Spatial transcriptomics is an emerging technology that aligns histopatho...
This paper introduces a novel benchmark to study the impact and relation...
Online violence against children has increased globally recently, demand...
We present EgoCOL, an egocentric camera pose estimation method for open-...
Mixed reality applications require tracking the user's full-body motion ...
We propose the first joint-task learning framework for brain and vessel
...
We propose Masked-Attention Transformers for Surgical Instrument Segment...
Most benchmarks for studying surgical interventions focus on a specific
...
We implemented Video Swin Transformer as a base architecture for the tas...
Deep Neural Networks (DNNs) lack robustness against imperceptible
pertur...
Adversarial Robustness is a growing field that evidences the brittleness...
Real-world Super-Resolution (SR) has been traditionally tackled by first...
Deep learning models are prone to being fooled by imperceptible perturba...
The reliability of Deep Learning systems depends on their accuracy but a...
Humans are arguably one of the most important subjects in video streams,...
The "MIcro-Surgical Anastomose Workflow recognition on training sessions...
We study the task of semantic segmentation of surgical instruments in
ro...
Bone Age Assessment (BAA) is a task performed by radiologists to diagnos...
We introduce MANTRA, an annotated dataset of 4869 transient and 71207
no...
This paper studies how encouraging semantically-aligned features during ...
Current methods for active speak er detection focus on modeling short-te...
Supervised classification of temporal sequences of astronomical images i...
Intraoperative tracking of laparoscopic instruments is often a prerequis...
This work takes a step towards investigating the benefits of merging
cla...
Instance-level video segmentation requires a solid integration of spatia...
We study the problem of object detection from a novel perspective in whi...
Cross-domain mapping has been a very active topic in recent years. Given...
In this paper, we address the task of segmenting an object given a natur...
We present the 2017 DAVIS Challenge, a public competition specifically
d...
We present Convolutional Oriented Boundaries (COB), which produces multi...
This paper presents Deep Retinal Image Understanding (DRIU), a unified
f...
We present Convolutional Oriented Boundaries (COB), which produces multi...
We propose a unified approach for bottom-up hierarchical image segmentat...
The goal of this work is to replace objects in an RGB-D scene with
corre...
We segment moving objects in videos by ranking spatio-temporal segment
p...
Recognition algorithms based on convolutional networks (CNNs) typically ...
In this paper we study the problem of object detection for RGB-D images ...
We aim to detect all instances of a category in an image and, for each
i...