-
Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
Authors:
Sagar Verma,
Pravin Nagar,
Divam Gupta,
Chetan Arora
Abstract:
We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories. Further, it has been argued that traditional cues used for third person action recognition do not suffice, and egoc…
▽ More
We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories. Further, it has been argued that traditional cues used for third person action recognition do not suffice, and egocentric specific features, such as head motion and handled objects have been used for such actions. Unlike the state-of-the-art approaches, we show that a regular two stream Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) architecture, having separate streams for objects and motion, can generalize to all categories of first-person actions. The proposed approach unifies the feature learned by all action categories, making the proposed architecture much more practical. In an important observation, we note that the size of the objects visible in the egocentric videos is much smaller. We show that the performance of the proposed model improves after cropping and resizing frames to make the size of objects comparable to the size of ImageNet's objects. Our experiments on the standard datasets: GTEA, EGTEA Gaze+, HUJI, ADL, UTE, and Kitchen, proves that our model significantly outperforms various state-of-the-art techniques.
△ Less
Submitted 17 October, 2019;
originally announced October 2019.
-
U-SegNet: Fully Convolutional Neural Network based Automated Brain tissue segmentation Tool
Authors:
Pulkit Kumar,
Pravin Nagar,
Chetan Arora,
Anubha Gupta
Abstract:
Automated brain tissue segmentation into white matter (WM), gray matter (GM), and cerebro-spinal fluid (CSF) from magnetic resonance images (MRI) is helpful in the diagnosis of neuro-disorders such as epilepsy, Alzheimer's, multiple sclerosis, etc. However, thin GM structures at the periphery of cortex and smooth transitions on tissue boundaries such as between GM and WM, or WM and CSF pose diffic…
▽ More
Automated brain tissue segmentation into white matter (WM), gray matter (GM), and cerebro-spinal fluid (CSF) from magnetic resonance images (MRI) is helpful in the diagnosis of neuro-disorders such as epilepsy, Alzheimer's, multiple sclerosis, etc. However, thin GM structures at the periphery of cortex and smooth transitions on tissue boundaries such as between GM and WM, or WM and CSF pose difficulty in building a reliable segmentation tool. This paper proposes a Fully Convolutional Neural Network (FCN) tool, that is a hybrid of two widely used deep learning segmentation architectures SegNet and U-Net, for improved brain tissue segmentation. We propose a skip connection inspired from U-Net, in the SegNet architetcure, to incorporate fine multiscale information for better tissue boundary identification. We show that the proposed U-SegNet architecture, improves segmentation performance, as measured by average dice ratio, to 89.74% on the widely used IBSR dataset consisting of T-1 weighted MRI volumes of 18 subjects.
△ Less
Submitted 12 June, 2018;
originally announced June 2018.
-
An Efficient and Secure Routing Protocol for Mobile Ad-Hoc Networks
Authors:
N. Ch. Sriman Narayana Iyengar,
Syed Mohammad Ansar Sachin kumar,
Piyush Nagar,
Siddharth Sharma,
Akshay Atrey
Abstract:
Efficiency and simplicity of random algorithms have made them a lucrative alternative for solving complex problems in the domain of communication networks. This paper presents a random algorithm for handling the routing problem in Mobile Ad hoc Networks [MANETS].The performance of most existing routing protocols for MANETS degrades in terms of packet delay and congestion caused as the number of mo…
▽ More
Efficiency and simplicity of random algorithms have made them a lucrative alternative for solving complex problems in the domain of communication networks. This paper presents a random algorithm for handling the routing problem in Mobile Ad hoc Networks [MANETS].The performance of most existing routing protocols for MANETS degrades in terms of packet delay and congestion caused as the number of mobile nodes increases beyond a certain level or their speed passes a certain level. As the network becomes more and more dynamic, congestion in network increases due to control packets generated by the routing protocols in the process of route discovery and route maintenance. Most of this congestion is due to flooding mechanism used in protocols like AODV and DSDV for the purpose of route discovery and route maintenance or for route discovery as in the case of DSR protocol. This paper introduces the concept of random routing algorithm that neither maintains a routing table nor floods the entire network as done by various known protocols thereby reducing the load on network in terms of number of control packets in a highly dynamic scenario. This paper calculates the expected run time of the designed random algorithm.
△ Less
Submitted 11 May, 2010;
originally announced May 2010.