I'm a 1st-year PhD student supervised by Prof. Pietro Liò and Dr. Ferenc Huszár at the University of Cambridge, Department of Computer Science and Technology, funded by a scholarship from Twitter.
Previously, I spent 5 great years as a Machine Learning Researcher at Bitdefender. I've graduated with valedictorian distinction the BSc in Computer Science from the University of Bucharest in 2016 and the MSc in Artificial Intelligence also from the University of Bucharest in 2018.
My research focuses on Graph Neural Networks. I am particularly interested in developing techniques to extract structured representation from data and to analyse the optimisation process of different graph and hypergraph neural networks.
Publications
Dynamic Regions Graph Neural Networks for Spatio-Temporal Reasoning
Iulia Duta*, Andrei Nicolicioiu*, Marius Leordeanu
We investigate how to create node representations useful for modeling visual interaction using Graph Neural Networks. Our DyReG method can discover salient regions in the scene, without explicit object-level supervision, that correlate with true objects locations. Moreover, it improves the relational processing and obtains superior results on video classification tasks, while being more explainable.
Recurrent Space-time Graph Neural Networks
Andrei Nicolicioiu*, Iulia Duta*, Marius Leordeanu
We propose a neural graph model, recurrent in space and time, suitable for capturing both the local appearance and the complex higher-level interactions of different entities and objects within the changing world scene. Our model is general and could learn to recognize a variety of high level spatio-temporal concepts, obtaining state-of-the-art performance on the challenging Something-Something human-object interaction dataset.
Effective Receptive Field of Graph Neural Networks
Andrei Nicolicioiu*, Iulia Duta*
Technical Report
pdf
We analysed theoretically and empirically the effective receptive field for Graph Convolutional Network and Self-Attention layer.
Mining for meaning: from vision to language through multiple networks consensus
Iulia Duta*, Andrei Nicolicioiu*, Vlad Bogolin, Marius Leordeanu
We design multiple models, to explore different video encoding strategies, to explore intermediate video-language representation and to investigate the gains brought by additional tasks and features. We propose a method for video captioning by selecting from the results of multiple encoder-decoder models. Our method surpassed the state-of-the-art results on the challenging MSR-VTT dataset.
* denotes equal contribution
News
- 12/2021: Held a presentation about our paper Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks at Bucharest Deep Learning Group link
- 10/2021: Our work on Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks just got accepted to NeurIPS 2021! link
- 07/2021: Held a presentation about Graph Neural Networks with a focus on Computer Vision applications at the Human Pose Recovery and Behavior Analysis Group, University of Barcelona link
- 07/2021: Held an introductory presentation about Graph Nets at Timisoara/Strasbourg Meetup link
- 01-09/07/2020: Help as Teaching Assistent at Virtual EEML 2020 Summer School link
- 01/2020: Present Graph Neural Networks for video processing at Bitdefender TechDays link
- 06/2020: Receive best reviewer award at GRL+ Workshop - ICML 2020 link
- 01-09/07/2020: Teaching Assistent for the tutorial at EEML 2019 Summer School link
- 29/06/2019: Present our work on Recurrent Graph Neural Network at RAAI 2019, Bucharest, Romania link
- 18/03/2019: Held presentation on Recent approaches on GNNs at Bucharest Deep Learning Group link
- 18/03/2019: Present Captioning approches at Bucharest Deep Learning Group link
Teaching
Representation Learning on Graphs and Networks
University of Cambridge 2022
Teaching Assistent
University of Cambridge 2022
Teaching Assistent
Prepare material and present the practicals/assignments for the course. (MPhil ACS, Part III)
❯
Deep Learning Course
University of Bucharest 2022
Invited speaker
University of Bucharest 2022
Invited speaker
Held a presentation as invited speaker in the MPhil Deep Learning Course (MPhil)
❯
Introduction in Deep Learning
University of Bucharest 2019-2021
Lecturer/Tutor
University of Bucharest 2019-2021
Lecturer/Tutor
Prepare and present the Recurrent Neural Network lecture and mentor several students for their final projects. (MPhil)
❯
Introduction in Graph Nets
University of Bucharest 2021
Lecturer/Tutor
University of Bucharest 2021
Lecturer/Tutor
Prepare and present 2 introductory lectures about Graph Nets, together with Andrei Nicolicioiu. (MPhil)
slides1 video1 slides2 video2
❯
slides1 video1 slides2 video2
Algorithm & Data Structure
University of Bucharest 2017-2019
Teaching Assistent
University of Bucharest 2017-2019
Teaching Assistent
As a teaching assistent, I prepared and presented the laboratories and seminars and helped with the final exam. (1st-year Undergraduate)
❯
Bitdefender Deep Learning Course
Bitdefender 2019
Lecturer/Tutor
Bitdefender 2019
Lecturer/Tutor
Prepare and present the RNNs lecture and offer project mentoship for some collegues. (Industry)
❯