no code implementations • 2 Mar 2024 • Lian Xu, Mohammed Bennamoun, Farid Boussaid, Wanli Ouyang, Ferdous Sohel, Dan Xu
We propose AuxSegNet+, a weakly supervised auxiliary learning framework to explore the rich information from these saliency maps and the significant inter-task correlation between saliency detection and semantic segmentation.
no code implementations • 2 Feb 2024 • Linping Xu, Jiawei Jiang, Dejun Zhang, Xianjun Xia, Li Chen, Yijian Xiao, Piao Ding, Shenyi Song, Sixing Yin, Ferdous Sohel
Recently, neural networks have proven to be effective in performing speech coding task at low bitrates.
no code implementations • 2 Feb 2022 • Juan lu, Rebecca Hutchens, Joseph Hung, Mohammed Bennamoun, Brendan McQuillan, Tom Briffa, Ferdous Sohel, Kevin Murray, Jonathon Stewart, Benjamin Chow, Frank Sanfilippo, Girish Dwivedi
Conclusions Multilabel ML models can outperform clinical risk stratification scores for predicting the risk of major bleeding and death in non-valvular AF patients.
no code implementations • 3 Oct 2021 • Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel, Guojun Lu
In this work, first, we analyse deep features with Fourier transform and show that Depth Adaptive Blurring is more effective, as opposed to monotonic blurring.
no code implementations • 27 Sep 2021 • Md Tahmid Hossaina, Shyh Wei Teng, Guojun Lu, Ferdous Sohel
Convolutional Neural Networks (CNNs) are commonly designed for closed set arrangements, where test instances only belong to some "Known Known" (KK) classes used in training.
1 code implementation • ICCV 2021 • Lian Xu, Wanli Ouyang, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel, Dan Xu
Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels.
1 code implementation • 2 Mar 2021 • A S M Mahmudul Hasan, Ferdous Sohel, Dean Diepeveen, Hamid Laga, Michael G. K. Jones
The rapid advances in Deep Learning (DL) techniques have enabled rapid detection, localisation, and recognition of objects from images or videos.
no code implementations • 31 Dec 2020 • Tasfia Shermin, Shyh Wei Teng, Ferdous Sohel, Manzur Murshed, Guojun Lu
In this paper, we propose to explore global and direct attribute-supervised local visual features for both EL and FS categories in an integrated manner for fine-grained GZSL.
no code implementations • 30 Dec 2020 • Tasfia Shermin, Shyh Wei Teng, Ferdous Sohel, Manzur Murshed, Guojun Lu
Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data.
Generalized Zero-Shot Learning Generative Adversarial Network
no code implementations • 1 Dec 2020 • Saqib Ejaz Awan, Mohammed Bennamoun, Ferdous Sohel, Frank M Sanfilippo, Girish Dwivedi
State-of-the-art imputation approaches, such as Generative Adversarial Imputation Nets (GAIN), model the distribution of observed data to approximate the missing values.
1 code implementation • 16 Sep 2020 • A. Nugaliyadde, Kok Wai Wong, Jeremy Parry, Ferdous Sohel, Hamid Laga, Upeka V. Somaratne, Chris Yeomans, Orchid Foster
We used 60 WSIs for training the RCNN model and another 12 WSIs for testing.
1 code implementation • 18 Jul 2020 • Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel, Guojun Lu
In this work, we instill low-pass filtering into the AF (LP-ReLU) to improve robustness against HFc.
no code implementations • 1 Jul 2020 • Tasfia Shermin, Guojun Lu, Shyh Wei Teng, Manzur Murshed, Ferdous Sohel
The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains.
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 • IEEE Transactions on Image Processing 2019 • Qiuhong Ke, Mohammed Bennamoun, Hossein Rahmani, Senjian An, Ferdous Sohel, Farid Boussaid
Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes.
Ranked #4 on Skeleton Based Action Recognition on SYSU 3D
no code implementations • 26 Jun 2019 • Ammar Mahmood, Ana Giraldo Ospina, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid, Renae Hovey, Robert B. Fisher, Gary Kendrick
Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas.
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 • 18 Apr 2019 • Anupiya Nugaliyadde, Kok Wai Wong, Ferdous Sohel, Hong Xie
Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), and Memory Networks which contain memory are popularly used to learn patterns in sequential data.
no code implementations • 25 Mar 2019 • Tasfia Shermin, Shyh Wei Teng, Manzur Murshed, Guojun Lu, Ferdous Sohel, Manoranjan Paul
Thus, we hypothesize that the presence of this layer is crucial for growing network depth to adapt better to a new task.
no code implementations • 22 Jan 2019 • Anupiya Nugaliyadde, Kok Wai Wong, Ferdous Sohel, Hong Xie
Furthermore, the use of 3D visual representations has shown to be capable of representing the similarity and association between words.
3 code implementations • 6 Oct 2018 • Md. Zakir Hossain, Ferdous Sohel, Mohd Fairuz Shiratuddin, Hamid Laga
We discuss the foundation of the techniques to analyze their performances, strengths and limitations.
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.
no code implementations • IEEE Transactions on Image Processing ( Volume: 27 , Issue: 6 , June 2018 ) 2018 • Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid
This paper presents a new representation of skeleton sequences for 3D action recognition.
Ranked #60 on Skeleton Based Action Recognition on NTU RGB+D 120
no code implementations • 14 Nov 2017 • Senjian An, Farid Boussaid, Mohammed Bennamoun, Ferdous Sohel
By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majorization-minimization (MM) algorithms.
no code implementations • IEEE Signal Processing Letters ( Volume: 24 , Issue: 6 , June 2017 ) 2017 • Qiuhong Ke, Senjian An, Mohammed Bennamoun, Ferdous Sohel, Farid Boussaid
Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition.
Ranked #106 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • CVPR 2017 • Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid
This paper presents a new method for 3D action recognition with skeleton sequences (i. e., 3D trajectories of human skeleton joints).
Ranked #65 on Skeleton Based Action Recognition on NTU RGB+D 120
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 • 21 Nov 2016 • Ammar Mahmood, Mohammed Bennamoun, Senjian An, Ferdous Sohel
Deep residual networks have recently emerged as the state-of-the-art architecture in image segmentation and object detection.
no code implementations • 18 Aug 2016 • Qiuhong Ke, Mohammed Bennamoun, Senjian An, Farid Bossaid, Ferdous Sohel
The structural models, including the spatial and the temporal models, are learned with Long Short Term Memory (LSTM) networks to capture the dependency of the global and local contexts of each RGB frame and each optical flow image, respectively.
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 • Senjian An, Munawar Hayat, Salman H. Khan, Mohammed Bennamoun, Farid Boussaid, Ferdous Sohel
The contractive constraints ensure that the achieved separating margin in the input space is larger than or equal to the separating margin in the output layer.
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.
no code implementations • 11 Apr 2013 • Yulan Guo, Ferdous Sohel, Mohammed Bennamoun, Min Lu, Jianwei Wan
The performance of the proposed LRF, RoPS descriptor and object recognition algorithm was rigorously tested on a number of popular and publicly available datasets.