José Oramas M.

Contact

Office: S.B, S.BC.702
University of Antwerp, imec-IDLab
Sint-Pietersvliet 7
Antwerp, B2000
Belgium.

tel: +32 326 59783
jose.oramas AT uantwerpen DOT be

I come from that little country in the middle of the world, Ecuador. In October 2019, I joined the IDLab at UAntwerp as Assistant Professor. I received my PhD at the Center for Processing Speech and Images (ESAT-PSI) of KU. Leuven under the advice of Prof. Tinne Tuytelaars and Prof. Luc de Raedt in April 2015. Earlier I received my engineering degree from Escuela Superior Politecnica del Litoral in Ecuador. During my Ph.D. I conducted research on understanding how groups of elements from the image (objects, object-parts, image regions, trajectories, etc.) interact and how the relationships between them can be exploited to address computer vision problems. This fueled my interest towards investigating exploratory/explanatory models that can identify informative intermediate representations and use them as means to justify the predictions that they make.

Research Interests

Representation Learning, Model Interpretability and Explainability, Multiple Instance Learning and Collective Classification, Computer Vision

I thank the following institutions for supporting my research:

News

2025-01: Two papers accepted at ICLR'25 on Twin Network Augmentation and Interpretability via Bilinear MLPs.
2025-01: One paper on the quantification of generative stability got accepted at a WACV'25 workshop.
2024-12: Our work on Compositionality and Interpretability was accepted at ColoRAI@AAAI'25.
2024-12: Our work on the interpretability of CapsNets was accepted at Neurocomputing .
2024-10: Our paper on deeper forward-forward networks got accepted at TMLR.
2024-09: I got tenured!
2024-09: I got a awarded the Education Award 23-24 by the Faculty of Science at UAntwerp.
2024-07: One paper on the analysis of feature dynamics accepted at XKDD@ECML-PKDD 2024.
2024-07: I gave a talk at the Flanders AI Forum 2024.
2024-06: One paper on the subjective evaluation of visual explanations accepted at TOMM.
2024-02: I gave a tutorial on model explainability at the BOSA'24 Winter School.
2024-01: One paper on the quantitative evaluation of visual explanations accepted at CVIU.

Awards

- Outstanding Reviewer at CVPR 2019, NeurIPS 2020, ACCV 2020, ICCV 2021, ICLR 2022
- University of Antwerp - Faculty of Science - Education Award 2023-2024
- IEEE ICIP 2020 Best Paper Award Runner-up (top 0.3%)
- BNAIC/BENELEARN 2019 Student Paper Award Finalist
- Nokia Bell Labs Student Award Benelux 2018
- NVIDIA Academic Hardware Grant 2015-2018
- ICPRAM 2012 Best Application Paper Award

Teaching Activities

Courses
- 2500WETANN: Artificial Neural Networks (Spring 2023, 2022, 2021)
- 1500WETOPS: Operating Systems (Fall 2023, 2022, 2021)
- 1500WETAPR: Advanced Programming (Fall 2022, 2021, 2020, 2019)
- 1500WETDIS: Distributed Systems (Fall 2023, 2022, 2021, 2020, 2019)
- H01D4A : (PO-3) Problem Solving and Engineering Design
(Fall 2018, 2017, 2016, 2015, 2014 (*). 2013, 2012)
- H09J2A: Pattern Recognition and Image Interpretation (Spring 2014).

Doctoral Students
- Peter Kirby
- Thomas Dooms
- Fabian Denoodt
- Stijn D'Hondt (co-advised with Hans De Winter).
- Arian Sabaghi Khameneh
- Benjamin Vandersmissen
- Jens Duym (co-advised with Ali Anwar)
- Saja Tawalbeh
- Hamed Behzadi Khormouji
- Salma Haidar

Alumni
- Kaili Wang (co-advised with Tinne Tuytelaars, now at imec).

Research

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Projects

I have collaborated in the following projects:
- Flanders AI Research Program (FAIR 2)
- imec.ICON BoB (concluded)
- UAntwerp BOF-DOCPRO4-NZ: Multimodal Relational Interpretation for Deep Models
- FWO Senior Fundamental project Desing & Interpret (concluded)
- SPOTT (concluded)
- imec.ICON Lecture+ (concluded)
- ICO LoCoVision (concluded)
- KUL-PDM/16/131: Context-aware reasoning for multi-camera action recognition.
- IWT PARIS (concluded)
- ERC COGNIMUND (concluded)

Service

Reviewer for several scientific venues including ICJV, TMM, CVIU, TIP, JMLC, NeuIPS, ICML, CVPR, ICCV, ECCV, ICLR, AAAI, ICRA.
Co-organizer of the AIMLAI workshop held in conjunction with CIKM and ECML-PKDD.
Co-organizer of the tutorial "Deep convolutional neural networks as a tool for vision science" at ECVP 2019
Session Chair at ICIP 2015, DSSV-ECDA 2023 and ECML-PKDD 2024.
Co-organizer of the Latin American Free Software Installation Festival (FLISOL) 2007-2009 at Guayaquil-Ecuador.
Co-founder of ESPOL’s Free Software community (KOKOA-ESPOL).

Technical Talks

14/10/2024 "Model Interpretability: A Machine-centric View to Model Transparency" Flanders AI Research Day 2024, Gent, Belgium.
11/06/2024 "Model Interpretability: Extracting insights on what an AI-System has learned" Flanders AI Forum 2024, Gent, Belgium.
06/02/2024 "On the Explanainabiity of Deep Visual Classifiers". Becoming Outstanding in Sports Analytics (BOSA), Gent, Belgium.
17/01/2023: "Interpretation and Explanation of Deep Computer Vision Models". VAIA & TRAIL AI courses, online.
03/02/2022 : "Sobre la Importancia de Comprender los Modelos que Construimos". ESPOL AI Seminar Series, online.
09/07/2020 : "Making Learning-based Visual Represetations more Intelligible". Data Science Portugal (DSPT) Webinar Series, online.
07/11/2019 : "Interpreting and Explaining Deep Models Visually". BNAIC/BENELEARN'19, Brussels, Belgium.
25/09/2019 : "Towards Object Shape Translation Through Unsupervised Generative Deep Models". ICIP'19, Taipei, Taiwan.
25/08/2019 : "Model Interpretation and Explanation for Deep Neural Networks.". ECVP'19, Leuven, Belgium.
14/05/2019 : "Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks". TTIC, Chicago, US.
01/04/2019 : "Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks". PSI lab, KU Leuven. Leuven, Belgium.
31/05/2018 : "End-to-end modelling of visual data for autonomous navigation". LICT Workshop on autonomous Systems. Leuven, Belgium.
11/07/2016 : "Motion Blur Compensation for Line Scan Cameras". LoCoVision Hands-On Workshop, Flanders Make, Leuven, Belgium.
28/09/2015 : "Towards Sign Language Recognition based on Body Parts Relations". ICIP'15, Quebec City, Canada.
29/04/2015 : "Context-based Reasoning for Object Detection and Object Pose Estimation". Arenberg Castle, KU Leuven. Leuven, Belgium.
14/08/2014 : "Scene-driven Cues for Object Viewpoint Classification". PSI lab, KU Leuven. Leuven, Belgium.
19/05/2014 : "Towards Cautious Collective Inference for Object Verification". PSI lab, KU Leuven. Leuven, Belgium.
25/04/2014 : "Reasoning about Object Relations for Object Pose Classification". NCCV'14. Ermelo, Netherlands.
24/03/2014 : "Towards Cautious Collective Inference for Object Verification". WACV'14. Steamboat Springs, US.
26/11/2013 : "Allocentric Pose Estimation". PSI lab, KU Leuven. Leuven, Belgium.
04/06/2013 : "Cautious Collective Inference for Object Detection". CS. Dept., KU Leuven. Leuven, Belgium.
25/10/2010 : "Answering Complex Questions in Natural Language using Probabilistic Logic Programming and the Web". BNAIC'10. Luxembourg.
19/10/2009 : "Sign Language Recognition Technology for the Learning of Hearing-Impaired People". SIGHI.be'09. Belgium.