Search Results for author:
Found 19 papers, 4 papers with code
Fine-Grained Engine Fault Sound Event Detection Using Multimodal Signals
Sound event detection (SED) is an active area of audio research that aims to detect the temporal occurrence of sounds.
RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic
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)
SpaDen : Sparse and Dense Keypoint Estimation for Real-World Chart Understanding
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.
CoNAN: Conditional Neural Aggregation Network For Unconstrained Face Feature Fusion
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.
RidgeBase: A Cross-Sensor Multi-Finger Contactless Fingerprint Dataset
Contactless fingerprint matching using smartphone cameras can alleviate major challenges of traditional fingerprint systems including hygienic acquisition, portability and presentation attacks.
NAPReg: Nouns As Proxies Regularization for Semantically Aware Cross-Modal Embeddings
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
Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization
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.
Active Face Frontalization using Commodity Unmanned Aerial Vehicles
The system is implemented using an off-the-shelf hardware and software components and can be easily transfered to any ROS enabled UAVs.
Article citation study: Context enhanced citation sentiment detection
For citation analysis, we developed eight datasets comprising citation sentences, which are manually annotated by us into three sentiment polarities viz.
CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System
We present a feature aggregation architecture called Composite Appearance Network (CAN) to address the above problem.
On Optimality Conditions for Auto-Encoder Signal Recovery
Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost.
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
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.
Maximum Entropy Binary Encoding for Face Template Protection
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.
Deep Secure Encoding: An Application to Face Recognition
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.
Why Regularized Auto-Encoders learn Sparse Representation?
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.
Dimensionality Reduction with Subspace Structure Preservation
Modeling data as being sampled from a union of independent subspaces has been widely applied to a number of real world applications.
Parallel Feature Selection Inspired by Group Testing
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.
Is Joint Training Better for Deep Auto-Encoders?
But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers.
An Analysis of Random Projections in Cancelable Biometrics
With increasing concerns about security, the need for highly secure physical biometrics-based authentication systems utilizing \emph{cancelable biometric} technologies is on the rise.
