Visual Learning and Intelligence Lab (VIGIL)

PUBLICATIONS RESOURCES PROJECTS EVENTS PEOPLE HOME
Snow
Forest
Snow
Snow

ABOUT VIGIL

The history of the Visual Learning and Intelligence Lab VIGIL began around 10 years ago. We are working in the area of video content analysis. The main objective of our research is to address various issues in representing videos, which can help in video classification and video abstraction for automatic indexing and retrieval of videos.
Some of the important studies include:
(a) Exploring features to describe video content
(b) Video genre classification
(c) Activity recognition
(d) Surveillance video analysis
(e) Expression recognition
(f) Active video understanding for recommendation systems

OUR EXPERTISE

We are working on video content analysis which is used for traffic management in smart cities where there is a need to analyze a large amount (hours/days) of video footage in order to locate abnormalities such as the appearance of restricted objects, accident incidents, snatch thefts, traffic rule violations, and variety of threats. Traditional computer vision techniques are unable to analyze such a huge amount of visual data generated in real-time. So, there is a need for visual big data analytics which involves processing and analyzing large streams of images and videos to find semantic patterns that are useful for interpretation. We investigate the scalable implementation of several visual computing methods on GPUs. Also, we explore efficient and real-time detection of motorcyclist driving without a helmet and accident detection in a city-scale CCTV surveillance network using efficient and compact deep-net models and edge computing frameworks resulting in patents.
We are also planning to broaden our research activity in the areas of video activity recognition and understanding by participating in the ongoing and upcoming competitions like THUMOS challenge for action localization, and YouTube 8M Video Understanding sponsored by Google. Also, we are in collaboration with industry partners, Sellomni, and The Hook in order to develop social video recommender systems with active video content understanding and community interest detection.

NEWS BULLETIN

  • [2018/12/07] VIGIL student won first prize at eighth IDRBT Doctoral Colloquium

    • Dinesh Singh has won the first prize for his contribution entitled "Graph Formulation of Video Activities for Abnormal Activity Recognition" at the eighth IDRBT Doctoral Colloquium held on December 7, 2018

  • [2018/11/18] VIGIL student has been awarded 2018 IEEE BigData Travel Award

    • Dinesh Singh has been awarded 2018 IEEE BigData Travel Award to attend and present paper at IEEE International Conference on Big Data (IEEE Big Data 2018), Seattle, WA, USA

  • [2018/10/16] Paper accepted in IEEE BigData 2018

    • Dinesh Singh and C. Krishna Mohan, "Projection-SVM: Distributed Kernel Support Vector Machine for Big Data using Subspace Partitioning," accepted in IEEE International Conference on Big Data, Seattle, WA, USA, December 10-14, 2018

  • [2018/07/02] Paper accepted in BMVC 2018

    • Dinesh Singh, Abhijeet Bhure, Sumit Mamtani, and C. Krishna Mohan, "Fast-BoW: Scaling Bag-of-Visual-Words Generation," accepted in British Machine Vision Conference (BMVC), Newcastle upon Tyne, UK, Sep 2018

  • [2018/09/29] Project Proposal selected in DST-JSPS

    • Titles: Design and Development of Real-Time Transportation Safety Monitoring System for Smart Cities

    • Program: India-Japan Cooperative Science Programme (IJCSP) funded by DST-JSPS

  • [2018/07/06] VIGIL alumni offered assistant professor positions in IIIT Guwahati

    • An alumni of VIGIL Dr. Shyju Wilson offered a post of Assistant Professors in the Department of Computer Science and Engineeering, IIIT Guwahati

  • [2017/11/11] VIGIL student has been awarded 2017 IEEE HiPC Travel Grant

    • Dinesh Singh has been awarded 2017 IEEE HiPC Travel Grant to attend IEEE International Conference on High Performance Computing, Data, and Analytic (IEEE HiPC 2017), Jaipur, India

  • [2017/05/07] Paper accepted in IEEE Transactions on Intelligent Transportation Systems

    • Dinesh Singh and C. Krishna Mohan, "Deep Spatio-Temporal Representation for Detection of Road Accident using Stacked Autoencoder," accepted in IEEE Transactions on Intelligent Transportation Systems, April 2018

  • [2017/02/04] Paper accepted in IJCNN 2017

    • C. Vishnu, Dinesh Singh, and C. Krishna Mohan, "Detection of Motorcyclists without Helmet in Videos using Convolutional Neural Network," accepted in IEEE International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, May 14-19, 2017

  • [2017/01/02] Paper accepted in Pattern Recognition (Elsevier)

    • Dinesh Singh and C. Krishna Mohan, "Graph Formulation of Video Activities for Abnormal Activity Recognition," accepted in Pattern Recognition (Elsevier)

  • [2016/12/26] Paper accepted in IEEE Transactions on Big Data

    • Dinesh Singh, Debaditya Roy, and C. Krishna Mohan, "DiP-SVM: Distribution Preserving Kernel Support Vector Machine for Big Data," accepted in IEEE Transactions on Big Data

  • [2016/12/07] VIGIL student won first prize at sixth IDRBT Doctoral Colloquium

    • Mr. Earnest Paul Ijjina has won the first prize for his contribution entitled "Classification of Human Actions Using Pose-based Features and Stacked Auto Encoder" at the sixth IDRBT Doctoral Colloquium held on December 8-9, 2016

  • [2016/09/19] Two papers accepted in IEEE ICMLA 2016

    • Dinesh Singh, C. Vishnu, and C. Krinshna Mohan, "Visual Big Data Analytics for Traffic Monitoring in Smart City," 15th IEEE International Conference on Machine Learning and Applications, Anaheim, CA, USA, December 18-20, 2016

    • Nazil Perveen, Dinesh Singh, and C. Krishna Mohan, "Spontaneous Facial Expression Recognition: A Part Based Approach," accepted in 15th IEEE International Conference on Machine Learning and Applications, Anaheim, CA, USA, December 18-20, 2016

  • [2016/08/08] VIGIL student has been awarded 2018 VLDB Travel Grant

    • Dinesh Singh has been awarded VLDB Travel Grant to attend International Conference on Very Large Data Bases (VLDB 2016), New Delhi, India

  • [2016/03/29] VIGIL student has been awarded Microsoft Research Travel Grant

    • Dinesh Singh has been supported by Microsoft Research Travel Grant to attend and present paper at IEEE Congress on Evolutionary Computation (IEEE CEC 2016), Vancouver, Canada

  • [2016/03/16] Two papers accepted in IEEE WCCI 2016

    • Dinesh Singh, and C. Krinshna Mohan, "Distributed Quadratic Programming Solver for Kernel SVM using Genetic Algorithm," accepted in IEEE Congress on Evolutionary Computation (IEEE CEC), Vancouver, Canada, July 24-29, 2016

    • Kunal Dahiya, Dinesh Singh, and C. Krishna Mohan, "Automatic Detection of Bike-riders without Helmet using Surveillance Videos in Real-time," International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada, July 24-29, 2016