It has received much research attention in recent years because of the close relationship between... more It has received much research attention in recent years because of the close relationship between object detection and video analysis and image comprehension. Traditional methods of object detection are based on hand-crafted features and architectures that are flawlessly trainable. Their performance stagnates easily by constructing complex ensembles that combine multiple lowlevel image features with high-level context from object detectors and scene classifiers. With the rapid growth of deep learning, more efficient techniques are implemented to solve the problems inherent in conventional architectures, capable of learning semantic, high-level, and deeper features. These models act differently in the context of network design, training strategy, and optimization.
Uploads
Papers by Mukul Bhardwaj