Search Results for author:
Found 31 papers, 12 papers with code
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds.
3D Object Classification
3D Point Cloud Linear Classification
+3
DeepCaps: Going Deeper with Capsule Networks
Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data.
TextCaps : Handwritten Character Recognition with Very Small Datasets
Our system is useful in character recognition for localized languages that lack much labeled training data and even in other related more general contexts such as object recognition.
Ranked #4 on
Image Classification
on EMNIST-Letters
CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking Detection
In this paper, we introduce a novel road marking benchmark dataset for road marking detection, addressing the limitations in the existing publicly available datasets such as lack of challenging scenarios, prominence given to lane markings, unavailability of an evaluation script, lack of annotation formats and lower resolutions.
DualCam: A Novel Benchmark Dataset for Fine-grained Real-time Traffic Light Detection
We introduce a novel benchmark traffic light dataset captured using a synchronized pair of narrow-angle and wide-angle cameras covering urban and semi-urban roads.
Towards Real-time Traffic Sign and Traffic Light Detection on Embedded Systems
In this work, we propose a simple deep learning based end-to-end detection framework, which effectively tackles challenges inherent to traffic sign and traffic light detection such as small size, large number of classes and complex road scenarios.
Exploiting the Redundancy in Convolutional Filters for Parameter Reduction
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years.
KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
Despite the simplicity of our approach, our lightweight end-to-end architecture achieves state-of-the-art frame-mAP of 74. 7% on the challenging UCF101-24 dataset, demonstrating a performance gain of 6. 4% over the previous best online methods.
Optical Flow Estimation
Spatio-Temporal Action Localization
+1
TimeCaps: Capturing Time Series Data With Capsule Networks
Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks.
3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation
However, most models do not offer controllability to manipulate the shape semantics of component object parts without extensive semantic attribute labels or other reference point clouds.
Context-Aware Automatic Occlusion Removal
Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal.
Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos
We propose three schemas for combining static and motion components: based on a variance ratio, principal components, and Cholesky decomposition.
Context-Aware Multipath Networks
In view of this, networks which can allocate resources according to the context of the input and regulate flow of information across the network are effective.
Ranked #2 on
Image Classification
on Kuzushiji-MNIST
Feature-Dependent Cross-Connections in Multi-Path Neural Networks
As opposed to conventional network widening, multi-path architectures restrict the quadratic increment of complexity to a linear scale.
Fast and Accurate Light Field Saliency Detection through Deep Encoding
Light field saliency detection -- important due to utility in many vision tasks -- still lacks speed and can improve in accuracy.
DEVI: Open-source Human-Robot Interface for Interactive Receptionist Systems
Humanoid robots that act as human-robot interfaces equipped with social skills can assist people in many of their daily activities.
Diverse Single Image Generation with Controllable Global Structure
Image generation from a single image using generative adversarial networks is quite interesting due to the realism of generated images.
Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering
The network parameters pose as the parameters of those distributions.
End-To-End Data-Dependent Routing in Multi-Path Neural Networks
Having multiple parallel convolutional/dense operations in each layer solves this problem, but without any context-dependent allocation of resources among these operations: the parallel computations tend to learn similar features making the widening process less effective.
SwiftLane: Towards Fast and Efficient Lane Detection
Recent work done on lane detection has been able to detect lanes accurately in complex scenarios, yet many fail to deliver real-time performance specifically with limited computational resources.
Ranked #43 on
Lane Detection
on CULane
HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing
Inspired by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing and feature learning over large-scale outdoor LiDAR point clouds.
PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing
We address these limitations in existing capsule network based approaches by proposing PointCaps, a novel convolutional capsule architecture with parameter sharing.
Dynamic Template Initialization for Part-Aware Person Re-ID
Many of the existing Person Re-identification (Re-ID) approaches depend on feature maps which are either partitioned to localize parts of a person or reduced to create a global representation.
Class-Aware Attention for Multimodal Trajectory Prediction
These trajectories mainly depend on the surrounding static environment, as well as the past movements of those dynamic agents.
Vision Transformer with Convolutional Encoder-Decoder for Hand Gesture Recognition using 24 GHz Doppler Radar
Transformers combined with convolutional encoders have been recently used for hand gesture recognition (HGR) using micro-Doppler signatures.
Realistic, Animatable Human Reconstructions for Virtual Fit-On
We present an end-to-end virtual try-on pipeline, that can fit different clothes on a personalized 3-D human model, reconstructed using a single RGB image.
Visual-Semantic Contrastive Alignment for Few-Shot Image Classification
The pre-trained semantic feature extractor (learned from a large-scale text corpora) we use in our approach provides a strong contextual prior knowledge to assist FSL.
Contrastive Deep Encoding Enables Uncertainty-aware Machine-learning-assisted Histopathology
We show that our approach can reach the state-of-the-art (SOTA) for patch-level classification with only 1-10% randomly selected annotations compared to other SOTA approaches.
SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning
The inherent ability of GWR to form distinct clusters, each corresponding to a class in the feature vector space, regardless of the order of samples or class imbalances, is well suited to achieving GCIL.
Moving Object Based Collision-Free Video Synopsis
Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving.
Forensic Video Analytic Software
This project has resulted in three research outcomes Moving Object Based Collision Free Video Synopsis, Forensic and Surveillance Analytic Tool Architecture and Tampering Detection Inter-Frame Forgery.
