IIIT-Delhi Institutional Repository

Browsing by Author "Vatsa, Mayank (Advisor)"

Browsing by Author "Vatsa, Mayank (Advisor)"

Sort by: Order: Results:

  • Goel, Akhil; Singh, Anirudh; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (IIITD-Delhi, 2019-04-30)
    Extensive research on attacks on deep learning models has shown that these models are not as robust as they seem. A carefully designed low magnitude perturbation is enough to cause havoc and completely confuse the model. ...
  • Agarwal, Mallika; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (2017-04-18)
    Recognizing people with their face has received a lot of attention from the research community. However, face recognition for newborns is in a nascent stage. The need for effective identification of newborns has been rising ...
  • Sinha, Sanchit; Agarwal, Mohit; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (IIITD-Delhi, 2019-04-26)
    Deforestation and loss of habitat have resulted in a rapid decline of certain species of primates in forests. On the other hand, the uncontrolled growth of a few species of primates in urban areas has led to safety issues ...
  • Basak, Protichi; De, Saurabh; Vatsa, Mayank (Advisor) (2017-04-18)
    The idea of fusing multiple biometric modalities for the identification of an individual has received significant attention in the last two decades. However, this has been limited to recognizing adults only. With the quality ...
  • Kalra, Harshvardhan; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (IIIT-Delhi, 2018-07-06)
    Current face recognition systems make extensive use of class-wise disparate features drawn from faces in order to achieve state-of-the-art performances. However, there exists a multitude of information in a given image ...
  • Agrawal, Praful; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (2014-05-19)
    With the advent of research, it has been established that many leading diseases among women, such as breast cancer, cervical cancer, and autoimmune diseases, can be prevented if diagnosed at initial stage. This research ...
  • Keswani, Sumit; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (2017-04)
    In past few years, cross-modal information retrieval has drawn much attention due to significant growth in the multimodal data. It takes one type of data as the query to retrieve relevant data of multiple modalities. For ...
  • Gupta, Nikita; Gupta, Sanchit; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (2017-04-24)
    One of the challenging applications in face recognition is video surveillance, where unconstrained low-resolution video data is captured both in day and night time (visible and near-infrared) with multiple subjects in ...
  • Chawla, Mohit; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (IIIT-Delhi, 2019-07)
    With the increased interest in face recognition across di erent applications, the research in this area has ourished over the past few decades. However, face recognition with disguise variations has gained little ...
  • Sethi, Akshay; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (IIIT-Delhi, 2018-04-17)
    The first part of this work focuses on facial attribute prediction using a novel deep learning formulation, termed as R-Codean autoencoder. The work presents Cosine similarity based loss function in an autoencoder which ...
  • Bhatt, Himanshu S; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (2014-04-14)
    A covariate in face recognition can be defined as an effect that independently increases the intra-class variability or decreases the inter-class variability or both. Covariates such as pose, illumination, expression, ...
  • Verma, Priyanka; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (2015-12-03)
    Research in face and gender recognition under constrained environment has achieved an acceptable level of performance. There have been advancements in face and gender recognition in unconstrained environment, however, ...
  • Shah, Mahek; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (2015-12-05)
    With increasing security concerns, surveillance cameras are playing an important role in the society and face recognition in crowd is gaining more importance than ever. For video face recognition, researchers have primarily ...
  • Jain, Arushi; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (2017-04-18)
    Face Recognition involves a wide range of applications, many of which are centered around forensic applications. Dead bodies in large-scale calamities like foods and earthquakes require to be identified. However, the bodies ...
  • Kalra, Isha; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (IIITD-Delhi, 2019-05-20)
    Unmanned Aerial Vehicles (UAVs) or drones are often used to reach remote areas or regions which are inaccessible to humans. Equipped with a large eld of view, compact size, and remote control abilities, drones are deemed ...
  • Chopra, Shaan; Vatsa, Mayank (Advisor); Singh, Richa (Advisor); Malhotra, Aakarsh (Mentor) (IIITD-Delhi, 2019-01-22)
    Biometrics based user authentication is rather popular in mobile devices using face and fingerprints as the primary modalities. Fingerphoto (an image of a person’s finger captured using an inbuilt smartphone camera) based ...
  • Agrawal, Navin; Singh, Richa (Advisor); Vatsa, Mayank (Advisor) (2016-09-13)
    Gender classification is used in applications as a soft feature or attribute in biometrics to help identify people. Using gender classification as an indexing technique can boost the performance of facial-biometric. If the ...
  • Bharadwaj, Samarth; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (2015-09-02)
    Large scale biometric identification systems still lack the versatility to handle challenging situations such as adverse imaging conditions, missing or corrupt data, and non-conventional operating scenarios. It is well ...
  • Garg, Rishabh; Baweja, Yashasvi; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (IIITD-Delhi, 2018-11)
    Heterogeneous biometric recognition requires matching images with variations such as resolution and spectrum. Heterogeneity in images often reduces the inter-class homogeneous distance while increasing the intra-class ...
  • Jain, Anubhav; Vatsa, Mayank (Advisor); Singh, Richa (Advisor) (IIITD-Delhi, 2018-01-09)
    Digital alterations have become a common trend on social media websites as well as in the entertainment industry, with magazine printing altered images of celebrities to make them look more attractive. Advancements in ...

Search Repository

Browse

My Account