no code implementations • 21 Oct 2022 • Yu Xuan, Xiangyu Zhang, Shuyue Stella Li, Zihan Shen, Xin Xie, Leibny Paola Garcia, Roberto Togneri
Compared with the state-of-the-art MSF-ANC method, CRLS shows improved performance.
no code implementations • 27 Sep 2022 • Fuling Chen, Roberto Togneri, Murray Maybery, Diana Weiting Tan
For younger age groups, a broad range of acoustic factors contributed evenly to sex classification, while for older age groups, F0-related acoustic factors were found to be the most critical predictors generally.
no code implementations • 26 Sep 2022 • Xiangyu Zhang, Shuyue Stella Li, Zhanhong He, Roberto Togneri, Leibny Paola Garcia
Lyrics recognition is an important task in music processing.
no code implementations • 7 Jan 2022 • Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun
Then we use an RNN on the spatial relations to predict the spatio-temporal relations of reviewers in the group.
no code implementations • 10 Nov 2021 • Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun
Many studies proposed approaches based on user behaviors and review text to address the challenges of fraud detection.
1 code implementation • 2 Jun 2021 • Syed Saiq Hussain, Muhammad Usman, Taha Hasan Masood Siddique, Imran Naseem, Roberto Togneri, Mohammed Bennamoun
In this research a novel stochastic gradient descent based learning approach for the radial basis function neural networks (RBFNN) is proposed.
no code implementations • 25 May 2021 • Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun
Social reviews are indispensable resources for modern consumers' decision making.
1 code implementation • 6 Jul 2020 • Syed Muhammad Atif, Shujaat Khan, Imran Naseem, Roberto Togneri, Mohammed Bennamoun
A simple yet effective architectural design of radial basis function neural networks (RBFNN) makes them amongst the most popular conventional neural networks.
no code implementations • 11 Jun 2020 • Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun
However, the lack of trusted labeled data has limited the performance of the current solutions in detecting fraud reviews.
no code implementations • 10 Jun 2020 • Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun
In this research, instead of focusing only on one component, detecting either fraud reviews or fraud users (fraudsters), vector representations are learnt for each component, enabling multi-component classification.
no code implementations • 29 May 2020 • Uzair Nadeem, Mohammed Bennamoun, Roberto Togneri, Ferdous Sohel
We use this concept to directly localize images in a 3D point cloud.
no code implementations • 14 Jun 2019 • Uzair Nadeem, Mohammad A. A. K. Jalwana, Mohammed Bennamoun, Roberto Togneri, Ferdous Sohel
We use this concept to localize the position and orientation (pose) of the camera of a query image in dense point clouds.
no code implementations • 9 May 2019 • Shujaat Khan, Imran Naseem, Roberto Togneri, Mohammed Bennamoun
In this paper, we propose a novel adaptive kernel for the radial basis function (RBF) neural networks.
no code implementations • 25 Sep 2018 • Shujaat Khan, Imran Naseem, Roberto Togneri, Mohammed Bennamoun
In extreme cold weather, living organisms produce Antifreeze Proteins (AFPs) to counter the otherwise lethal intracellular formation of ice.
2 code implementations • 3 Aug 2018 • Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
We present DataDeps. jl: a julia package for the reproducible handling of static datasets to enhance the repeatability of scripts used in the data and computational sciences.
Software Engineering
1 code implementation • ACL 2018 • Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
Our tool detects the main character that each section is from the POV of, and allows the user to generate a new ebook with only those sections.
no code implementations • 26 Mar 2018 • Uzair Nadeem, Syed Afaq Ali Shah, Mohammed Bennamoun, Roberto Togneri, Ferdous Sohel
Class specific gallery subspaces are used to estimate regression models for each image of the test image set.
1 code implementation • 27 Sep 2017 • Lyndon White, Roberto Togneri, Wei Liu, Mohammed Bennamoun
Color names are often made up of multiple words.
no code implementations • 10 Jan 2017 • Syed Afaq Ali Shah, Uzair Nadeem, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
We estimate regression models for each test image using the class specific gallery subspaces.
no code implementations • 7 Jun 2016 • Salman H. Khan, Xuming He, Fatih Porikli, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
We apply a constrained mean-field algorithm to estimate the pixel-level labels, and use the estimated labels to update the parameters of the CNN in an iterative EM framework.
no code implementations • ICCV 2015 • Chao Sui, Mohammed Bennamoun, Roberto Togneri
This paper presents a novel feature learning method for visual speech recognition using Deep Boltzmann Machines (DBM).
no code implementations • 14 Aug 2015 • Salman H. Khan, Munawar Hayat, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
Class imbalance is a common problem in the case of real-world object detection and classification tasks.
no code implementations • 17 Jun 2015 • Salman H. Khan, Munawar Hayat, Mohammed Bennamoun, Roberto Togneri, Ferdous Sohel
To this end, we introduce a new large-scale dataset of 1300 object categories which are commonly present in indoor scenes.
no code implementations • CVPR 2015 • Salman H. Khan, Xuming He, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
Objects' spatial layout estimation and clutter identification are two important tasks to understand indoor scenes.
no code implementations • CVPR 2014 • Salman Hameed Khan, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
We present a practical framework to automatically detect shadows in real world scenes from a single photograph.