Semantic Segmentation under Adverse Conditions

We will soon present at BMVC 2022 our work “Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach”. This work presents a novel algorithm for harnessing synthetic data in order to improve semantic segmentation in real images.

Our work is freely available here. Our source code, simulator, and new dataset can also be obtained freely at

Congestion control algorithms for robotic swarms with a common target

Our work “Congestion control algorithms for robotic swarms with a common target based on the throughput of the target area” is already available on-line in the journal Robotics and Autonomous Systems. It presents novel algorithms for handling hard congestion situations when thousands of robots move towards a common target. This work is inspired by our previous theoretical work, but it is now focused on presenting algorithms for real robots.

Our author version is freely available at The publisher final version is at

You can also find our source code freely available at

Verifying 3D Point Cloud Machine Learning Models

Our work “3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models” was accepted in the journal Machine Learning. The paper is freely available at It presents a novel method to verify the robustness against attacks of machine learning models aimed at classifying 3D Point Cloud data.

Our tool, 3DVerifier is also released, including its source code. You can find it at

New Paper on Ad-hoc Teamwork

Our work “On-line estimators for ad-hoc task execution: learning types and parameters of teammates for effective teamwork” was recently published at the Journal Autonomous Agents and Multi-Agent Systems (JAAMAS). It presents OEATE, a novel algorithm for online estimation of teammates’ type and parameters in decentralised task execution.

The paper is freely available at The source code, built using our AdLeap-MAS framework, is available on Github.

Investigating Machine Learning Techniques for Drug Re-purpose

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

Paper in TPAMI: Text-driven video acceleration

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