2 code implementations • 11 Apr 2024 • Aleksander Nagaj, Zenjie Li, Dim P. Papadopoulos, Kamal Nasrollahi
During training, pixel-based transformations are applied to segmented objects, and the models are then evaluated on raw images without segmentation.
1 code implementation • 31 Aug 2023 • Neelu Madan, Nicolae-Catalin Ristea, Kamal Nasrollahi, Thomas B. Moeslund, Radu Tudor Ionescu
In this paper, we propose a curriculum learning approach that updates the masking strategy to continually increase the complexity of the self-supervised reconstruction task.
1 code implementation • 25 Sep 2022 • Neelu Madan, Nicolae-Catalin Ristea, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah
In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
Ranked #4 on Anomaly Detection on CUHK Avenue
no code implementations • 16 Jul 2022 • Antonio Barbalau, Radu Tudor Ionescu, Mariana-Iuliana Georgescu, Jacob Dueholm, Bharathkumar Ramachandra, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature.
Ranked #2 on Anomaly Detection on CUHK Avenue
no code implementations • 16 Jan 2022 • Javier Selva, Anders S. Johansen, Sergio Escalera, Kamal Nasrollahi, Thomas B. Moeslund, Albert Clapés
Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video.
4 code implementations • CVPR 2022 • Nicolae-Catalin Ristea, Neelu Madan, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah
Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field.
Ranked #1 on Anomaly Detection on CUHK Avenue (TBDC metric)
no code implementations • 5 Feb 2021 • Andreas Aakerberg, Kamal Nasrollahi, Thomas B. Moeslund
Experimental results on both real and artificially corrupted face images show that our method results in more detailed reconstructions with less noise compared to existing State-of-the-Art (SoTA) methods.
3 code implementations • 26 Nov 2020 • Adrien Deliège, Anthony Cioppa, Silvio Giancola, Meisam J. Seikavandi, Jacob V. Dueholm, Kamal Nasrollahi, Bernard Ghanem, Thomas B. Moeslund, Marc Van Droogenbroeck
In this work, we propose SoccerNet-v2, a novel large-scale corpus of manual annotations for the SoccerNet video dataset, along with open challenges to encourage more research in soccer understanding and broadcast production.
Ranked #1 on Camera shot segmentation on SoccerNet-v2
no code implementations • 3 Apr 2020 • Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei, Kamal Nasrollahi, Thomas B. Moeslund
Then, the proposed method extracts deep semantic information from a fully convolutional FEN and fuses it with the best ResNet-based feature maps to strengthen the target representation in the learning process of continuous convolution filters.
no code implementations • 25 May 2018 • Alireza Sepas-Moghaddam, Mohammad A. Haque, Paulo Lobato Correia, Kamal Nasrollahi, Thomas B. Moeslund, Fernando Pereira
This paper proposes a double-deep spatio-angular learning framework for light field based face recognition, which is able to learn both texture and angular dynamics in sequence using convolutional representations; this is a novel recognition framework that has never been proposed before for either face recognition or any other visual recognition task.