Search Results for author: Asim Smailagic

Found 13 papers, 5 papers with code

Design, Development, and Evaluation of an Interactive Personalized Social Robot to Monitor and Coach Post-Stroke Rehabilitation Exercises

no code implementations12 May 2023 Min Hun Lee, Daniel P. Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez i Badia

In this paper, we present our work of iteratively engaging therapists and post-stroke survivors to design, develop, and evaluate a social robot exercise coaching system for personalized rehabilitation.

ExplainFix: Explainable Spatially Fixed Deep Networks

1 code implementation18 Mar 2023 Alex Gaudio, Christos Faloutsos, Asim Smailagic, Pedro Costa, Aurelio Campilho

We are first to demonstrate that all spatial filters in state-of-the-art convolutional deep networks can be fixed at initialization, not learned.

HeartSpot: Privatized and Explainable Data Compression for Cardiomegaly Detection

1 code implementation5 Oct 2022 Elvin Johnson, Shreshta Mohan, Alex Gaudio, Asim Smailagic, Christos Faloutsos, Aurélio Campilho

HeartSpot priors are ante-hoc explainable and give a human-interpretable image of the preserved spatial features that clearly outlines the heart.

Data Compression Image Compression

Enhancement of Retinal Fundus Images via Pixel Color Amplification

1 code implementation28 Jul 2020 Alex Gaudio, Asim Smailagic, Aurélio Campilho

We propose a pixel color amplification theory and family of enhancement methods to facilitate segmentation tasks on retinal images.


Designing Personalized Interaction of a Socially Assistive Robot for Stroke Rehabilitation Therapy

no code implementations13 Jul 2020 Min Hun Lee, Daniel P. Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez i Badia

The research of a socially assistive robot has a potential to augment and assist physical therapy sessions for patients with neurological and musculoskeletal problems (e. g. stroke).

Attention Filtering for Multi-person Spatiotemporal Action Detection on Deep Two-Stream CNN Architectures

no code implementations21 Jul 2019 João Antunes, Pedro Abreu, Alexandre Bernardino, Asim Smailagic, Daniel Siewiorek

Our method, using fovea attention filtering and our generalized binary loss, achieves a relative video mAP improvement of 20% over the two-stream baseline in AVA, and is competitive with the state-of-the-art in the UCF101-24.

Action Detection General Classification +1

Weighted Multisource Tradaboost

no code implementations26 Mar 2019 João Antunes, Alexandre Bernardino, Asim Smailagic, Daniel Siewiorek

In this paper we propose an improved method for transfer learning that takes into account the balance between target and source data.

Transfer Learning

MedAL: Deep Active Learning Sampling Method for Medical Image Analysis

no code implementations25 Sep 2018 Asim Smailagic, Hae Young Noh, Pedro Costa, Devesh Walawalkar, Kartik Khandelwal, Mostafa Mirshekari, Jonathon Fagert, Adrián Galdrán, Susu Xu

Active learning techniques can be used to minimize the number of required training labels while maximizing the model's performance. In this work, we propose a novel sampling method that queries the unlabeled examples that maximize the average distance to all training set examples in a learned feature space.

Active Learning Diabetic Retinopathy Detection

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