Search Results for author: Pablo Arbeláez

Found 34 papers, 22 papers with code

Pixel-Wise Recognition for Holistic Surgical Scene Understanding

4 code implementations20 Jan 2024 Nicolás Ayobi, Santiago Rodríguez, Alejandra Pérez, Isabela Hernández, Nicolás Aparicio, Eugénie Dessevres, Sebastián Peña, Jessica Santander, Juan Ignacio Caicedo, Nicolás Fernández, Pablo Arbeláez

This paper presents the Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies (GraSP) dataset, a curated benchmark that models surgical scene understanding as a hierarchy of complementary tasks with varying levels of granularity.

Scene Understanding Segmentation

Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models

1 code implementation19 Dec 2023 Angela Castillo, Jonas Kohler, Juan C. Pérez, Juan Pablo Pérez, Albert Pumarola, Bernard Ghanem, Pablo Arbeláez, Ali Thabet

Our findings provide insights into the efficiency of the conditional denoising process that contribute to more practical and swift deployment of text-conditioned diffusion models.

Denoising Neural Architecture Search

SEPAL: Spatial Gene Expression Prediction from Local Graphs

1 code implementation2 Sep 2023 Gabriel Mejia, Paula Cárdenas, Daniela Ruiz, Angela Castillo, Pablo Arbeláez

Spatial transcriptomics is an emerging technology that aligns histopathology images with spatially resolved gene expression profiling.

Graph Neural Network

STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction

1 code implementation25 Aug 2023 Cristina González, Nicolás Ayobi, Felipe Escallón, Laura Baldovino-Chiquillo, Maria Wilches-Mogollón, Donny Pasos, Nicole Ramírez, Jose Pinzón, Olga Sarmiento, D Alex Quistberg, Pablo Arbeláez

This paper introduces a novel benchmark to study the impact and relationship of built environment elements on pedestrian collision prediction, intending to enhance environmental awareness in autonomous driving systems to prevent pedestrian injuries actively.

Autonomous Driving object-detection +1

BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis

no code implementations21 Apr 2023 Angela Castillo, Maria Escobar, Guillaume Jeanneret, Albert Pumarola, Pablo Arbeláez, Ali Thabet, Artsiom Sanakoyeu

To the best of our knowledge, this is the first approach that uses the reverse diffusion process to model full-body tracking as a conditional sequence generation task.

Mixed Reality Motion Synthesis

JoB-VS: Joint Brain-Vessel Segmentation in TOF-MRA Images

1 code implementation16 Apr 2023 Natalia Valderrama, Ioannis Pitsiorlas, Luisa Vargas, Pablo Arbeláez, Maria A. Zuluaga

These results show the adequacy of JoB-VS for the challenging task of vessel segmentation in complete TOF-MRA images.

Data Augmentation Segmentation

MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation

1 code implementation16 Mar 2023 Nicolás Ayobi, Alejandra Pérez-Rondón, Santiago Rodríguez, Pablo Arbeláez

We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation.


Towards Holistic Surgical Scene Understanding

1 code implementation8 Dec 2022 Natalia Valderrama, Paola Ruiz Puentes, Isabela Hernández, Nicolás Ayobi, Mathilde Verlyk, Jessica Santander, Juan Caicedo, Nicolás Fernández, Pablo Arbeláez

Second, we present Transformers for Action, Phase, Instrument, and steps Recognition (TAPIR) as a strong baseline for surgical scene understanding.

Atomic action recognition Scene Understanding

Video Swin Transformers for Egocentric Video Understanding @ Ego4D Challenges 2022

no code implementations22 Jul 2022 Maria Escobar, Laura Daza, Cristina González, Jordi Pont-Tuset, Pablo Arbeláez

We implemented Video Swin Transformer as a base architecture for the tasks of Point-of-No-Return temporal localization and Object State Change Classification.

Object Object State Change Classification +2

Towards Assessing and Characterizing the Semantic Robustness of Face Recognition

no code implementations10 Feb 2022 Juan C. Pérez, Motasem Alfarra, Ali Thabet, Pablo Arbeláez, Bernard Ghanem

We propose a methodology for assessing and characterizing the robustness of FRMs against semantic perturbations to their input.

Face Recognition

Generalized Real-World Super-Resolution through Adversarial Robustness

1 code implementation25 Aug 2021 Angela Castillo, María Escobar, Juan C. Pérez, Andrés Romero, Radu Timofte, Luc van Gool, Pablo Arbeláez

Instead of learning a dataset-specific degradation, we employ adversarial attacks to create difficult examples that target the model's weaknesses.

Adversarial Robustness Super-Resolution

Towards Robust General Medical Image Segmentation

2 code implementations9 Jul 2021 Laura Daza, Juan C. Pérez, Pablo Arbeláez

The reliability of Deep Learning systems depends on their accuracy but also on their robustness against adversarial perturbations to the input data.

Image Classification Image Segmentation +3

SIMBA: Specific Identity Markers for Bone Age Assessment

1 code implementation10 Jul 2020 Cristina González, María Escobar, Laura Daza, Felipe Torres, Gustavo Triana, Pablo Arbeláez

With this lack of available methods as motivation, we present SIMBA: Specific Identity Markers for Bone Age Assessment.

Hand Pose Estimation

Rethinking Clustering for Robustness

1 code implementation13 Jun 2020 Motasem Alfarra, Juan C. Pérez, Adel Bibi, Ali Thabet, Pablo Arbeláez, Bernard Ghanem

This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness.


Classifying Image Sequences of Astronomical Transients with Deep Neural Networks

no code implementations28 Apr 2020 Catalina Gómez, Mauricio Neira, Marcela Hernández Hoyos, Pablo Arbeláez, Jaime E. Forero-Romero

Supervised classification of temporal sequences of astronomical images into meaningful transient astrophysical phenomena has been considered a hard problem because it requires the intervention of human experts.

Classification General Classification +3

SMIT: Stochastic Multi-Label Image-to-Image Translation

1 code implementation10 Dec 2018 Andrés Romero, Pablo Arbeláez, Luc van Gool, Radu Timofte

This problem is highly challenging due to three main reasons: (i) unpaired datasets, (ii) multiple attributes, and (iii) the multimodality (e. g., style) associated with the translation.

Image-to-Image Translation Translation

The 2017 DAVIS Challenge on Video Object Segmentation

no code implementations3 Apr 2017 Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbeláez, Alex Sorkine-Hornung, Luc van Gool

The DAVIS Challenge follows up on the recent publication of DAVIS (Densely-Annotated VIdeo Segmentation), which has fostered the development of several novel state-of-the-art video object segmentation techniques.

Object Scene Classification +5

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

2 code implementations17 Jan 2017 Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs).

Boundary Detection Contour Detection +7

Deep Retinal Image Understanding

1 code implementation5 Sep 2016 Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool

This paper presents Deep Retinal Image Understanding (DRIU), a unified framework of retinal image analysis that provides both retinal vessel and optic disc segmentation.

General Classification Image Classification +4

Convolutional Oriented Boundaries

1 code implementation9 Aug 2016 Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs).

Contour Detection General Classification +2

Oracle MCG: A first peek into COCO Detection Challenges

no code implementations14 Aug 2015 Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool

The recently presented COCO detection challenge will most probably be the reference benchmark in object detection in the next years.

Object object-detection +1

Inferring 3D Object Pose in RGB-D Images

no code implementations16 Feb 2015 Saurabh Gupta, Pablo Arbeláez, Ross Girshick, Jitendra Malik

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library.


Hypercolumns for Object Segmentation and Fine-grained Localization

6 code implementations CVPR 2015 Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik

Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation.

Object Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.