Basura Fernando

I am is a research scientist at the IHPC of Agency for Science, Technology and Research (A*STAR) 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.

Research interests: Action Recognition, Transfer Learning, Action Prediction, Weakly Supervised Learning, Computer Vision, Machine Learning. My CV

Contact: basuraf at gmail dot com

News:





Projects Teaching Supervision Services Education





Grants

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
Amount : 10 Million SGD

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
Amount : 750,000 SGD

Auto optical character recognition (OCR) of indented part markings on aero components
This research is supported by RIE2020 Advanced Manufacturing And Engineering (AME) IAF-PP under the Singapore Aerospace Programme Cycle 13.
Duration : Feb 2020 to Jan 2022
Amount : 260,000 SGD

Publications

2021
Deep Implicit Feature Matching
Yunlu Chen, Basura Fernando, Hakan Bilen, Thomas Mensink, and Efstratios Gavves
ICML 2021
PDF Bibtex
Anticipating human actions by correlating past with the future with Jaccard similarity measures
Basura Fernando and Samitha Herath
CVPR 2021
PDF Bibtex
A Log-likelihood Regularized KL Divergence for Video Prediction with A 3D Convolutional Variational Recurrent Network
Haziq Razali and Basura Fernando
WACV 2021
Generation of Human Behavior Workshop

PDF Bibtex
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition
Vinoj Jayasundara, Debaditya Roy and Basura Fernando
WACV 2021
PDF Bibtex
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 Gould
WACV 2021
PDF Bibtex
2020
Forecasting future action sequences with attention: a new approach to weakly supervised action forecasting
Yan Bin Ng, and Basura Fernando
IEEE Transactions on Image Processing 2020
Impact factor 9.34
PDF Web Bibtex
What do CNNs gain by imitating the visual development of primate infants?
Shantanu Jaiswal, Dongkyu Choi, Basura Fernando
BMVC 2020
PDF Bibtex
Injecting Prior Knowledge into Image Caption Generation
Arushi Goel, Basura Fernando, Thanh-Son Nguyen, Hakan Bilen
ECCV 2020
In European Conference on Computer Vision Workshops

PDF openreview Bibtex
Inferring Temporal Compositions of Actions Using Probabilistic Automata
Rodrigo Santa Cruz, Dylan Campbell, Anoop Cherian, Basura Fernando and Stephen Gould
CVPR 2020
Conference on Computer Vision and Pattern Recognition Workshops

PDF arxiv Bibtex
Weakly Supervised Gaussian Networks for Action Detection
Basura Fernando and Cheston Tan and Hakan Bilen
WACV 2020
PDF arxiv Bibtex
Human Action Sequence Classification
Yan Bin Ng and Basura Fernando
PDF Bibtex
2019
Hallucinating Unaligned Face Images by Multiscale Transformative Discriminative Networks
Xin Yu and Fatih Porikli and Basura Fernando and Richard Hartley
International Journal of Computer Vision (IJCV) 2019
PDF Link Bibtex
Using Temporal Information for Recognizing Actions from Still Images
Samitha Herath, Basura Fernando and Mehrtash Harandi
Pattern Recognition Journal, 2019
PDF web Bibtex
Semantic Face Hallucination: Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
Xin Yu and Basura Fernando and Richard Hartley and Fatih Porikli
To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019
PDF IEEE Access Bibtex
Min-Max Statistical Alignment for Transfer Learning
Samitha Herath, Mehrtash Harandi, Basura Fernando, and Richard Nock
CVPR 2019
PDF Web Bibtex
Visual Permutation Learning
Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian and Stephen Gould
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019
PDF IEEE PDF Bibtex
2018
Action Anticipation with RBF Kernelized Feature Mapping RNN
Yuge Shi, Basura Fernando and Richard Hartley
ECCV 2018
PDF Bibtex
Face Super-resolution Guided by Facial Component Heatmaps
Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, and Richard Hartley
ECCV 2018
PDF Bibtex
VIENA2: A Driving Anticipation Dataset
Mohammad Sadegh Aliakbarian, Fatemehsadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson, Lars Andersson
Asian Conference on Computer Vision (ACCV 2018)
PDF Bibtex
Action Anticipation by Predicting Future Dynamic Images
Cristian Rodriguez, Basura Fernando and Hongdong Li
ECCV'18 workshop on Anticipating Human Behavior
PDF Bibtex
Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
Xin Yu, Basura Fernando, Richard Hartley, and Fatih Porikli
CVPR 2018
PDF Bibtex
Neural Algebra of Classifiers
Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
Winter Conference on Applications of Computer Vision (WACV) 2018
PDF Bibtex
2017
Action Recognition with Dynamic Image Networks
Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (Accepted)
arxiv IEEE PDF Bibtex
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 Tuytelaars
Advances in Computer Vision and Pattern Recognition book series (ACVPR)
PDF Bibtex
Encouraging LSTMs to Anticipate Actions Very Early
Mohammad Sadegh Aliakbarian, Fatemehsadat Saleh, Mathieu Salzmann, Basura Fernando, Lars Petersson and Lars Andersson
ICCV 2017
State-of-the-art in action anticipation!
PDF arxiv Bibtex
Discriminatively Learned Hierarchical Rank Pooling Networks
Basura Fernando and Stephen Gould
International Journal of Computer Vision (IJCV)
PDF PDF (published) arxiv Code Project Bibtex
Self-Supervised Video Representation Learning With Odd-One-Out Networks
Basura Fernando, Hakan Bilen, Efstratios Gavves, Stephen Gould
CVPR 2017
PDF arxiv Bibtex
Generalized Rank Pooling for Activity Recognition
Anoop Cherian, Basura Fernando, Mehrtash Harandi, Stephen Gould
CVPR 2017
PDF arxiv Bibtex
DeepPermNet: Visual Permutation Learning
Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, Stephen Gould
CVPR 2017
PDF arxiv Bibtex
Unsupervised Human Action Detection by Action Matching
Basura Fernando, Sareh Shirazi, Stephen Gould
CVPR Workshops 2017
PDF arxiv Bibtex
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 Gould
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2017.
arxiv Bibtex
Generalized BackPropagation, Etude De Cas: Orthogonality
Mehrtash Harandi and Basura Fernando
arxiv
arxiv Bibtex
2016
SPICE: Semantic Propositional Image Caption Evaluation
Peter Anderson, Basura Fernando, Mark Johnson, Stephen Gould
ECCV 2016
PDF Project Bibtex
Learning End-to-end Video Classification with Rank-Pooling
Basura Fernando, Stephen Gould
ICML 2016
PDF JMLR PDF project Bibtex
Rank pooling and variants
Rank Pooling for Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas, Amir Ghodrati and Tinne Tuytelaars
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
PDF(academia) PDF Code Bibtex project
Rank pooling and variants
Dynamic Image Networks for Action Recognition
Hakan Bilen*, Basura Fernando*, Efstratios Gavves, Andrea Vedaldi and Stephen Gould
* Equal contributions
CVPR 2016 (oral)
PDF project Bibtex Read more
Simple Dynamic Image Code
Dynamic Image Nets Code

Download Dynamic Images for UCF101
Rank pooling and variants
Discriminative Hierarchical Rank Pooling for Activity Recognition
Basura Fernando, Peter Anderson, Marcus Hutter and Stephen Gould
CVPR 2016
PDF Code project Bibtex Read more
Rank pooling and variants
2015
Learning to rank based on subsequences
Basura Fernando, Efstratios Gavves, Damien Muselet and Tinne Tuytelaars
ICCV 2015
PDF arxiv Supplementary (120Mb) Bibtex Code Read more
Guided Long-Short Term Memory for Image Caption Generation
Xu Jia, Efstratios Gavves, Basura Fernando and Tinne Tuytelaars
ICCV 2015
PDF arxiv Bibtex Read more
Modeling Video Evolution For Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas, Amir Ghodrati and Tinne Tuytelaars
CVPR 2015 (oral)
PDF Code project Bibtex
Dataset Fingerprints: Exploring Image Collections Through Data Mining
Konstantinos Rematas, Basura Fernando, Frank Dellaert and Tinne Tuytelaars
CVPR 2015
PDF Project Bibtex
Location Recognition Over Large Time Lags
Basura Fernando, Tatiana Tommasi and Tinne Tuytelaars
Computer Vision and Image Understanding
arxiv PDF Project & Code Bibtex
Joint cross-domain classification and subspace learning for unsupervised adaptation
Basura Fernando, Tatiana Tommasi and Tinne Tuytelaars
Pattern Recognition Letters
PDF Code Project Bibtex
2014
Subspace Alignment For Domain Adaptation
Basura Fernando, Amaury Habrard, Marc Sebban and Tinne Tuytelaars
arXiv.org
PDF arxiv Code Bibtex
Color Features For Dating Historical Color Images
Basura Fernando, Damien Muselet, Rahat Khan and Tinne Tuytelaars
International conference of image processing (ICIP)
PDF Bibtex
Local Alignments for Fine-Grained Categorization
Efstratios Gavves, Basura Fernando, Cees G.M. Snoek, Arnold W.M. Smeulders and Tinne Tuytelaars
International Journal of Computer Vision (IJCV)
January 2014, Volume 111, Issue 2, pp 191-212,Issn 0920-5691
PDF (Accepted author version) Bibtex
Mining Mid-level Features for Image Classification
Basura Fernando, Elisa Fromont, Tinne Tuytelaars
International Journal of Computer Vision (IJCV)
July 2014, Volume 108, Issue 3, pp 186-203
PDF (Accepted author version) PDF (Springer) Bibtex
2013
Mining Multiple Queries for Image Retrieval: On-the-fly learning of an Object-specific Mid-level Representation
Basura Fernando and Tinne Tuytelaars
ICCV 2013
PDF Suppl. Material Dataset Bibtex
Unsupervised Visual Domain Adaptation Using Subspace Alignment
Basura Fernando, Amaury Habrard, Marc Sebban and Tinne Tuytelaars
ICCV 2013
PDF Suppl. Material Code Bibtex
Fine-Grained Categorization by Alignments
Efstratios Gavves, Basura Fernando, Cees Snoek, Arnold Smeulders and Tinne Tuytelaars
ICCV 2013
PDF Demo Bibtex
Does Evolution cause a Domain Shift?
Konstantinos Rematas, Basura Fernando, Tatiana Tommasi and Tinne Tuytelaars
International Workshop on Visual Domain Adaptation and Dataset Bias - ICCV 2013
PDF Project Bibtex
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 Tuytelaars
ECCV 2012
PDF Project Code Bibtex
Discriminative Feature Fusion for Image Classification
Basura Fernando, Elisa Fromont, Damien Muselet, Marc Sebban
CVPR 2012
PDF Bibtex
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
PDF Bibtex

Projects and Grants

Grant: Learning To Anticipate Human Actions That Happen In The Next One To Five Seconds Using Self-Regularised Future Content Generation For Human-Robotic Engagement
Our ability to anticipate the behaviour of others comes naturally to us. For example, an experienced driver can often predict the behaviour of other road users. Similarly, a good table tennis player can estimate the direction of the ball just by observing the movements of the opponent. This phenomenon is called Action Anticipation, the ability to recognise actions of others before it happens in the immediate future. This is so natural to us but how to develop a computational approach to do the same remains a challenge. It is critical to transfer this ability to computers so that robots may be able to react quickly by anticipating human actions like humans. Robots' ability to understand what humans might do in the immediate future is important for the development of assistive robotics in domains such as manufacturing and healthcare. The objective of this project is to investigate a novel approach to anticipate human actions, specifically one to five seconds before action happens using visual information in human-robot engagement scenarios.
Project website
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 2021
Amount : 750,000 SGD

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

Professional Activities

Area Chair for ICCV 2021.

Area Chair for IJCAI 2021.

Area Chair for CVPR 2021.

Area Chair for BMVC 2020.

Senior Program Committee member at IJCAI-2020

Area Chair for BMVC 2019.

Senior Program Committee member at IJCAI-2019

Area Chair for BMVC 2018

Associate Editor ICRA 2018.

Organising CVPR17 workshop on Brave New Ideas for Motion and Spatio-Temporal Representations.

Organising ECCV 2016 workshop titled Brave New Ideas For Motion Representations.

Co-chairing the CVPR 2016 oral and spotlight session on Learning and CNN Architectures.

Program committee member of Robotic Vision RVSS 2016 Summer School.

Program committee member of RoboVis 2016 workshop.

Review Activities

CVPR 2013, 2015, 2016, 2017, 2018, 2019 reviewer

ICCV 2013, 2017 reviewer

ECCV 2014, 2016, 2018 reviewer

NIPS 2016, 2017, 2018, 2019 reviewer

ICML 2016, 2017, 2018, 2019 reviewer

TPAMI: IEEE Transactions on Pattern Analysis and Machine Intelligence

IJCV: International Journal of Computer Vision

Machine Learning Journal

IEEE Transactions on Image Processing

PR: Pattern Recognition Journal

PRL: Pattern Recognition Letters Journal

IEEE Transactions on Neural Networks and Learning Systems

IEEE Transactions on Multimedia

CVIU: Computer vision and image understanding journal

Teaching

Guest lecture 2017 Semester1 : ENGN4528: Computer Vision at ANU

Tutorial on Action recognition and Semitic Vision at the "Robotic Vision Summer School" RVSS 2017

Guest lecture in Advanced Topics in Mechatronics Systems ENGN8536 ANU

Guest lecture 2016 Semester1 : ENGN4528: Computer Vision at ANU

2015 Spring : H09J2A: Pattern Recognition and Image Interpretation (TA) at KU Leuven

2014 Spring : H09J2A: Pattern Recognition and Image Interpretation (TA) at KU Leuven

2013 Spring : H09J2A: Pattern Recognition and Image Interpretation (TA) at KU Leuven

PhD Supervision

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.)

MSc/ BSc Supervision

2018: ENGN4712 - Engineering Research and Development Project - Tengda Han - Video object segmentation (Bachelor thesis)

2018: ENGN4200 - Individual Project - Yuge Shi -Video action prediction (Bachelor thesis)

2013: Learning object categories from the web - Alberto Dominguez (Master thesis KU Leuven)

Other Supervision

1. 2018-2019 Arushi Goel (Research Engineer)
(Now a PhD student at University of Edinburgh)

2. 2019-Now Yan Bin Ng (Research Engineer)

3. 2019-Now Haziq Razali (Research Engineer)

4. 2019-Now Jaiswal Shantanu (Research Engineer)

5. 2019-Now Vinoj Jayasundara (Research Engineer)

6. 2020-now Debaditya Roy (Research Scientist)

Seminar, talks

May 24, 2016 - Rank pooling and variants for action and activity recognition - ACRV The Australian National University

March 17, 2016 - Action and Activity Recognition Research at ANU - Australian Centre for Visual Technologies, The University of Adelaide, Australia

July 15, 2015 - Effective Image and Video Representations - Australian Centre for Robotic Vision, ANU, Australia

March 30, 2015 - Image Representations for Improving Object Recognition - VISICS Lab, Leuven, Belgium

Dec 12, 2013 - Unsupervised Visual Domain Adaptation Using Subspace Alignment - VISICS Lab, Leuven, Belgium

Dec 12, 2013 - Mining Multiple Queries for Image Retrieval- VISICS Lab, Leuven, Belgium

Dec 04, 2012 - Learning mid-level features for classification and retrieval - Intelligent Systems Lab, Amsterdam

Nov 22, 2012 - Learning mid-level features for image retrieval - Hubert-Curien Lab, Saint Etienne, France

May 15, 2012 - Discriminative Feature Fusion for Image Classification - VISICS Lab, Leuven, Belgium

Conference/workshops/meetings attended.

Jun. 2017 - CVPR - Hawaii, USA
Jun. 2016 - CVPR - Las Vegas, USA
Jun. 2016 - ICML - New York, USA
Dec. 2015 - ICCV - Santiago, Chile
Dec. 2013 - ICCV - Sydney, Australia
Aug. 2013 - iMinds Opportunity Recognition - Leuven, Belgium
Jul. 2013 - ROKS - Leuven, Belgium
Oct. 2012 - ECCV - Florence, Italy
July 2012 - INRIA Visual Recognition and Machine Learning - Grenoble, France

Education

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

PhD
KU Leuven, Belgium
Computer Vision
2011-2015

Scholarships and awards

Mahapola Scholarship (Sri Lanka)
2003-2007

Erusmus Mundus Scholarship (European Union)
2009-2011

Ph.D Fellowship (KU Leuven, Belgium)
01-Oct-2011 to 31-March-2015

Research Fellowship (ARC Centre of Excellence for Robotic Vision, The Australian National University)
02-July-2015 to 31-December-2018