Xavier Giró
Position | |
---|---|
Associate Professor | xavier.giro@upc.edu |
Office | Phone |
---|---|
Biography
NOTICE: Since July 2022, I am on leave for a full-time job at Amazon Science Barcelona. I have published my teaching material in this site. If you are a master or PhD student interested in an internship at Amazon, you can apply here.
Xavier Giro-i-Nieto is an applied scientist at Amazon Barcelona, in the science team lead by Aleix Martinez and Francesc Moreno-Noguer. Until 2022, he was an associate professor at the Universitat Politecnica de Catalunya (UPC) in Barcelona, member of the Image Processing Group (GPI), Intelligent Data Science and Artificial Intelligence Research Center (IDEAI-UPC) and the Institute of Industrial Robotics (IRI UPC-CSIC). He graduated in Telecommunications Engineering at ETSETB (UPC) in 2000, after completing his master thesis on image compression at the Vrije Universiteit in Brussels (VUB) with Prof. Peter Schelkens. After working one year in Sony Brussels, he returned to UPC to obtain a PhD on computer vision, supervised by Prof. Ferran Marqués and Prof. Shih-Fu Chang from the Digital Video and MultiMedia laboratory at Columbia University, that he repeatedly visited between 2008-2014. Dr. Giró was the director of the Postgraduate on Artificial Intelligence with Deep Learning at UPC School, and also taught undergradute and graduate course on deep learning at ESEIAAT and ETSETB schools at UPC, as well as the Master in Computer Vision of Barcelona. He regularly collaborated with the Insight Center of Data Analytics at Dublin City University, and is a member of the Governance Committee of the Science Foundation Ireland Centre for Research Training in Machine Learning. From a transfer technology perspective, he collaborated with Barcelona-based company Crisalix, and was a member of the scientific advisory committee of Vilynx, which was acquired by Apple in 2020. He is a member of the ELLIS Barcelona unit and the Computer Vision Foundation. He is a funding organizer of the Deep Learning Barcelona Symposium, and serves as area chair in computer vision conferences like ICCV 2024 and CVPR 2025.
Scientific IDs: Google Scholar, WoK Researcher ID: M-5834-2013, ORCID: 0000-0002-9935-5332, Scopus Author ID: 35098596700, UPC Futur
- Current PhD student: Laia Tarrés, co-advised with Jordi Torres (UPC), Coloma Ballester and Josep Blat (UPF).
- Former PhD students (with employer after graduation): Carles Ventura (UOC 2016), Amaia Salvador (Amazon 2019), Víctor Campos (Deepmind 2020), Míriam Bellver (Amazon 2021), Andreu Girbau (NII 2021), Eduard Ramon (Amazon 2022), Amanda Duarte (BSC 2022), Dèlia Fernandez (Apple 2023), Konstantin Schürholt (2024).
External activities
- Area Chair: CVPR 2025, ECCV 2024, ACM Multimedia (2022, 2021, 2020, 2019, 2016), ICCV 2021, WACV 2021
- Associate Editor: IEEE Transactions on Multimedia (2017-2022)
- Reviewer
- CVPR (2022, 2021, 2020, 2019), ECCV 2022, ICCV (2019, 2017), ECCV (2022, 2020), ICIP (2014, 2003), EUSIPCO 2011.
- NeurIPS (2021, 2020, 2019, 2018, 2017), ICLR (2022, 2018, 2017), ICML (2020, 2019, 2018),
- ACM Multimedia (2019, 2018, 2017, 2016, 2014), ACM ICMR (2021, 2020, 2019, 2018, 2017).
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Multimedia Tools and Applications (MTAP), EURASIP Journal on Image and Video Processing, Multimedia Systems (MMSJ), Image and Vision Computing (IMAVIS)
- Tutorial: Deep Learning for Multimedia: ACM ICMR 2020, MMM 2019.
- Organization Commitee: Deep Learning Barcelona (2023, 2022, 2021, 2019, 2018), Lifelogging Tools and Applications (LTA) workshop at ACM Multimedia 2016 & 2017, Annual Catalan Meeting on Computer Vision (2020).
- Awards & recognitions
- Top 8% reviewer at NeurIPS 2021, Top 10% reviewer at NeurIPS 2020, Top 33% reviewer at ICML 2020, Outstanding reviewer mention at CVPR 2020, Best paper award at the CVPR 2019 DeepVision Workshop, Best scanpath prediction in Salient360 ICME Challenge 2017, Best poster award at LSCVS NIPS workshop 2016, Best poster award at ICMR 2016, Among Top 10% papers in ICIP 2015, Winner of the LSUN Saliency prediction challenge in CVPRW 2015, 2nd place in ChaLearn Cultural Event Recognition Challenge in CVPRW 2015, 2nd place in MediaEval Social Event Detection 2014, 3rd place in MediaEval Social Event Detection 2013, Winner of the Videobrowser Showdown in MMM 2012.
- Advisor for the awarded MSc thesis of Adrià Romero (Càtedra Telefònica 2017), Víctor Campos (ACIA 2017), Dèlia Fernàndez (MCV 2016) and Òscar Mañas (MCV 2020).
Journal Articles top
“Neural ADMIXTURE: rapid population clustering with autoencoders”, Nature Computational Science, 2023. | ,
“Deep Variational Autoencoders for Population Genetics”, 2023. | ,
“RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation”, Multimedia Tools and Applications, 2022. (5.78 MB) | ,
“SALAI-Net: species-agnostic local ancestry inference network”, Bioinformatics, vol. 38, 2022. | ,
“Mask-guided sample selection for Semi-Supervised Instance Segmentation”, Multimedia Tools and Applications, 2020. (2.2 MB) | ,
Book Chapters and Bookstop
“Sentiment concept embedding for visual affect recognition”, in Multimodal Behavior Analysis in theWild, 1st ed., Elsevier, 2018. | ,
“Object Retrieval with Deep Convolutional Features”, in Deep Learning for Image Processing Applications, vol. 31, Amsterdam, The Netherlands: IOS Press, 2017. | ,
“Hierarchical Object Detection with Deep Reinforcement Learning”, in Deep Learning for Image Processing Applications, vol. 31, Amsterdam, The Netherlands: IOS Press, 2017. | ,
“Hierarchical Navigation and Visual Search for Video Keyframe Retrieval”, in Advances in Multimedia Modeling, vol. 7131, Springer Berlin / Heidelberg, 2012, pp. 652-654. | ,
“Rich Internet Application for Semi-automatic Annotation of Semantic Shots on Keyframes”, in Computational Intelligence for Multimedia Understanding, vol. 7242, Pisa, Italy: Springer-Verlag, 2012, pp. 172-182. (6.93 MB) | ,
Conference Papers top
“HyperFast: Instant Classification for Tabular Data”, in 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024. (3.15 MB) | ,
“Adversarial Learning for Feature Shift Detection and Correction”, in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023. | ,
“SIRA: Relightable Avatars from a Single Image”, in Winter Conference on Applications of Computer Vision (WACV), 2023. | ,
“Sign Language Translation from Instructional Videos”, in CVPR 2023 Women in Computer Vision Workshop, Vancouver, Canada, 2023. (4.64 MB) | ,
“Sign Language Video Retrieval with Free-Form Textual Queries”, in CVPR 2022 - CVF/IEEE Conference on Computer Vision and Pattern Recognition, 2022. (3.22 MB) | ,
Theses top
“Hyper-Representations: Learning from Populations of Neural Networks”, 2024. (18.12 MB) | ,
“Knowledge graph population from news streams”, Universitat Politècnica de Catalunya, Barcelona, Catalonia, 2023. (6.07 MB) | ,
“Data and methods for a visual understanding of sign languages”, 2022. | ,
“Few-shot 3D Reconstruction of Body Parts with Deep Neural Networks”, 2022. | ,
“Sports broadcasting and multiple object tracking with deep learning methods”, 2021. | ,
Other top
“Exploring Visual Representations for Sign Language Translation”. 2022. (700.12 KB) | ,Ms Thesis |
“Sign Language Translation based on Transformers for the How2Sign Dataset”, 2022. (1.56 MB) | ,Report |
“Multimodal 3D Hand Pose Enhancement for Sign Language”, 2022. (1.2 MB) | ,Report |
“Machine Learning for Genomic Sequence Processing”, 2022. | ,Report |
“Sign-Language Translation with Pseudo-Glosses”. 2022. (7.51 MB) | ,Ms Thesis |
Projects top
DeeLight: Efficient Deep Learning for Video Sequences and Point Clouds | National | Sep 2021 | Aug 2025 | |
High-Fidelity 3D Full Head Reconstruction from Few lmages | National | Aug 2021 | Jun 2022 | |
A European AI On Demand Platform and Ecosystem | European | Jan 2019 | Dec 2021 | |
SGR17 - Image and Video Processing Group | National | Jan 2017 | Sep 2021 | |
MALEGRA - Multimodal Signal Processing and Machine Learning on Graphs | National | Jan 2017 | Jun 2021 |
Research Areas top
Sign Language Recognition, Translation and Production | Internal | May 2017 | May 2026 | |
Population Genomics | Internal | Jan 2021 | Jul 2022 | |
Steganography | Internal | Sep 2019 | Jul 2022 | |
Language and Vision | Internal | Feb 2016 | Dec 2021 | |
Multimodal Deep Reinforcement Learning | Internal | Sep 2016 | Jul 2021 |
Demos and Resources top
EgoMon Gaze & Video Dataset | Dataset | Jul 2016 | |
UPC at CVPRW Visual Question Answering Challenge 2016 | Software | Jun 2016 | |
UPC at CVPRW ActivityNet Challenge 2016 | Software | Jun 2016 | |
Faster R-CNN Features for Instance Search (software) | Software | May 2016 | |
Sentiment maps generator | Software | Apr 2016 |
Teaching top
Acronym | Title | Level | College |
---|---|---|---|
AIDL | Artificial Intelligence with Deep Learning | Postgraduate | UPC School |
ARAP | Deep and Reinforcement Learning | Bachelor | ETSETB TelecomBCN |
DLMM | Deep Learning for Multimedia | Master & PhD | Dublin City University |
GDSA | Multimedia Content Management and Delivery | Degree in Audiovisual Systems (3rd year) | Escola Superior d'Enginyeries Industrials, Aeroespacial i Audiovisual de Terrassa (ESEIAAT) |