A Mobile Food Recognition System for Dietary Assessment

no code implementations • 20 Apr 2022 • Şeymanur Aktı, Marwa Qaraqe, Hazim Kemal Ekenel

With the model achieving 94% accuracy on 23 food classes, the developed mobile application has potential to serve the visually impaired in automatic food recognition via images.

Data Augmentation Food Recognition

Fight Detection from Still Images in the Wild

1 code implementation • 16 Nov 2021 • Şeymanur Aktı, Ferda Ofli, Muhammad Imran, Hazim Kemal Ekenel

We also propose a new dataset, named Social Media Fight Images (SMFI), comprising real-world images of fight actions.

A Comparative Study of Machine Learning Methods for Predicting the Evolution of Brain Connectivity from a Baseline Timepoint

1 code implementation • 16 Sep 2021 • Şeymanur Aktı, Doğay Kamar, Özgür Anıl Özlü, Ihsan Soydemir, Muhammet Akcan, Abdullah Kul, Islem Rekik

The competing teams developed their ML pipelines with a combination of data pre-processing, dimensionality reduction, and learning methods.

Dimensionality Reduction

MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection

1 code implementation • 9 Dec 2020 • Fabio Valerio Massoli, Fabrizio Falchi, Alperen Kantarcı, Şeymanur Aktı, Hazim Kemal Ekenel, Giuseppe Amato

Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i. e., using the output of the last layer only, MOCCA explicitly leverages the multi-layer structure of deep architectures.

Classification General Classification +1

Vision-based Fight Detection from Surveillance Cameras

1 code implementation • 11 Feb 2020 • Şeymanur Aktı, Gözde Ayşe Tataroğlu, Hazim Kemal Ekenel

This dataset is made publicly available.

Action Recognition Scene Classification