58 citations · 200 across the 25 of their papers we have counts for
28 papers
Moving Object Based Collision-Free Video Synopsis
Anton Jeran Ratnarajah, Sahani Goonetilleke, Dumindu Tissera +2
Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving. Existing trajector…
3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation
Amaya Dharmasiri, Dinithi Dissanayake, Mohamed Afham +3
3D generative models have been recently successful in generating realistic 3D objects in the form of point clouds. However, most models do not offer controllability to manipulate t…
Visual-Semantic Contrastive Alignment for Few-Shot Image Classification
Mohamed Afham, Ranga Rodrigo
Few-Shot learning aims to train and optimize a model that can adapt to unseen visual classes with only a few labeled examples. The existing few-shot learning (FSL) methods, heavily…
Realistic, Animatable Human Reconstructions for Virtual Fit-On
Gayal Kuruppu, Bumuthu Dilshan, Shehan Samarasinghe +2
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. Our main idea is to cons…
Vision Transformer with Convolutional Encoder-Decoder for Hand Gesture Recognition using 24 GHz Doppler Radar
Kavinda Kehelella, Gayangana Leelarathne, Dhanuka Marasinghe +5
Transformers combined with convolutional encoders have been recently used for hand gesture recognition (HGR) using micro-Doppler signatures. We propose a vision-transformer-based a…
DualCam: A Novel Benchmark Dataset for Fine-grained Real-time Traffic Light Detection
Harindu Jayarathne, Tharindu Samarakoon, Hasara Koralege +3
Traffic light detection is essential for self-driving cars to navigate safely in urban areas. Publicly available traffic light datasets are inadequate for the development of algori…
Class-Aware Attention for Multimodal Trajectory Prediction
Bimsara Pathiraja, Shehan Munasinghe, Malshan Ranawella +3
Predicting the possible future trajectories of the surrounding dynamic agents is an essential requirement in autonomous driving. These trajectories mainly depend on the surrounding…
Dynamic Template Initialization for Part-Aware Person Re-ID
Kalana Abeywardena, Shechem Sumanthiran, Sanoojan Baliah +5
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 rep…
HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing
Arulmolivarman Thieshanthan, Amashi Niwarthana, Pamuditha Somarathne +2
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 l…
Towards Real-time Traffic Sign and Traffic Light Detection on Embedded Systems
Oshada Jayasinghe, Sahan Hemachandra, Damith Anhettigama +5
Recent work done on traffic sign and traffic light detection focus on improving detection accuracy in complex scenarios, yet many fail to deliver real-time performance, specificall…
CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
Mohamed Afham, Isuru Dissanayake, Dinithi Dissanayake +3
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 struct…
PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing
Dishanika Denipitiyage, Vinoj Jayasundara, Ranga Rodrigo +1
Raw point cloud processing using capsule networks is widely adopted in classification, reconstruction, and segmentation due to its ability to preserve spatial agreement of the inpu…
KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization
Kalana Abeywardena, Shechem Sumanthiran, Sakuna Jayasundara +3
Real-time and online action localization in a video is a critical yet highly challenging problem. Accurate action localization requires the utilization of both temporal and spatial…
SwiftLane: Towards Fast and Efficient Lane Detection
Oshada Jayasinghe, Damith Anhettigama, Sahan Hemachandra +3
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 computati…
CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking Detection
Oshada Jayasinghe, Sahan Hemachandra, Damith Anhettigama +3
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 o…
Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering
Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe +4
Any clustering algorithm must synchronously learn to model the clusters and allocate data to those clusters in the absence of labels. Mixture model-based methods model clusters wit…
End-To-End Data-Dependent Routing in Multi-Path Neural Networks
Dumindu Tissera, Rukshan Wijessinghe, Kasun Vithanage +3
Neural networks are known to give better performance with increased depth due to their ability to learn more abstract features. Although the deepening of networks has been well est…
Diverse Single Image Generation with Controllable Global Structure
Sutharsan Mahendren, Chamira Edussooriya, Ranga Rodrigo
Image generation from a single image using generative adversarial networks is quite interesting due to the realism of generated images. However, recent approaches need improvement…
DEVI: Open-source Human-Robot Interface for Interactive Receptionist Systems
Ramesha Karunasena, Piumi Sandarenu, Madushi Pinto +3
Humanoid robots that act as human-robot interfaces equipped with social skills can assist people in many of their daily activities. Receptionist robots are one such application whe…
Fast and Accurate Light Field Saliency Detection through Deep Encoding
Sahan Hemachandra, Ranga Rodrigo, Chamira Edussooriya
Light field saliency detection -- important due to utility in many vision tasks -- still lacks speed and can improve in accuracy. Due to the formulation of the saliency detection p…
Feature-Dependent Cross-Connections in Multi-Path Neural Networks
Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe +3
Learning a particular task from a dataset, samples in which originate from diverse contexts, is challenging, and usually addressed by deepening or widening standard neural networks…
TimeCaps: Capturing Time Series Data With Capsule Networks
Hirunima Jayasekara, Vinoj Jayasundara, Mohamed Athif +4
Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with Time…
Context-Aware Multipath Networks
Dumindu Tissera, Kumara Kahatapitiya, Rukshan Wijesinghe +2
Making a single network effectively address diverse contexts---learning the variations within a dataset or multiple datasets---is an intriguing step towards achieving generalized i…
Exploiting the Redundancy in Convolutional Filters for Parameter Reduction
Kumara Kahatapitiya, Ranga Rodrigo
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years. However, this comes at the cost of heavy computation a…