In collaboration with friends of Federal University of Viçosa (UFV), we investigated machine learning techniques in order to find potential existing drugs that could be used to inhibit the Covid-19 virus. The work, “Computational prediction of potential inhibitors for SARS-COV-2 main protease based on machine learning, docking, MM-PBSA calculations, and metadynamics” was published at PLOS ONE, and it is available here.

Source code and datasets are available in the Github repository at https://github.com/IsabelaGomes/Prediction_SARSCOV2_inhibitors.

We have released the AdLeap-MAS Framework, aimed at facilitating experiments on ad-hoc teamwork or opponent modeling, when an agent uses a model of others during decision-making. It was released as a demo paper at AAMAS, please find our paper here.

This video introduces our framework:

The framework and documentation is available in the Github repository at https://github.com/lsmcolab/adleap-mas/.

Our work “Text-driven video acceleration: A weakly-supervised reinforcement learning method” was accepted at the IEEE Transactions on Pattern Analysis and Machine Intelligence. The paper presents a novel method to automatically accelerate instructional videos based on the corresponding textual instructions. Check our video below:

The paper is available here. The source code of our algorithm is also available on Github at https://github.com/verlab/TextDrivenVideoAcceleration_TPAMI_2022.

Our BMVC paper “Sparse Adversarial Video Attacks with Spatial Transformations” is now available here. Our paper presents a novel adversarial attack strategy on videos, using both additive perturbation and spatial transformation in a unified optimisation framework.

Check our video below:

Our code is also openly available at https://github.com/TrustAI/DeepSAVA.

Our recent work “A Meta-interactive Compositional Approach that Fosters Musical Emergence through Ludic Expressivity” will be presented soon at CHI Play. The paper is now freely available here. Check our video below!

For more information, and to download our demo, check the Bubble Sounds project home page.

We recently had a paper accepted in the 2nd International Workshop on Data Quality Assessment for Machine Learning, which will be held with the International Conference on Knowledge Discovery and Data Mining (KDD) next month.

The paper describes Silver, a simulator that Abdulrahman Kerim, one of our PhD students, developed for Computer Vision applications. Our simulator produces 3D virtual worlds at run-time, aiming at photo-realism, diversity, and scalability.

The paper is available here. There is also a Github page for the simulator at https://github.com/lsmcolab/Silver.

Welcome to our new website! Here you will find the latest information on our projects and papers. Feel free to browse:

Publications: To download our research papers.
Projects: To know about some of our current projects.
People: To see the list of our current students and collaborators.
Openings: To check the current opportunities to join the lab.
About Us: To read more about who we are and what we do.

If you would like to get in touch, feel free to contact us at: l.marcolino@lancaster.ac.uk.