1

Multi-Input Fusion for Practical Pedestrian Intention Prediction
Pedestrians are the most vulnerable road users and are at a high risk of fatal accidents. Accurate pedestrian detection and effectively …
Ankur Singh, Upendra Suddamalla
PDF
Multi-Input Fusion for Practical Pedestrian Intention Prediction
The Curious Case of Convex Neural Networks
In this paper, we investigate a constrained formulation of neural networks where the output is a convex function of the input. We show …
Sarath Sivaprasad, Ankur Singh, Naresh Manwani, Vineet Gandhi
PDF
The Curious Case of Convex Neural Networks
Pedestrian Intention Prediction with Multi-Input Concatenation
Responding safely to the pedestrians on the road is one of the critical challenges for autonomous vehicles. For smooth navigation of …
Ankur Singh, Upendra Suddamalla, Anthony Wong, Dilip Kumar Limbu
PDF
Pedestrian Intention Prediction with Multi-Input Concatenation
Video Colorization using CNNs and Keyframes extraction: An application in saving bandwidth
In this paper, we tackle the problem of colorization of grayscale videos to reduce bandwidth usage. For this task, we use some colored …
Ankur Singh, Anurag Chanani, Harish Karnick
PDF
Video Colorization using CNNs and Keyframes extraction: An application in saving bandwidth