World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
36
Citations
9996
World Ranking
10999
National Ranking
147

Overview

Basura Fernando is affiliated with the Agency for Science, Technology and Research in Singapore and specializes in computer science with a focus on computer vision and artificial intelligence. Their work primarily involves advancing machine learning techniques related to human pose and action recognition, video analysis, and multimodal machine learning applications.

The scientist has contributed notably to several key topics, including:

  • Multimodal Machine Learning Applications
  • Human Pose and Action Recognition
  • Anomaly Detection Techniques and Applications
  • Domain Adaptation and Few-Shot Learning
  • Topic Modeling
  • Advanced Neural Network Applications
  • Video Analysis and Summarization

Basura Fernando's research has appeared in a range of publication venues. The most frequent outlets include:

  • arXiv (Cornell University)
  • IEEE Transactions on Image Processing
  • International Journal of Computer Vision
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

The scientist has co-authored work with several frequent collaborators, such as:

  • Debaditya Roy
  • Hakan Bilen
  • Arushi Goel
  • Cheston Tan
  • Frank Keller

Recent notable publications from Basura Fernando include:

  • "Forecasting Future Action Sequences With Attention: A New Approach to Weakly Supervised Action Forecasting" (2020), IEEE Transactions on Image Processing
  • "Action Anticipation Using Pairwise Human-Object Interactions and Transformers" (2021), IEEE Transactions on Image Processing
  • "Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation" (2022), 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • "Action anticipation using latent goal learning" (2022), 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • "Long-term Action Forecasting Using Multi-headed Attention-based Variational Recurrent Neural Networks" (2022), 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Their publications demonstrate a consistent focus on advancing methods for forecasting and anticipating human actions, often leveraging attention mechanisms and transformer models. The breadth of work includes both theoretical innovations and applications relevant to computer vision systems designed to interpret complex scenes and human-object interactions.

Best Publications

  • SPICE: Semantic Propositional Image Caption Evaluation

    Peter Anderson;Basura Fernando;Mark Johnson;Stephen Gould

  • Unsupervised Visual Domain Adaptation Using Subspace Alignment

    Basura Fernando;Amaury Habrard;Marc Sebban;Tinne Tuytelaars

  • Dynamic Image Networks for Action Recognition

    Hakan Bilen;Basura Fernando;Efstratios Gavves;Andrea Vedaldi

  • Modeling video evolution for action recognition

    Basura Fernando;Efstratios Gavves;M. Jose Oramas;Amir Ghodrati

  • Guiding the Long-Short Term Memory Model for Image Caption Generation

    Xu Jia;Efstratios Gavves;Basura Fernando;Tinne Tuytelaars

  • Self-Supervised Video Representation Learning with Odd-One-Out Networks

    Basura Fernando;Hakan Bilen;Efstratios Gavves;Stephen Gould

  • Rank Pooling for Action Recognition

    Basura Fernando;Efstratios Gavves;M Jose Oramas Oramas;Amir Ghodrati

  • Action Recognition with Dynamic Image Networks

    Hakan Bilen;Basura Fernando;Efstratios Gavves;Andrea Vedaldi

  • Face Super-resolution Guided by Facial Component Heatmaps

    Xin Yu;Basura Fernando;Bernard Ghanem;Fatih Porikli

  • Fine-Grained Categorization by Alignments

    E. Gavves;B. Fernando;C. G. M. Snoek;A. W. M. Smeulders

  • Guided Open Vocabulary Image Captioning with Constrained Beam Search

    Peter Anderson;Basura Fernando;Mark Johnson;Stephen Gould

  • Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes

    Xin Yu;Basura Fernando;Richard Hartley;Fatih Porikli

  • Encouraging LSTMs to Anticipate Actions Very Early

    Mohammad Sadegh Aliakbarian;Fatemeh Sadat Saleh;Mathieu Salzmann;Basura Fernando

  • On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization

    Stephen Gould;Basura Fernando;Anoop Cherian;Peter Anderson

  • Discriminative Hierarchical Rank Pooling for Activity Recognition

    Basura Fernando;Peter Anderson;Marcus Hutter;Stephen Gould

  • Discriminative feature fusion for image classification

    Basura Fernando;Elisa Fromont;Damien Muselet;Marc Sebban

  • Effective use of frequent itemset mining for image classification

    Basura Fernando;Elisa Fromont;Tinne Tuytelaars

  • Mining Mid-level Features for Image Classification

    Basura Fernando;Elisa Fromont;Tinne Tuytelaars

  • Guiding Long-Short Term Memory for Image Caption Generation.

    Xu Jia;Efstratios Gavves;Basura Fernando;Tinne Tuytelaars

  • Learning end-to-end video classification with rank-pooling

    Basura Fernando;Stephen Gould

Frequent Co-Authors

Stephen Gould
Stephen Gould Australian National University
Efstratios Gavves
Efstratios Gavves University of Amsterdam
Anoop Cherian
Anoop Cherian Mitsubishi Electric (United States)
Richard Hartley
Richard Hartley Australian National University
Mehrtash Harandi
Mehrtash Harandi Monash University
Lars Petersson
Lars Petersson Commonwealth Scientific and Industrial Research Organisation
Mathieu Salzmann
Mathieu Salzmann École Polytechnique Fédérale de Lausanne
Fatih Porikli
Fatih Porikli Australian National University
Mark Johnson
Mark Johnson Macquarie University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online options can open up more flexible and affordable routes for studying Computer Science in the USA. Many students start with an online associate degree, which provides foundational knowledge and can often be transferred toward a bachelor’s program.

For those concerned about affordability, choosing from affordable online degree programs can help reduce student debt while earning a respected qualification. Online learning has come a long way and many reputable schools now offer budget-friendly courses.

If your GPA isn’t as high as you’d like, don’t worry. There are best online colleges that accept low gpa, providing more opportunities for those who might need a second chance. Such institutions make quality education accessible to a broader range of students.

Finally, pursuing Computer Science can lead to diverse job roles—not unlike those available with other majors. To explore alternative fields, check out potential jobs for environmental science majors to see how interdisciplinary skills can expand your career pathways.

Best Scientists Citing Basura Fernando

Trending Scientists