activity
20162024
most citedSentiment-driven Community Profiling and Detection on Social Media

8 citations · 15 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2024

Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View

Andreea Ardelean, Mert Özer, Bernhard Egger

Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of…

cs.CV2024★ 2 cited

Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging

Mert Özer, Maximilian Weiherer, Martin Hundhausen +1

Neural Radiance Fields (NeRFs) quickly evolved as the new de-facto standard for the task of novel view synthesis when trained on a set of RGB images. In this paper, we conduct a co…

cs.LG2019★ 5 cited

Leveraging Uncertainty in Deep Learning for Selective Classification

Mehmet Yigit Yildirim, Mert Ozer, Hasan Davulcu

The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recogni…

cs.LG2019

Discovering patterns of online popularity from time series

Mert Ozer, Anna Sapienza, Andrés Abeliuk +2

How is popularity gained online? Is being successful strictly related to rapidly becoming viral in an online platform or is it possible to acquire popularity in a steady and discip…

cs.SI2018★ 8 cited

Sentiment-driven Community Profiling and Detection on Social Media

Amin Salehi, Mert Ozer, Hasan Davulcu

Web 2.0 helps to expand the range and depth of conversation on many issues and facilitates the formation of online communities. Online communities draw various individuals together…

cs.SI2016

Community Detection in Political Twitter Networks using Nonnegative Matrix Factorization Methods

Mert Ozer, Nyunsu Kim, Hasan Davulcu

Community detection is a fundamental task in social network analysis. In this paper, first we develop an endorsement filtered user connectivity network by utilizing Heider's struct…