Pablo Arbeláez

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

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

Multi-View Dynamic Facial Action Unit Detection

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale...

Inferring 3D Object Pose in RGB-D Images

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene...

Latent Gene Diffusion for Spatial Transcriptomics Completion

Context by region ancestry

Volumetric Semantic Segmentation Using Pyramid Context Features

Panoptic Narrative Grounding

CARDIUM: Congenital Anomaly Recognition with Diagnostic Images and Unified Medical Records

Semantic contours from inverse detectors

Cerberus: A Multi-headed Network for Brain Tumor Segmentation

Rethinking Clustering for Robustness

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

Analysis of PHOW representations for Alzheimer disease classification on brain structural MRI

FeST: Learning Spatio-Temporal Priors for Fetal Brain MRI Segmentation

SEPAL: Spatial Gene Expression Prediction from Local Graphs

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

A Hierarchical Assessment of Adversarial Severity

Guarding the Guardians: Automated Analysis of Online Child Sexual Abuse