no code implementations • 4 Dec 2023 • Jie Liu, Qilin Li, Senjian An, Bradley Ezard, Ling Li
Transformer-based models for anomaly detection in multivariate time series can benefit from the self-attention mechanism due to its advantage in modeling long-term dependencies.
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 • 16 Feb 2019 • Qilin Li, Senjian An, Ling Li, Wanquan Liu
Graph-based semi-supervised learning usually involves two separate stages, constructing an affinity graph and then propagating labels for transductive inference on the graph.
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 #65 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 • 24 Aug 2017 • Senjian An, Mohammed Bennamoun, Farid Boussaid
To show the superior compressive power of deep rectifier networks over shallow rectifier networks, we prove that the maximum boundary resolution of a single hidden layer rectifier network classifier grows exponentially with the number of units when this number is smaller than the dimension of the patterns.
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 #108 on Skeleton Based Action Recognition on NTU RGB+D
no code implementations • 30 Mar 2017 • Senjian An, Farid Boussaid, Mohammed Bennamoun, Jiankun Hu
Similarly, for a residual net and a conventional rectifier net with the same structure except for the skip connections in the residual net, the corresponding single hidden layer representation of the residual net is much more complex than the corresponding single hidden layer representation of the conventional net.
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 #69 on Skeleton Based Action Recognition on NTU RGB+D 120
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 • 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 • 18 Jun 2015 • Munawar Hayat, Salman H. Khan, Mohammed Bennamoun, Senjian An
This paper introduces a new learnable feature descriptor called "spatial layout and scale invariant convolutional activations" to deal with these challenges.
no code implementations • CVPR 2014 • Munawar Hayat, Mohammed Bennamoun, Senjian An
We propose a deep learning framework for image set classification with application to face recognition.