPR 2020 — International Conference on Pattern Recognition, IEEE, pp. 3542–3549
-
2021
Recursive Training for Zero-Shot Semantic SegmentationIJCNN 2021 — International Joint Conference on Neural Networks, IEEE
-
2021
Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMIJCNN 2021 — International Joint Conference on Neural Networks, IEEE
-
2018
Reciprocal Attention Fusion for Visual Question AnsweringBMVC 2018 — 29th British Machine Vision Conference, Newcastle upon Tyne, UK
-
2016
Inpainting multiple sclerosis lesions for improving registration performance with brain atlasMediTec 2016 — International Conference on Medical Engineering, Health Informatics and Technology, Dhaka
-
2015
A 3D Dynamic Biomechanical Swallowing Model for Training and Diagnosis of DysphagiaISBI 2015 — International Symposium on Biomedical Imaging, Brooklyn, USA
-
2015
Subject-Specific Biomechanical Modelling of the Oropharynx with Application to Speech ProductionISBI 2015 — International Symposium on Biomedical Imaging, Brooklyn, USA
-
2015
Development of a 3D Biomechanical Swallowing Model for Dysphagia TrainingCMBBE 2015 — 13th International Symposium on Computer Methods in Biomechanics and Biomedical Engineering, Montreal
-
2014
Swallowing Simulation Using an MBSImP-Based 3D Biomechanical ModelCMBBE 2014 — 12th International Symposium on Computer Methods in Biomechanics and Biomedical Engineering, Amsterdam
-
2014
A Subject-Specific Model of Tongue-Jaw-Hyoid: Toward the Analysis of SpeechGRAND 2014 — Graphics, Animations and New Media Conference, Ottawa
-
2013
Model Predictive Controller for the Flight Control of OrnithoptersICACME 2013 — 2nd International Conference on Automatic Control and Mechatronic Engineering, Bangkok
-
2012
Factor based Sum Product decoding in Log Domain for Low Density Parity Check CodesICECE 2012 — 7th International Conference on Electrical and Computer Engineering, Dhaka
-
2012
Difference to Sum Ratio Factor based Min-Sum decoding for Low Density Parity Check CodesComComAp 2012 — Computer, Communications & Applications Conference, Hong Kong