I am a research scientist at the IHPC (Institute of High-Performance Computing) of Agency for Science, Technology and Research (A*STAR) Singapore. I am also a NRF (National Research Foundation) Singapore Fellowship recipient and a principal investigator for CFAR (Centre for Frontier AI Research).
I am also an Adjunct Assistant Professor in the Faculty Scheme, in the School of Computer Science and Engineering at NTU located in NTU Main Campus, Singapore. I was an honorary lecturer at the Australian National University (ANU). Prior to that I was a research fellow at the Australian Centre for Robotic Vision (ACRV), the Australian National University. I obtained my PhD from the VISICS group of KU Leuven, Belgium in March 2015 under the supervision of Professor Tinne Tuytelaars. I am interested in Computer Vision and Machine Learning research.
We have three papers accepted to NeurIPS 2024. Congratulations to Paritosh, Shantanu, Binqian and all co-authors.!
We have papers accepted to ACMMM 2024 and ICPR 2024. Congratulations to Zhang Hao and Roy!
We have papers accepted to ICML 2024 and IJCAI 2024. Congratulations to Ishaan and Jinmeng!
We have papers accepted to EACL 2024 and IEEE Transactions on AI. Congratulations to Hu Tao and J. Burton-Barr!
We have papers accepted to EMNLP 2023 and WACV 2024. Congratulations to Arushi, Roy and Dhruv!
We have two papers accepted to ICCV 2023. Congratulations to Arushi and Samitha!
We have paper accepted to EACL on Temporal Moment Localization in Long Videos.
2022 Sept : We have a paper accepted TIP on image paragraph generation. Congratulations to Son!
2022 Jul : We have two papers accepted to ECCV 2022 on top down attention and equivariant graph implicit functions. Congratulations to Shantanu and Yunlu.
2022 Mar : We have a papers accepted to CVPR 2022 on scene graph generation and a CVPR workshop paper. Congratulations to Arushi and Brandon.
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
Paritosh Parmar, Eric Peh, Ruirui Chen, Ting En Lam, Yuhan Chen, Elston Tan, Basura Fernando
NeurIPS 2024 (Accepted) PDF code
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
Shantanu Jaiswal, Debaditya Roy, Basura Fernando, Cheston Tan
NeurIPS 2024 (Accepted) PDF code (soon)
DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
Binqian Xu, Xiangbo Shu, Haiyang Mei, Zechen Bai, Basura Fernando, Mike Zheng Shou, Jinhui Tang
NeurIPS 2024 (Accepted) PDF code
RCA: Region Conditioned Adaptation for Visual Abductive Reasoning
Hao Zhang and Yeo Keat Ee and Basura FernandoACM MM (Accepted 2024) PDF code
Predicting the Next Action by Modeling the Abstract Goal
Debaditya Roy and Basura FernandoICPR (Accepted 2024) PDF code
Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion
Ishaan Singh Rawal, Alexander Matyasko, Shantanu Jaiswal, Basura Fernando, Cheston TanICML (Accepted 2024) PDF code
PointTFA: Training-Free Clustering Adaption for Large 3D Point Cloud Models
Jinmeng Wu, Chong Cao, Hao Zhang, Basura Fernando, Yanbin Hao, and Hanyu HongIJCAI (Accepted 2024) PDF
Activation Control of Vision Models for Sustainable AI Systems
Jonathan Burton-Barr, Basura Fernando, and Deepu RajanIEEE Transactions on Artificial Intelligence (Accepted 2024) PDF
Flow Matching for Conditional Text Generation in a Few Sampling Steps
Vincent Tao Hu, Di Wu, Yuki M Asano, Pascal Mettes, Basura Fernando, Björn Ommer, Cees G. M. SnoekEuropean Chapter of the Association for Computational Linguistics - EACL 2024 PDF
Interaction Visual Transformer for Egocentric Action Anticipation
Debaditya Roy, Ramanathan Rajendiran, and Basura FernandoIEEE/CVF Winter Conference on Applications of Computer Vision - WACV (2024)Ranked 1 team in EPIC-KITCHEN 100 PDF CodeBibtex
@article{
inavit,
title={Interaction Visual Transformer for Egocentric Action Anticipation},
author={Debaditya Roy and Ramanathan Rajendiran and Basura Fernando},
journal={IEEE/CVF Winter Conference on Applications of Computer Vision WACV},
year={2024},
}
ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition
Debaditya Roy and Dhruv Verma and Basura FernandoIEEE/CVF Winter Conference on Applications of Computer Vision - WACV (2024)Best results in SWiG - 2024Best results in imSitu - 2024 Code PDFBibtex
@inproceedings{clipsitu2023,
title={ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition},
author={Debaditya Roy and Dhruv Verma and Basura Fernando},
booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision WACV 2024},
pages={},
year={2024}
}
2023
Semi-supervised multimodal coreference resolution in image narrations
Arushi Goel and Basura Fernando and Frank Keller and Hakan BilenEmpirical Methods in Natural Language Processing - EMNLP (2023) PDFBibtex
@inproceedings{emnlp2023,
title={Semi-supervised multimodal coreference resolution in image narrations},
author={Arushi Goel and Basura Fernando and Frank Keller and Hakan Bilen},
booktitle={Empirical Methods in Natural Language Processing 2023},
pages={},
year={2023}
}
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
Samitha Herath, Basura Fernando, Ehsan Abbasnejad, Munawar Hayat, Shahram Khadivi, Mehrtash Harandi, Hamid Rezatofighi, and Reza Haffari International Conference on Computer Vision - ICCV (2023) PDFBibtex
@inproceedings{samith2023,
title={Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation},
author={Samitha Herath and Basura Fernando and Ehsan Abbasnejad and Munawar Hayat and Shahram Khadivi and Mehrtash Harandi and Hamid Rezatofighi and Reza Haffari},
booktitle={International Conference on Computer Vision 2023},
pages={},
year={2023}
}
Who are you referring to? Coreference resolution in image narrations
Arushi Goel and Basura Fernando and Frank Keller and Hakan BilenInternational Conference on Computer Vision - ICCV (2023) PDF CIN Dataset CodeBibtex
@inproceedings{arushi2023,
title={Who are you referring to? Coreference resolution in image narrations},
author={Arushi Goel and Basura Fernando and Frank Keller and Hakan Bilen},
booktitle={International Conference on Computer Vision 2023},
pages={},
year={2023}
}
Memory-efficient Temporal Moment Localization in Long Videos
Cristian Rodriguez, Edison Marrese-Taylor, Basura Fernando, Hiroya Takamura, Qi WuEuropean Chapter of the Association for Computational Linguistics - EACL (2023) PDFBibtex
@inproceedings{rodriguez2023memory,
title={Memory-efficient Temporal Moment Localization in Long Videos},
author={Rodriguez, Cristian and Marrese-Taylor, Edison and Fernando, Basura and Takamura, Hiroya and Wu, Qi},
booktitle={Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics},
pages={1901--1916},
year={2023}
}
@article{
royabstractgoal,
title={Predicting the Next Action by Modeling the Abstract Goal},
author={Debaditya Roy and Basura Fernando},
journal={under review, IEEE Transactions on Image Processing},
year={2022},
}
2022
Effective Multimodal Encoding for Image Paragraph Captioning
Thanh-Son Nguyen and Basura FernandoIEEE Transactions on Image Processing (2022) PDFBibtex
@article{
son2022,
title={Effective Multimodal Encoding for Image Paragraph Captioning},
author={Thanh-Son Nguyen and Basura Fernando},
journal={IEEE Transactions on Image Processing},
year={2022},
}
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
Shantanu Jaiswal and Basura Fernando and Cheston TanECCV 2022 PDF CodeBibtex
@inproceedings{
eccv2022shan,
title={TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs},
author={Shantanu Jaiswal and Basura Fernando and Cheston Tan},
booktitle={ECCV},
year={2022},
}
3D Equivariant Graph Implicit Functions
Yunlu Chen and Basura Fernando and Hakan Bilen and Matthias Niessner and Efstratios GavvesECCV 2022 PDF CodeBibtex
@inproceedings{
eccv22yunlu,
title={3D Equivariant Graph Implicit Functions},
author={Yunlu Chen and Basura Fernando and Hakan Bilen and Matthias Niessner and Efstratios Gavves},
booktitle={ECCV},
year={2022},
}
Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation
Arushi Goel, Basura Fernando, Frank Keller, and Hakan BilenCVPR 2022 PDFBibtex
@inproceedings{
cvpr22,
title={Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation},
author={Arushi Goel and Basura Fernando and Frank Keller and Hakan Bilen},
booktitle={CVPR},
year={2022},
}
Consistency Regularization for Domain Adaptation
Kian Boon Koh and Basura FernandoECCV 2022 (Workshop) PDFBibtex
@inproceedings{
eccv2022kianboon,
title={Consistency Regularization for Domain Adaptation},
author={Kian Boon Koh and Basura Fernando},
booktitle={ECCV Workshops},
year={2022},
}
Long-term Action Forecasting Using Multi-headed Attention-based Variational Recurrent Neural Networks
Siyuan Brandon Loh, Debaditya Roy and Basura FernandoCVPR 2022 (Workshop) PDFBibtex
@inproceedings{
cvpr22w,
title={Long-term Action Forecasting Using Multi-headed Attention-based Variational Recurrent Neural Networks},
author={Siyuan Brandon Loh and Debaditya Roy and Basura Fernando},
booktitle={CVPR},
year={2022},
}
Action anticipation using latent goal learning
Debaditya Roy and Basura FernandoWACV 2022 PDF CodeBibtex
@inproceedings{
wacv22,
title={Action anticipation using latent goal learning},
author={Debaditya Roy and Basura Fernando},
booktitle={WACV},
year={2022},
}
2021
Neural Feature Matching in Implicit 3D Representations
Yunlu Chen, Basura Fernando, Hakan Bilen, Thomas Mensink, and Efstratios GavvesICML 2021 PDFBibtex
@article{
Chen21,
title={Neural Feature Matching in Implicit 3D Representations},
author={Yunlu Chen and Basura Fernando and Hakan Bilen and Thomas Mensink and Efstratios Gavves},
booktitle={ICML},
year={2021},
}
Anticipating human actions by correlating past with the future with Jaccard similarity measures
Basura Fernando and Samitha HerathCVPR 2021 PDFBibtex
@article{
Fernando21,
title={Anticipating human actions by correlating past with the future with Jaccard similarity measures},
author={Basura Fernando and Samitha Herath},
booktitle={CVPR},
year={2021},
}
Action Anticipation using Pairwise Human-Object Interactions and Transformers
Debaditya Roy and Basura FernandoIEEE Transactions on Image Processing 2021Impact factor 10.856 PDFBibtex
@article{
2021_TIP_ROY,
title={Action Anticipation using Pairwise Human-Object Interactions and Transformers},
author={Debaditya Roy and Basura Fernando},
journal={IEEE Transactions of Image Processing},
year={2021},
}
Weakly supervised action segmentation with effective use of attention and self-attention.
Yan Bin Ng and Basura FernandoComputer Vision and Image Understanding 2021 PDFBibtex
@article{
CVIU_2021,
title={Weakly supervised action segmentation with effective use of attention and self-attention.},
author={Yan Bin Ng and Basura Fernando},
journal={Computer Vision and Image Understanding},
year={2021},
}
A Log-likelihood Regularized KL Divergence for Video Prediction with A 3D Convolutional Variational Recurrent Network
Haziq Razali and Basura FernandoWACV 2021 Generation of Human Behavior Workshop PDFBibtex
@article{
Haziq20,
title={A Log-likelihood Regularized KL Divergence for Video Prediction with A 3D Convolutional Variational Recurrent Network},
author={Haziq Razali and Basura Fernando},
booktitle={WACV},
year={2021},
}
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition
Vinoj Jayasundara, Debaditya Roy and Basura FernandoWACV 2021 PDFBibtex
@article{
Vinoj,
title={FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition},
author={Vinoj Jayasundara and Debaditya Roy and Basura Fernando},
booktitle={WACV},
year={2021},
}
DORi: Discovering Objects Relationship for Temporal Moment Localization of a Natural-Language Query in Video
Cristian Rodriguez, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, and Stephen GouldWACV 2021 PDFBibtex
@article{
Rodriguez2021,
title={DORi: Discovering Objects Relationship for Temporal Moment Localization of a Natural-Language Query in Video},
author={Cristian Rodriguez and Edison Marrese-Taylor and Basura Fernando and Hongdong Li, and Stephen Gould},
booktitle={WACV},
year={2021},
}
2020
Forecasting future action sequences with attention: a new approach to weakly supervised action forecasting
Yan Bin Ng, and Basura FernandoIEEE Transactions on Image Processing 2020 Impact factor 10.856 PDF WebBibtex
@article{
YanBin2020,
title={Forecasting future action sequences with attention: a new approach to weakly supervised action forecasting},
author={Yan Bin Ng, Basura Fernando},
booktitle={IEEE Transactions on Image Processing},
year={2020},
}
What do CNNs gain by imitating the visual development of primate infants?
Shantanu Jaiswal, Dongkyu Choi, Basura FernandoBMVC 2020 PDFBibtex
@inproceedings{
Jaiswal2020,
title={What do CNNs gain by imitating the visual development of primate infants?},
author={Shantanu Jaiswal, Dongkyu Choi, Basura Fernando},
booktitle={The British Machine Vision Conference (BMVC)},
year={2020},
}
Injecting Prior Knowledge into Image Caption Generation
Arushi Goel, Basura Fernando, Thanh-Son Nguyen, Hakan BilenECCV 2020 In European Conference on Computer Vision Workshops PDF openreviewBibtex
Inferring Temporal Compositions of Actions Using Probabilistic Automata
Rodrigo Santa Cruz, Dylan Campbell, Anoop Cherian, Basura Fernando and Stephen GouldCVPR 2020 Conference on Computer Vision and Pattern Recognition Workshops PDF arxivBibtex
@InProceedings{santa2020inferring,
title={Inferring Temporal Compositions of Actions Using Probabilistic Automata},
Author = {Santa Cruz, Rodrigo and Cherian, Anoop and Fernando, Basura and Campbell, Dylan and Gould, Stephen},
Booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
Year = {2020},
}
Weakly Supervised Gaussian Networks for Action Detection
Basura Fernando and Cheston Tan and Hakan BilenWACV 2020 PDF arxivBibtex
@InProceedings{FernandoWACV20,
Title = {Weakly Supervised Gaussian Networks for Action Detection},
Author = {Fernando, Basura and Chet, Cheston Tan Yin and Bilen, Hakan},
Booktitle = {Winter Conference on Applications of Computer Vision (WACV ’20)},
Year = {2020},
}
Human Action Sequence Classification
Yan Bin Ng and Basura Fernando PDFBibtex
@misc{ng2019human,
title={Human Action Sequence Classification},
author={Yan Bin Ng and Basura Fernando},
year={2019},
eprint={1910.02602},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
}
2019
Hallucinating Unaligned Face Images by Multiscale Transformative Discriminative Networks
Xin Yu and Fatih Porikli and Basura Fernando and Richard HartleyInternational Journal of Computer Vision (IJCV) 2019 PDF LinkBibtex
@Article{IJCV_Xin_Yu,
Title = {Hallucinating Unaligned Face Images by Multiscale Transformative Discriminative Networks},
Author = {Xin Yu, Fatih Porikli,Basura Fernando,Richard Hartley},
Journal = {International Journal of Computer Vision},
Year = {2020},
}
Using Temporal Information for Recognizing Actions from Still Images
Samitha Herath, Basura Fernando and Mehrtash HarandiPattern Recognition Journal, 2019 PDF webBibtex
@article{PR19Herath,
Title = {Using Temporal Information for Recognizing Actions from Still Images},
Author = {Samitha Herath and Basura Fernando and Mehrtash Harandi},
Booktitle = {Pattern Recognition},
Year = {2019},
}
Semantic Face Hallucination: Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
Xin Yu and Basura Fernando and Richard Hartley and Fatih PorikliTo appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019 PDF IEEE AccessBibtex
@article{TPAMI_XINYU2019,
Title = {Semantic Face Hallucination: Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes},
Author = {Xin Yu and Basura Fernando and Richard Hartley and Fatih Porikli},
Booktitle = {TPAMI},
Year = {2019},
}
Min-Max Statistical Alignment for Transfer Learning
Samitha Herath, Mehrtash Harandi, Basura Fernando, and Richard NockCVPR 2019 PDF WebBibtex
@InProceedings{HerathCVPR19,
Title = {Min-Max Statistical Alignment for Transfer Learning},
Author = {Samitha Herath and Mehrtash Harandi and Basura Fernando and Richard Nock},
Booktitle = {CVPR},
Year = {2019},
}
Visual Permutation Learning
Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian and Stephen GouldIEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019 PDF IEEE PDFBibtex
@article{Cruz18,
Title = {Visual Permutation Learning},
Author = {Rodrigo Santa Cruz and Basura Fernando and Anoop Cherian and Stephen Gould},
Booktitle = {IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018},
Year = {2019},
}
2018
Action Anticipation with RBF Kernelized Feature Mapping RNN
Yuge Shi, Basura Fernando and Richard HartleyECCV 2018 PDFBibtex
@InProceedings{Yuge18,
Title = {Action Anticipation with RBF Kernelized Feature Mapping RNN},
Author = {Yuge Shi and Basura Fernando and Richard Hartley},
Booktitle = {ECCV},
Year = {2018},
}
Face Super-resolution Guided by Facial Component Heatmaps
Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, and Richard HartleyECCV 2018 PDFBibtex
@InProceedings{Yu18,
Title = {Face Super-resolution Guided by Facial Component Heatmaps},
Author = {Xin Yu and Basura Fernando and Bernard Ghanem and Fatih Porikli and Richard Hartley},
Booktitle = {ECCV},
Year = {2018},
}
VIENA2: A Driving Anticipation Dataset
Mohammad Sadegh Aliakbarian, Fatemehsadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars AnderssonAsian Conference on Computer Vision (ACCV 2018) PDFBibtex
@InProceedings{Aliakbarian18,
Title = {VIENA2: A Driving Anticipation Dataset},
Author = {Mohammad Sadegh Aliakbarian and Fatemehsadat Saleh and Mathieu Salzmann and Basura Fernando and Lars Petersson and Lars Andersson},
Booktitle = {Asian Conference on Computer Vision (ACCV 2018)},
Year = {2018},
}
Action Anticipation by Predicting Future Dynamic Images
Cristian Rodriguez, Basura Fernando and Hongdong LiECCV'18 workshop on Anticipating Human Behavior PDFBibtex
@InProceedings{Yuge18,
Title = {Action Anticipation by Predicting Future Dynamic Images},
Author = {Cristian Rodriguez and Basura Fernando and Hongdong Li},
Booktitle = {ECCV'18 workshop on Anticipating Human Behavior},
Year = {2018},
}
Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
Xin Yu, Basura Fernando, Richard Hartley, and Fatih PorikliCVPR 2018 PDFBibtex
@InProceedings{Yu18,
Title = {Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes},
Author = {Xin Yu and Basura Fernando and Richard Hartley and Fatih Porikli},
Booktitle = {CVPR},
Year = {2018},
}
Neural Algebra of Classifiers
Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen GouldWinter Conference on Applications of Computer Vision (WACV) 2018 PDFBibtex
@InProceedings{Cruz18,
Title = {Neural Algebra of Classifiers},
Author = {Rodrigo Santa Cruz and Basura Fernando and Anoop Cherian and Stephen Gould},
Booktitle = {WACV},
Year = {2018},
}
2017
Action Recognition with Dynamic Image Networks
Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea VedaldiIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (Accepted) arxiv IEEE PDFBibtex
@article{DBLP:journals/corr/BilenFGV16,
author = {Hakan Bilen and
Basura Fernando and
Efstratios Gavves and
Andrea Vedaldi},
title = {Action Recognition with Dynamic Image Networks},
journal = {CoRR},
volume = {abs/1612.00738},
year = {2016},
url = {http://arxiv.org/abs/1612.00738},
timestamp = {Mon, 02 Jan 2017 11:09:15 +0100},
biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/BilenFGV16},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
State of the art results on UCF101 (96.0%) and HMDB51 (74.9%) !
Unsupervised Domain Adaptation Based on Subspace Alignment
Basura Fernando, Rahaf Aljundi, Remi Emonet, Amaury Habrard, Marc Sebban and Tinne TuytelaarsAdvances in Computer Vision and Pattern Recognition book series (ACVPR) PDFBibtex
@InBook{Fernando2017book,
Title = {Unsupervised Domain Adaptation Based on Subspace Alignment},
Author = {Fernando, Basura
and Aljundi, Rahaf
and Emonet, R{\'e}mi
and Habrard, Amaury
and Sebban, Marc
and Tuytelaars, Tinne},
Editor = {Csurka, Gabriela},
Pages = {81--94},
Publisher = {Springer International Publishing},
Year = {2017},
Address = {Cham},
Booktitle = {Domain Adaptation in Computer Vision Applications},
Doi = {10.1007/978-3-319-58347-1_4},
ISBN = {978-3-319-58347-1},
Url = {https://doi.org/10.1007/978-3-319-58347-1_4}
}
Encouraging LSTMs to Anticipate Actions Very Early
Mohammad Sadegh Aliakbarian, Fatemehsadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson and Lars AnderssonICCV 2017State-of-the-art in action anticipation! PDF arxivBibtex
@InProceedings{Aliakbarian2017,
Title = {Encouraging LSTMs to Anticipate Actions Very Early},
Author = {Mohammad Sadegh Aliakbarian and Fatemehsadat Saleh and Mathieu Salzmann and Basura Fernando and Lars Petersson and Lars Andersson},
Booktitle = {arxiv},
Year = {2017},
Url = {https://arxiv.org/abs/1703.07023}
}
Discriminatively Learned Hierarchical Rank Pooling Networks
Basura Fernando and Stephen GouldInternational Journal of Computer Vision (IJCV) PDF PDF (published) arxiv Code ProjectBibtex
@article{Fernando2017ijcv,
Title = {Discriminatively Learned Hierarchical Rank Pooling Networks},
Author = {Basura Fernando and Stephen Gould},
journal = {International Journal of Computer Vision},
volume = {},
year = {2017},
url = {},
}
Self-Supervised Video Representation Learning With Odd-One-Out Networks
Basura Fernando, Hakan Bilen, Efstratios Gavves, Stephen GouldCVPR 2017 PDF arxivBibtex
@InProceedings{Fernando2017,
Title = {Self-Supervised Video Representation Learning With Odd-One-Out Networks},
Author = {Basura Fernando and Hakan Bilen and Efstratios Gavves and Stephen Gould},
Booktitle = {CVPR},
Year = {2017},
Url = {http://arxiv.org/abs/1611.06646}
}
Generalized Rank Pooling for Activity Recognition
Anoop Cherian, Basura Fernando, Mehrtash Harandi, Stephen GouldCVPR 2017 PDF arxivBibtex
@InProceedings{Cherian2017,
Title = {Generalized Rank Pooling for Activity Recognition},
Author = {Anoop Cherian and Basura Fernando and Mehrtash Harandi and Stephen Gould},
Booktitle = {CVPR},
Year = {2017}
}
DeepPermNet: Visual Permutation Learning
Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, Stephen GouldCVPR 2017 PDF arxivBibtex
@InProceedings{Cruz2017,
Title = {Visual Permutation Learning},
Author = {Rodrigo Santa Cruz and Basura Fernando and Anoop Cherian and Stephen Gould},
Booktitle = {CVPR},
Year = {2017},
}
Unsupervised Human Action Detection by Action Matching
Basura Fernando, Sareh Shirazi, Stephen GouldCVPR Workshops 2017 PDF arxivBibtex
@InProceedings{Fernando2017,
Title = {Unsupervised Human Action Detection by Action Matching},
Author = {Basura Fernando and Sareh Shirazi and Stephen Gould},
Booktitle = {CVPR Workshops},
Year = {2017},
Url = {https://arxiv.org/abs/1612.00558}
}
Deep Learning Based Decision Support System for Automated Diagnosis of Age-related Macular Degeneration (AMD)
Sajib Kumar Saha, Di Xiao, Basura Fernando, Mei-Ling Tay-Kearney, Dong An, and Yogesan Kanagasingam.Investigative Ophthalmology & Visual Science, 58(8):25--25, 2017. Impact factor for 2016: 3.303
Zero-Shot Image Captioning with Constrained Beam Search
Peter Anderson, Basura Fernando, Mark Johnson and Stephen GouldConference on Empirical Methods in Natural Language Processing (EMNLP), 2017. arxivBibtex
@InProceedings{Anderson2017,
Title = {Zero-Shot Image Captioning with Constrained Beam Search},
Author = {Peter Anderson and Basura Fernando and Mark Johnson and Stephen Gould},
Booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
year = {2017},
}
Generalized BackPropagation, Etude De Cas: Orthogonality
Mehrtash Harandi and Basura Fernandoarxiv arxivBibtex
@InProceedings{Harandi2017,
Title = {Generalized BackPropagation, Étude De Cas: Orthogonality},
Author = {Mehrtash Harandi and Basura Fernando},
Booktitle = {arxiv},
Year = {2017},
Url = {https://arxiv.org/abs/1611.05927}
}
2016
SPICE: Semantic Propositional Image Caption Evaluation
Peter Anderson, Basura Fernando, Mark Johnson, Stephen GouldECCV 2016 PDF ProjectBibtex
@inproceedings{Anderson:ECCV2016,
author = {Peter Anderson and Basura Fernando and Mark Johnson and Stephen Gould},
title = {SPICE: Semantic Propositional Image Caption Evaluation},
booktitle = {ECCV},
year = {2016}
}
Learning End-to-end Video Classification with Rank-Pooling
Basura Fernando, Stephen GouldICML 2016 PDF JMLR PDF project Bibtex
@inproceedings{Fernando:ICML2016,
author = {Basura Fernando and Stephen Gould},
title = {Learning End-to-end Video Classification with Rank-Pooling},
booktitle = {ICML},
year = {2016}
}
Rank Pooling for Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas, Amir Ghodrati and Tinne TuytelaarsIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) PDF(academia) PDF CodeBibtex project
@article{Fernando2016b,
title={Rank Pooling for Action Recognition},
author={Fernando, Basura and Gavves, Efstratios and Oramas, Jose and Ghodrati, Amir and Tuytelaars, Tinne},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2016}}
Dynamic Image Networks for Action Recognition
Hakan Bilen*, Basura Fernando*, Efstratios Gavves, Andrea Vedaldi and Stephen Gould* Equal contributionsCVPR 2016 (oral) PDF project BibtexRead more
@inproceedings{Bilen2016,
year={2016},
booktitle={CVPR},
title={Dynamic Image Networks for Action Recognition},
author={Hakan Bilen and Basura Fernando and Efstratios Gavves and Andrea Vedaldi and Stephen Gould}}
We introduce the concept of dynamic image, a novel compact representation of videos useful in the context of convolutional neural networks (CNNs). The dynamic image is based on the rank pooling and is obtained as the parameters of a ranking machine that reconstructs the order of the frames of the video. For dynamic images rank pooling is applied directly at the level of image pixels, in RGB space, producing a vector of parameters that can be interpreted as a single RGB image. This idea is simple but powerful as it is allows applying CNNs pre-trained for still image classification, where supervised data is abundant, to video classification, where supervised data is scarce. We also show how to efficiently approximate rank pooling, speeding it up orders of magnitude, and use this approximation to construct a general-purpose rank pooling CNN layer, genaralizing dynamic images to dynamic feature maps. We demonstrate the power of our new representations on standard benchmarks in action recognition achieving state-of-the-art performance.
Dynamic images for UCF 101 dataset
Original dynamic image paper based on VideoDarwin is explained here.
Rank Pooling for Action Recognition, Basura Fernando, Efstratios Gavves,
Jose Oramas, Amir Ghodrati, Tinne Tuytelaars
CNN version of Dynamic Images with approximate rank pooling is explained here.
Dynamic Image Networks for Action Recognition
Hakan Bilen*, Basura Fernando*, Efstratios Gavves, Andrea Vedaldi and Stephen Gould
Accepted to CVPR 2016
Discriminative Hierarchical Rank Pooling for Activity Recognition
Basura Fernando, Peter Anderson, Marcus Hutter and Stephen GouldCVPR 2016 PDF Code project BibtexRead more
@inproceedings{Fernando2016a,
year={2016},
booktitle={CVPR},
title={Discriminative Hierarchical Rank Pooling for Activity Recognition},
author={Basura Fernando and Peter Anderson and Marcus Hutter and Stephen Gould}}
We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which can be used for activity recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.
@inproceedings{Fernando2015b,
year={2015},
booktitle={ICCV},
title={Learning-to-rank based on subsequences},
author={Basura Fernando and Efstratios Gavves and Damien Muselet and Tinne Tuytelaars}}
We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences especially focusing on image re-ranking applications. Most often in the supervised learning to rank literature, ranking is approached either by analyzing pairs of images or by optimizing a list-wise surrogate loss function on full sequences. In this work we propose MidRank, which learns from moderately sized sub-sequences instead. These sub-sequences contain useful structural ranking information that leads to better learnability during training and better generalization during testing. By exploiting sub-sequences, the proposed MidRank improves ranking accuracy considerably on an extensive array of image re-ranking applications and datasets.
Guided Long-Short Term Memory for Image Caption Generation
Xu Jia, Efstratios Gavves, Basura Fernando and Tinne TuytelaarsICCV 2015 PDF arxivBibtexRead more
@inproceedings{Jia2015,
year={2015},
booktitle={ICCV},
title={Guided Long-Short Term Memory for Image Caption Generation},
author={Xu Jia and Efstratios Gavves and Basura Fernando and Tinne Tuytelaars}}
In this work we focus on the problem of image caption generation. We propose an extension of the long short term memory (LSTM) model, which we coin Guided LSTM or G-LSTM for short. In particular, we add semantic information extracted from the image as extra input to each unit of the LSTM block, with the aim of guiding the model towards solutions that are more tightly coupled to the image content. Additionally, we explore different length normalization strategies for beam search in order to prevent it from favoring short sentences. On various benchmark datasets, we obtain results that are on par with or even outperform the current state-of-the-art.
Modeling Video Evolution For Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas, Amir Ghodrati and Tinne TuytelaarsCVPR 2015 (oral) PDF Code project Bibtex
@inproceedings{Fernando2015a,
year={2015},
booktitle={CVPR},
title={Modeling Video Evolution For Action Recognition},
author={Basura Fernando and Efstratios Gavves and Jose Oramas and Amir Ghodrati and Tinne Tuytelaars}}
Dataset Fingerprints: Exploring Image Collections Through Data Mining
Konstantinos Rematas, Basura Fernando, Frank Dellaert and Tinne TuytelaarsCVPR 2015 PDF ProjectBibtex
@inproceedings{Rematas2015,
year={2015},
booktitle={CVPR},
title={Dataset Fingerprints: Exploring Image Collections Through Data Mining},
author={Konstantinos Rematas and Basura Fernando and Frank Dellaert and Tinne Tuytelaars}}
Location Recognition Over Large Time Lags
Basura Fernando, Tatiana Tommasi and Tinne TuytelaarsComputer Vision and Image Understanding arxiv PDF Project & CodeBibtex
@article{Fernando2015CVIU,
title = "Location recognition over large time lags ",
journal = "Computer Vision and Image Understanding ",
volume = "139",
number = "",
pages = "21-28",
year = "2015",
note = "",
issn = "1077-3142",
doi = "http://dx.doi.org/10.1016/j.cviu.2015.05.016",
url = "http://www.sciencedirect.com/science/article/pii/S107731421500137X",
author = "Basura Fernando and Tatiana Tommasi and Tinne Tuytelaars",
}
Joint cross-domain classification and subspace learning for unsupervised adaptation
Basura Fernando, Tatiana Tommasi and Tinne TuytelaarsPattern Recognition LettersPDFCodeProjectBibtex
@article{Fernando2015PRL,
title = "Joint cross-domain classification and subspace learning for unsupervised adaptation",
journal = "Pattern Recognition Letters",
volume = "",
number = "",
pages = " - ",
year = "2015",
note = "",
issn = "",
doi = " 10.1016/j.patrec.2015.07.009",
url = "",
author = "Basura Fernando and Tatiana Tommasi and Tinne Tuytelaars",
}
2014
Subspace Alignment For Domain Adaptation
Basura Fernando, Amaury Habrard, Marc Sebban and Tinne TuytelaarsarXiv.org PDF arxiv CodeBibtex
@article{Fernando2014c,
author = {Basura Fernando and Amaury Habrard and Marc Sebban and Tinne Tuytelaars},
title = {Subspace Alignment For Domain Adaptation},
journal = {CoRR},
volume = {abs/1409.5241},
year = {2014},
url = {http://arxiv.org/abs/1409.5241},
timestamp = {Wed, 01 Oct 2014 15:00:04 +0200},
biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/FernandoHST14},
bibsource = {dblp computer science bibliography, http://dblp.org}
Color Features For Dating Historical Color Images
Basura Fernando, Damien Muselet, Rahat Khan and Tinne TuytelaarsInternational conference of image processing (ICIP) PDFBibtex
@article{Fernando2014b,
year={2014},
BOOKTITLE={IEEE International Conference on Image Processing 2014 (ICIP 2014)},
title={Color Features For Dating Historical Color Images},
Basura Fernando and Damien Muselet and Rahat Khan and Tinne Tuytelaars},
}
Local Alignments for Fine-Grained Categorization
Efstratios Gavves, Basura Fernando, Cees G.M. Snoek, Arnold W.M. Smeulders and Tinne TuytelaarsInternational Journal of Computer Vision (IJCV)January 2014, Volume 111, Issue 2, pp 191-212,Issn 0920-5691 PDF (Accepted author version)Bibtex
@article{Gavves2014,
year={2015},
issn={0920-5691},
journal={International Journal of Computer Vision},
volume={111},
number={2},
doi={10.1007/s11263-014-0741-5},
title={Local Alignments for Fine-Grained Categorization},
url={http://dx.doi.org/10.1007/s11263-014-0741-5},
publisher={Springer US},
keywords={Alignment; Image representation; Object classification},
author={Gavves, Efstratios and Fernando, Basura and Snoek, CeesG.M. and Smeulders, ArnoldW.M. and Tuytelaars, Tinne},
pages={191-212},
language={English}
}
Mining Mid-level Features for Image Classification
Basura Fernando, Elisa Fromont, Tinne TuytelaarsInternational Journal of Computer Vision (IJCV)July 2014, Volume 108, Issue 3, pp 186-203 PDF (Accepted author version) PDF (Springer)Bibtex
@article{Fernando2014a,
year={2014},
issn={0920-5691},
journal={International Journal of Computer Vision},
volume={108},
number={3},
doi={10.1007/s11263-014-0700-1},
title={Mining Mid-level Features for Image Classification},
url={http://dx.doi.org/10.1007/s11263-014-0700-1},
publisher={Springer US},
keywords={Frequent itemset mining; Image classification; Discriminative patterns; Mid-level features},
author={Fernando, Basura and Fromont, Elisa and Tuytelaars, Tinne},
pages={186-203},
language={English}
}
2013
Mining Multiple Queries for Image Retrieval: On-the-fly learning of an Object-specific Mid-level Representation
Basura Fernando and Tinne TuytelaarsICCV 2013 PDF Suppl. Material DatasetBibtex
@inproceedings{Fernando2013a,
author = {Basura Fernando and Tinne Tuytelaars},
title = {Mining Multiple Queries for Image Retrieval: On-the-fly learning of an Object-specific Mid-level Representation},
booktitle = {ICCV},
year = {2013},
}
Unsupervised Visual Domain Adaptation Using Subspace Alignment
Basura Fernando, Amaury Habrard, Marc Sebban and Tinne TuytelaarsICCV 2013 PDF Suppl. Material CodeBibtex
@inproceedings{Fernando2013b,
author = {Basura Fernando and Amaury Habrard and Marc Sebban and Tinne Tuytelaars},
title = {Unsupervised Visual Domain Adaptation Using Subspace Alignment},
booktitle = {ICCV},
year = {2013},
}
Fine-Grained Categorization by Alignments
Efstratios Gavves, Basura Fernando, Cees Snoek, Arnold Smeulders and Tinne TuytelaarsICCV 2013 PDF DemoBibtex
@inproceedings{Efstratios2013a,
author = {Efstratios Gavves and Basura Fernando and Cees Snoek and Arnold Smeulders and Tinne Tuytelaars},
title = {Fine-Grained Categorization by Alignments},
booktitle = {ICCV},
year = {2013},
}
Does Evolution cause a Domain Shift?
Konstantinos Rematas, Basura Fernando, Tatiana Tommasi and Tinne TuytelaarsInternational Workshop on Visual Domain Adaptation and Dataset Bias - ICCV 2013PDFProjectBibtex
@inproceedings{Konstantinos2013a,
author = {Konstantinos Rematas and Basura Fernando and Tatiana Tommasi and Tinne Tuytelaars},
title = {Does Evolution cause a Domain Shift?},
booktitle = {International Workshop on Visual Domain Adaptation and Dataset Bias - ICCV 2013},
year = {2013},
}
The AXES submissions at TrecVid 2013
Robin Aly, Relja Arandjelovic, Ken Chatfield, Matthijs Douze,
Basura Fernando, Zaid Harchaoui, Kevin McGuinness, Noel E OConner, Dan Oneata, Omkar M Parkhi,
Danila Potapov, Jerome Revaud, Cordelia Schmid, Jochen Schwenninger,
David Scott, Tinne Tuytelaars, Jakob Verbeek, Heng Wang, Andrew Zisserman TRECVid 2013 PDF
2012
Effective Use of Frequent Itemset Mining for Image Classification
Basura Fernando, Elisa Fromont, Tinne TuytelaarsECCV 2012 PDF Project CodeBibtex
@inproceedings{Fernando2012b,
author = {Basura Fernando and Elisa Fromont and Tinne Tuytelaars},
title = {Effective Use of Frequent Itemset Mining for Image Classification},
booktitle = {ECCV},
year = {2012},
}
Discriminative Feature Fusion for Image Classification
Basura Fernando, Elisa Fromont, Damien Muselet, Marc SebbanCVPR 2012 PDFBibtex
@inproceedings{Fernando2012a,
author = {Basura Fernando and Elisa Fromont and Damien Muselet and Marc Sebban},
title = {Discriminative Feature Fusion for Image Classification},
booktitle = {CVPR},
year = {2012},
}
AXES at TRECVID 2012: KIS, INS, and MED
Aly, Robin and McGuinness, Kevin and Chen, Shu and O'Connor, Noel E. and Chatfield, Ken and Parkhi, Omkar and Arandjelovic, Relja and Zisserman, Andrew and Fernando, Basura and Tuytelaars, Tinne and Oneata, Dan and Douze, Matthijs and Revaud, Jerome and Schwenninger, Jochen and Potapov, Danila and Wang, Heng and Harchaoui, Zaid and Verbeek, Jakob and Schmid, Cordelia TRECVid 2012 PDF
Supervised learning of gaussian mixture models for visual vocabulary generation
Basura Fernando, Elisa Fromont, Damien Muselet, Marc Sebban Journal of Pattern Recognition Volume 45, Issue 2, February 2012 PDFBibtex
@article{Fernando2012pr,
author = {Basura Fernando and Elisa Fromont and Damien Muselet and Marc Sebban},
title = {Supervised learning of Gaussian mixture models for visual vocabulary generation},
journal = "Pattern Recognition ",
volume = "45",
number = "2",
pages = "897 - 907",
year = "2012",
}
The “Other Me”: Human-Centered AI Assistance In Situ This research is supported by the National Research Foundation Singapore under its AI Singapore Programme (Award Number: AISG2-RP-2020-0160). Duration : April 2021 to March 2025
Learning To Anticipate Human Actions This research is supported by the National Research Foundation Singapore under its AI Singapore Programme (Award Number: AISG-RP-2019-010).
Duration : October 2019 to October 2022
Project: ARC Centre of Excellence for Robotic Vision
Robots are changing the way we live and work. The Australian Centre for Robotic Vision (ACRV) brings together Australia's top researchers in computer vision and robotics to lead the world in robotic vision research. Robotic vision is the key enabling technology that will allow robotics to transform labour-intensive industries, disrupt stagnant markets, and ensure robots become a ubiquitous feature of the modern world.
Project website
Duration : June 2015 to March 2018
Project: EU-FP7 AXES: Access to Audiovisual Archives
The goal of AXES is to develop tools that provide various types of
users with new engaging ways to interact with audiovisual libraries, helping
them discover, browse, navigate, search and enrich archives.
In particular, apart from a search-oriented scheme, we will explore how
suggestions for audiovisual content exploration can be generated via a
myriad of information trails crossing the archive. This will be approached
from three perspectives (or axes): users, content, and technology.
Project website
Duration : May 2012 to March 2015
Project: BEELDCANON: Providing access to the rich Dutch-Flemish image culture
Images are an essential part of our culture. Thanks to digitization and other technological
innovations it is easier to distribute images. The research project BEELDCANON (Canon Image) wants to
map out 'typical' images from the Flemish and Dutch culture, store them into a database and make the
database easily searchable. Flemish researchers focus on listing buildings, such as the Atomium,
Louvain's town hall or the Cathedral in Antwerp, while their Dutch counterparts focus on typical
landscapes or scenes like the cheese market in Alkmaar and the Dam in Amsterdam.
Project website
Duration : September 2011 to May 2013
1. 2016-2018 - PhD thesis co-supervisor - Xin Yu (ANU) (Graduated, the first appointment: a research Fellow at ANU.)
2. 2016-2018 - PhD thesis co-supervisor/adviser - Peter Anderson (ANU) (Graduated, Graduated, the first appointment: a research Scientist at Georgia Tech.)
3. 2015-2018 - PhD thesis co-supervisor - Rodrigo Santa Cruz (ANU) (Graduated, the first appointment: a postdoctoral research fellow at CSIRO)
4. 2016-2019 - PhD Chair of the panel and thesis co-supervisor - Mohammad Sadegh Aliakbarian (ANU) (Graduated)
5. 2016-2019 - PhD thesis co-supervisor - Samitha Herath (ANU) (Graduated, the first appointment: a research Fellow at the University of Monash.)
6. 2016-2020 - PhD thesis co-supervisor - Cristian Rodriguez Opazo (ANU) (Graduated, the first appointment: a research Fellow at the University of Adelaide.)
7. 2020-2023 - PhD thesis co-supervisor - Arushi Goel (University of Edinburgh) (Graduated, the first appointment: Research Scientist at Nvidia.)
2022: Final year project (NTU) - ERIC PEH ZHENG QUAN - Learning to anticipate and forecast human actions from videos (Bachelor thesis)
2020: Final year project (NTU) - Adipraja Widjaja, Sergi - Deep learning methods for weakly supervised video temporal action localization (Bachelor thesis)
2018: ENGN4712 - Engineering Research and Development Project (ANU) - Tengda Han - Video object segmentation (Bachelor thesis)
Bachelor of Science in Engineering
University of Moratuwa Sri Lanka
Computer Science and Engineering 2003-2007
Master of Science - Color in Informatics and Media Technology
University of Saint-Etienne France and University of Gjovik Norway
Color in Informatics and Media Technology 2009-2011