no code implementations • 16 Mar 2024 • Dennis Fedorishin, Livio Forte III, Philip Schneider, Srirangaraj Setlur, Venu Govindaraju
Sound event detection (SED) is an active area of audio research that aims to detect the temporal occurrence of sounds.
1 code implementation • 3 Aug 2023 • Saleem Ahmed, Bhavin Jawade, Shubham Pandey, Srirangaraj Setlur, Venu Govindaraju
We present a comprehensive study of chart visual question-answering(QA) task, to address the challenges faced in comprehending and extracting data from chart visualizations within documents.
Ranked #3 on Chart Question Answering on RealCQA (using extra training data)
no code implementations • 3 Aug 2023 • Saleem Ahmed, Pengyu Yan, David Doermann, Srirangaraj Setlur, Venu Govindaraju
A combination of sparse and dense per-pixel objectives coupled with a uni-modal self-attention-based feature-fusion layer is applied to learn KP embeddings.
no code implementations • 16 Jul 2023 • Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju
Face feature aggregation, which involves aggregating a set of N feature representations present in a template into a single global representation, plays a pivotal role in such recognition systems.
1 code implementation • 9 Jul 2023 • Bhavin Jawade, Deen Dayal Mohan, Srirangaraj Setlur, Nalini Ratha, Venu Govindaraju
Contactless fingerprint matching using smartphone cameras can alleviate major challenges of traditional fingerprint systems including hygienic acquisition, portability and presentation attacks.
1 code implementation • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 • Bhavin Jawade, Deen Dayal Mohan, Naji Mohamed Ali, Srirangaraj Setlur, Venu Govindaraju
Cross-modal retrieval is a fundamental vision-language task with a broad range of practical applications.
Ranked #1 on Cross-Modal Retrieval on MSCOCO-1k
1 code implementation • 6 Nov 2022 • Dennis Fedorishin, Deen Dayal Mohan, Bhavin Jawade, Srirangaraj Setlur, Venu Govindaraju
Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound.
no code implementations • 17 Feb 2021 • Nagashri Lakshminarayana, Yifang Liu, Karthik Dantu, Venu Govindaraju, Nils Napp
The system is implemented using an off-the-shelf hardware and software components and can be easily transfered to any ROS enabled UAVs.
no code implementations • 10 May 2020 • Vishal Vyas, Kumar Ravi, Vadlamani Ravi, V. Uma, Srirangaraj Setlur, Venu Govindaraju
For citation analysis, we developed eight datasets comprising citation sentences, which are manually annotated by us into three sentiment polarities viz.
no code implementations • 15 Nov 2018 • Neeti Narayan, Nishant Sankaran, Srirangaraj Setlur, Venu Govindaraju
We present a feature aggregation architecture called Composite Appearance Network (CAN) to address the above problem.
no code implementations • ICLR 2018 • Devansh Arpit, Yingbo Zhou, Hung Q. Ngo, Nils Napp, Venu Govindaraju
Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost.
no code implementations • 4 Mar 2016 • Devansh Arpit, Yingbo Zhou, Bhargava U. Kota, Venu Govindaraju
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks.
no code implementations • 5 Dec 2015 • Rohit Kumar Pandey, Yingbo Zhou, Bhargava Urala Kota, Venu Govindaraju
In this paper we present a framework for secure identification using deep neural networks, and apply it to the task of template protection for face authentication.
no code implementations • 14 Jun 2015 • Rohit Pandey, Yingbo Zhou, Venu Govindaraju
In this paper we present Deep Secure Encoding: a framework for secure classification using deep neural networks, and apply it to the task of biometric template protection for faces.
no code implementations • 21 May 2015 • Devansh Arpit, Yingbo Zhou, Hung Ngo, Venu Govindaraju
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks.
no code implementations • NeurIPS 2014 • Devansh Arpit, Ifeoma Nwogu, Venu Govindaraju
Modeling data as being sampled from a union of independent subspaces has been widely applied to a number of real world applications.
no code implementations • NeurIPS 2014 • Yingbo Zhou, Utkarsh Porwal, Ce Zhang, Hung Q. Ngo, XuanLong Nguyen, Christopher Ré, Venu Govindaraju
Superior performance of our method is demonstrated on a challenging relation extraction task from a very large data set that have both redundant features and sample size in the order of millions.
no code implementations • 6 May 2014 • Yingbo Zhou, Devansh Arpit, Ifeoma Nwogu, Venu Govindaraju
But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers.
no code implementations • 17 Jan 2014 • Devansh Arpit, Ifeoma Nwogu, Gaurav Srivastava, Venu Govindaraju
With increasing concerns about security, the need for highly secure physical biometrics-based authentication systems utilizing \emph{cancelable biometric} technologies is on the rise.