Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms

Analysis of real-time hostile activitiy detection from spatiotemporal features using time distributed deep convolutional neural networks, recurrent neural networks and attention-based mechanisms

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.

Detalles Bibliográficos
Autores principales: Siddique, Labib Ahmed, Junhai, Rabita, Islam, Moshfeka, Qader, Shafinaz
Otros Autores: Chakrabarty, Dr. Amitabha
Formato: Tesis
Lenguaje:en_US
Publicado: Brac University 2022
Materias:
Artificial Intelligence
Deep learning
Neural network
Violence detection
Video classification
Attention based encoder
LRCN
ConvLSTM
Transformer
C3D
Neural networks (Computer science)
Neural network.
Deep learning (Machine learning)
Acceso en línea:http://hdl.handle.net/10361/17652

Internet

http://hdl.handle.net/10361/17652

Ejemplares similares