LatinX in CV (LXCV) Research at CVPR 2023

This is an official workshop of the LatinX in AI (LXAI) organization, known as LatinX in Computer Vision (LXCV) at CVPR, which will be hosted on Sun, Jun 18, 2023 – Thu, Jun 22, 2023 at Vancouver Convention Center, Vancouver, Canada.

How to Attend CVPR2023

REGISTRATION

Program Schedule

KEYNOTE SPEAKERS

nin hirata keynote lxcv cvpr2023
henry keynote lxcv cvpr2023
miguel keynote lxcv cvpr2023

  • Nina S. T. Hirata is an associate professor of the Computer Science Department, Institute of Mathematics and Statistics, at the University of São Paulo, Brazil. She has along experience in teaching and research involving Pattern Recognition, Machine/Deep Learning, and Computer Vision, covering fundamentals, methods, and applications in the fields such as Astronomy, Oceanography, Biomedicine, and Document Image Analysis. She enthusiastically promotes education and scientific training on machine learning and artificial intelligence through student supervision, courses, and talks.

  • Henry received a PhD in Electrical and Computer Engineering from the University of Delaware in 2013. Since 2006 he has been a full Professor of the Department of Systems Engineering and Informatics at the Universidad Industrial de Santander (UIS), Colombia, where is the leader of the High-Dimensional Signal Processing (HDSP) Research group.  He was named a Senior Member of IEEE in 2017 and was a visiting researcher at Stanford University, USA, in 2020. He has published more than 100 papers in international scientific conferences and journals and holds three patents. His research interests include high-dimensional signal processing, computational imaging, optical imaging, compressed sensing, seismic imaging, medical imaging, hyperspectral imaging, and deep optical sensor design.

  • Miguel is a Research Scientist at Apple Machine Learning Research (MLR), where he carries out research in machine learning and computer vision. His current focus is on developing generative models that make as little assumptions about data as possible. Before joining Apple, he held a Postdoctoral position at Björn Ommer's lab, where he led several research projects around self-supervision in deep learning, as well as the first forays into generative modeling (pre Stable Diffusion). Miguel got a Ph.D in Machine Learning in 2015 from University of Barcelona advised by Sergio Escalera and Oriol Pujol, working on learning Error-Correcting representations from data. Miguel spent a good part of his Ph.D at Carnegie Mellon University working with Fernando de la Torre on matrix factorization methods.

TUTORIAL SPEAKER

luis tutorial lxcv cvpr2023

  • Luis is the author of the best-seller Grokking Machine Learning and maintains the Serrano channel. Academy on YouTube, with over 100K subscribers. Luis has a Ph.D. in mathematics from the University of Michigan and has worked in machine learning at Apple, Google, and other technology companies. Luis is an educator with popular machine learning and math courses on platforms like Coursera and Udacity.

ACCEPTED PAPERS & ABSTRACTS

Full Papers

Title Presenting Author Affiliation Presentation Type
Difficulty Estimation with Action Scores for Computer Vision Tasks Matias A Valdenegro Toro University of Groningen, Department of AI Oral
Zero-shot Classification at Different Levels of Granularity Matias Daniel Molina National University of Córdoba Oral
Detail-Preserving Self-Supervised Monocular Depth with Self-Supervised Structural Sharpening Juan Luis Gonzalez Korea Advanced Institute of Science and Technology Oral
LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance Regularization Roman A Jacome Univesridad Industrial de Santander Oral
Isolated Sign Language Recognition based on Tree Structure Skeleton Images David Laines Tecnológico de Monterrey Oral
SUPRA: Superpixel Guided Loss for Improved Multi-modal Segmentation in Endoscopy Rafael Martínez García Peña ITESM Oral
Deep Prototypical-Parts Ease Morphological Kidney Stone Identification and are Competitively Robust to Photometric Perturbations Daniel Flores Araiza ITESM Oral
Wildlife Image Generation from Scene Graphs Yoshio J Rubio Samsung Research Tijuana Oral
Towards Characterizing the Semantic Robustness of Face Recognition Juan C Perez KAUST Oral
High-level context representation for emotion recognition in images Willams Costa Voxar Labs Oral

Extended Abstracts

Title Presenting Author Affiliation Presentation Type
Assessment and Follow-up of Chronic Leprosy Wounds with Deep Learning and Smartphone PhotographyKaren SánchezUniversidad Industrial de SantanderPoster
Multi-Scale Structural-aware Exposure Correction for Endoscopic ImagingRicardo EspinosaUniversidad PanamericanaPoster
A novel approach for skin lesion symmetry classification with a deep learning modelLidia Talavera-MartínezUniversity of the Balearic IslandsPoster
A Fast Multiple Cue Fusing Approach for Human Emotion RecognitionWillams CostaVoxar LabsPoster
Sign Language Translation from Instructional VideosLaia TarrésUniversitat Politecnica de CatalunyaPoster
Control of a Virtual Reality Environment for Upper Limb Movement using a Motor Imagery-based Brain Computer InterfaceOscar A. ManchaTecnológico de MonterreyPoster
Continuous Cartesian Genetic Programming based representation for Multi-Objective Neural Architecture Search for Image ClassificationCosijopii Garcia-GarciaInstituto Nacional de Astrofísica óptica y Electrónica (INAOE)Poster
Transfer Learning for Fine-grained Classification Using Semi-supervised Learning and Visual TransformersManuel LagunasAmazonPoster
Contrast enhancement in infrared and color images by homomorphic filtering and cluster-chaotic optimization (cco)Angel G ChavarinUniversidad de GuadalajaraPoster
TADIL: Task-Agnostic Domain-Incremental Learning through Task-ID Inference using Transformer Nearest-Centroid EmbeddingsGusseppe Bravo-RoccaUniversitat Politecnica de CatalunyaPoster
Bessel-NeRF: An Analytic Integrated Positional Encoding for Neural Radiance FieldsBrian Kostadinov Isaac MedinaDurham UniversityPoster
Stochastic Deep Image Prior for Multishot Compressive Spectral Image FusionRoman A JacomeUnivesridad Industrial de SantanderPoster
Transfer Robustness to Downstream Tasks Through Sampling Adversarial PerturbationsIván Reyes-AmezcuaCINVESTAVPoster
Leveraging improved triplet loss for robust action segmentationElena Belén Bueno BenitoInstitut de Robòtica i Informàtica IndustrialPoster
Impact of Video Length Reduction due to Missing Landmarks on Sign Language Recognition ModelCarlos E VasquezPontificia Universidad Católica del PerúPoster
Attention Semi-Siamese U-Net for quatification of biomarkers in tauopathiesJose A. Cantoral-CeballosTecnológico de MonterreyPoster
Layout Analysis of Document ImagesNina S. T. HirataInstitute of Mathematics and Statistics - University of São PauloPoster
A Similarity Constrained Signal Selection Algorithm for Contrastive Learning In The Detection Of Atrial Fibrillation.Alejandro Navarro LunaUniversidad Industrial de SantanderPoster
Towards Metric Monocular SLAM using Spoken Language and Object DetectionJosé Martínez-CarranzaInstituto Nacional de Astrofísica óptica y Electrónica (INAOE)Poster
Discrete Hierarchical Continual Learning for Single View Geo-LocalisationAldrich Cabrera PonceBenemerita Universidad Autonoma de PueblaPoster
Anomaly Detection in Surveillance Videos Using Spatio-Temporal Context InformationHernán Darío BenítezUniversidad Javeriana CaliPoster
Land Cover Classification using Compressive Covariance Sampling: A Case Study at Valle de San Jose, ColombiaTatiana Gelvez-Barrera Universidad Industrial de SantanderPoster

CALL FOR PARTICIPATION

The workshop is a one-day event with invited speakers, oral presentations, and posters. The event brings together faculty, graduate students, research scientists, and engineers for an opportunity to connect and exchange ideas. There will be a panel discussion and a mentoring session to discuss current research trends and career choices in computer vision.

While all presenters will identify primarily as LatinX, all are invited to attend. LatinX in AI encourage application for financial support to attend It must be noted that the Latinx in AI organization can provide financial support for attending the conference, either in the form of registration fees or other travel expense, if you have any questions feel free to contact us at lxcv2023-chairs@latinxinai.org

ORGANIZERS

Workshop Chairs

Operation and Logistics Chairs — Estefania Talavera (University of Twente), Fabian Caba (Adobe), Carlos Hinojosa (KAUST)

Presentation Chairs — Daniel Flores (Tecnologico de Monterrey), Rodolfo Valiente (University of Central Florida)

Mentorship Chairs — Leissi Castañeda (The Janssen Pharmaceutical Companies of Johnson & Johnson), Francisco López (Tecnologico de Monterrey)

Program Committee Chairs — Paola Ruiz (Universidad de los Andes), Alejandro Pardo (KAUST), Tatiana Gelvez (Université de Lyon, CREATIS)

Public Relations & Website Chairs — Maria Luisa Santiago (Accel AI), Karen Sánchez (Universidad Industrial de Santander), Gilberto Ochoa (Tecnologico de Monterrey), Victor Escorcia (Samsung AI Reseach Centre)

Sponsor & Finance Chair — Karina Perez (Universidad Panamericana), Amanda Duarte (Barcelona Supercomputing Center), Lidia Talavera (Universitat de les Illes Balears)

Volunteer Chair — Martin Menchon (Bayer), Jhony Giraldo (Télécom Paris, Institute Polytechnique de Paris)

Visa Chair — Lourdes Ramirez (Universidad Nacional de Trujillo)

MENTORSHIP PROGRAM

As part of the LXCV workshop, LatinX in AI hosts their mentoring program. The LatinX in AI Mentoring Program requires mentors and mentees to meet once a month. Applicants are encouraged to apply by March 12th to participate in the CVPR workshop. The decision of the matched mentors and mentees will be published by March 31st. On the day of the workshop, some mentees will be asked to share their experiences and the learnings they obtained from the program.

Important dates:

March 12th, 2023: Deadline to Apply for the CVPR Mentoring Program (Mentors & Mentees)

March 31st. 2023: Matching results for Mentee/Mentors will be announced

Following the completion of this program, you'll be asked to complete a quick survey about your experience and opportunities for our improvement. Mentors who complete the program and survey are eligible to receive a $25 gift voucher as a token of appreciation on behalf of LatinX in AI.

Mentor Application - https://www.latinxinai.org/mentor-application

Mentor Application - https://www.latinxinai.org/mentee-application

LXCV IMPORTANT DATES

Full Papers (11h59 PM PST)
March 2nd, 2023 - Sign up as Reviewer Deadline
March 15th, 2023 - Full Paper Submission Deadline
April 3, 2023 - Notification of Submission Acceptance
April 6th, 2023 - Camera-ready Submissions

Extended Abstracts (11h59 PM PST)
March 31st, 2023 - Abstract Paper Submission Deadline
April 21st, 2023 - Notification of Submission Acceptance
May 5th, 2023 - Camera-ready Submissions

April 8, 2023 - Call for Keynotes

April 8, 2023 - Call for Tutorials

FINANCIAL ASSISTANCE

LatinX in AI is committed to supporting LatinX & Hispanic individuals from all around the world. This year since the workshop and CVPR conference will be virtual, we want to ensure that our workshop is accessible to everyone, no matter where they live. As such, we are happy to provide support for registration fees and internet data grants to help those that have financial needs.

If you believe you need financial assistance to cover your internet/data expenses or to virtually register to CVPR, please make sure to fill out these applications as accurately and truthfully as possible.

LXAI Grant Form

CVPR DEI Grant Form

PROGRAM COMMITTEE

The LXCV Organizers are genuinely grateful to the following amazing individuals 👏🏽. The event would not have been possible without the tireless efforts of our reviewers. Your professionalism, expertise, and friendly demeanor helped to create a welcoming and enjoyable experience for the authors. Thank you for being a vital part of our team and making our event a huge success!

Full Papers Reviewers

Anthony Cioppa

Rodolfo Valiente

Andrés Villa

Brayan S. Zapata-Impata

Carlos E Thomaz

CJ Barberan

Dennis Nuñez-Fernández

Guillaume Jeanneret

Jesus Zarzar

Jorge Bacca

Juan C LeonJuan C Perez

Nils Murrugarra-Llerena

Paola Cascante-Bonilla

Peratham Wiriyathammabhum

Sara Rojas Martinez

Shyamal Buch

Amanda Duarte

Andrés A Hernández

Antoine Manzanera

Carlos A Miranda

Catalina Gomez

Claudio R Jung

Cristhian D Forigua

Eduardo Ulises Moya

Eric K. Tokuda

Ferley Medina

Fernando Wario

Gilberto Ochoa-Ruiz

Jesus García-Ramírez

Jorge Sanchez

Juan Luis Gonzalez

Julio Cardenas Chapellin

Karen Sánchez

Lama Alssum

Laura Daza

Laura Montoya

Lucia Cipolina-Kun

Manuel Loaiza Fernandez

Matias A Valdenegro Toro

Mattia Soldan

Miguel A Marquez

Motasem Alfarra

Ricardo Andres Diaz

Roberto Javier Lopez-Sastre

Roger D. Soberanis-Mukul

Rosa Y. G. Paccotacya-Yanque

Sandra Avila

Silvio Giancola

Thiago L. T. da Silveira

Victor A Escorcia

Yasir M Ghunaim

Zhuang Zhuang Chen

Extended Abstract Reviewers

CJ Barberan

Rodolfo Valiente

Ahmad Diab

Akshay R Kulkarni

Ali K Thabet

Andres Marrugo

Brayan Monroy

Carlos A Miranda

Claudia V Correa

Grigorios Chrysos

Jhon E Lopez

Jonathan Arley Monsalve

Lucia Cipolina-Kun

Marks CalderonSahib Singh

Bhalaji Nagarajan

Carlos Rodriguez-Pardo

Deisy Chaves

Eduardo Ulises Moya

Jose A Sosa Martinez

Karen Sánchez

WORKSHOP SPONSORS

If you are interested in becoming a sponsor, please send us a message at sponsor@latinxinai.org and we will follow up with more information.

PLATINUM

GOLD

BRONZE

NICKEL

CALL FOR PAPERS

We strongly encourage students, post-docs, and researchers who primarily identify as LatinX , working anywhere in the world in all areas of Computer Vision to submit work describing new ideas, work-in-progress as well as previously or concurrently published research. 

We welcome submissions in theoretical and methodological contributions, but also applications. While the presenting author need not be the first author of the work, we encourage authors to highlight the contribution of Latinx individuals — particularly the presenting author — in the abstract. While the event focuses primarily on researchers who identify as Latinx, everyone is invited to attend. 

Topics of interest include all aspects of computer vision and pattern recognition, for guidance, you can check the topics of interest of conferences such as ECCV, ICCV, and CVPR. 

We accept the following kind of submissions:

  • Full Paper: Up to 8 pages excluding references. We allow supplementary material in another file. Accepted papers of this kind will be part of the official CVPR workshop proceedings and presented in the workshop. Note that these papers are expected to present novel and complete research.

IMPORTANT: Accepted papers will be given registration to CVPR.

  • Extended abstracts: Up to four (4) pages excluding references. They can present work in progress, exploratory/preliminary research or already published work, or any relevant computer vision applications for Latin America. Accepted papers in this track will not be archived in the CVPR workshop proceedings and can be published in another venue in the future.

Submissions will be double-blind peer-reviewed and should be submitted as a single PDF file. The submissions should strictly follow the guidelines provided by the CVPR 2023 to avoid the risk of being rejected without consideration of their merits. Please download and use the CVPR 2023 Author Kit for your submission. Submissions must state the research problem, motivation, and technical contribution. All submissions must be self-contained and include all figures, tables, and references. 

The submission deadlines for the full papers and extended abstracts as well as other important dates are given below. Please note that no extensions will be offered for submissions.

Become an LXAI Member Today!