no code implementations • 17 Sep 2023 • Anton Jeran Ratnarajah, Sahani Goonetilleke, Dumindu Tissera, Kapilan Balagopalan, Ranga Rodrigo
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.
no code implementations • 17 Sep 2023 • Anton Jeran Ratnarajah, Sahani Goonetilleke, Dumindu Tissera, Kapilan Balagopalan, Ranga Rodrigo
Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving.
no code implementations • 13 Sep 2023 • Nirhoshan Sivaroopan, Chamuditha Jayanga, Chalani Ekanayake, Hasindri Watawana, Jathurshan Pradeepkumar, Mithunjha Anandakumar, Ranga Rodrigo, Chamira U. S. Edussooriya, Dushan N. Wadduwage
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.
no code implementations • 13 Aug 2023 • Sathursan Kanagarajah, Thanuja Ambegoda, Ranga Rodrigo
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.
1 code implementation • 17 Nov 2022 • Amaya Dharmasiri, Dinithi Dissanayake, Mohamed Afham, Isuru Dissanayake, Ranga Rodrigo, Kanchana Thilakarathna
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.
no code implementations • 20 Oct 2022 • Mohamed Afham, Ranga Rodrigo
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.
no code implementations • 16 Oct 2022 • Gayal Kuruppu, Bumuthu Dilshan, Shehan Samarasinghe, Nipuna Madhushan, Ranga Rodrigo
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.
no code implementations • 12 Sep 2022 • Kavinda Kehelella, Gayangana Leelarathne, Dhanuka Marasinghe, Nisal Kariyawasam, Viduneth Ariyarathna, Arjuna Madanayake, Ranga Rodrigo, Chamira U. S. Edussooriya
Transformers combined with convolutional encoders have been recently used for hand gesture recognition (HGR) using micro-Doppler signatures.
1 code implementation • 3 Sep 2022 • Harindu Jayarathne, Tharindu Samarakoon, Hasara Koralege, Asitha Divisekara, Ranga Rodrigo, Peshala Jayasekara
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.
no code implementations • 31 Aug 2022 • Bimsara Pathiraja, Shehan Munasinghe, Malshan Ranawella, Maleesha De Silva, Ranga Rodrigo, Peshala Jayasekara
These trajectories mainly depend on the surrounding static environment, as well as the past movements of those dynamic agents.
no code implementations • 24 Aug 2022 • Kalana Abeywardena, Shechem Sumanthiran, Sanoojan Baliah, Nadarasar Bahavan, Nalith Udugampola, Ajith Pasqual, Chamira Edussooriya, Ranga Rodrigo
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.
no code implementations • 5 Jun 2022 • Arulmolivarman Thieshanthan, Amashi Niwarthana, Pamuditha Somarathne, Tharindu Wickremasinghe, Ranga Rodrigo
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.
1 code implementation • 5 May 2022 • Oshada Jayasinghe, Sahan Hemachandra, Damith Anhettigama, Shenali Kariyawasam, Tharindu Wickremasinghe, Chalani Ekanayake, Ranga Rodrigo, Peshala Jayasekara
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.
1 code implementation • CVPR 2022 • Mohamed Afham, Isuru Dissanayake, Dinithi Dissanayake, Amaya Dharmasiri, Kanchana Thilakarathna, Ranga Rodrigo
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
no code implementations • 21 Dec 2021 • Dishanika Denipitiyage, Vinoj Jayasundara, Ranga Rodrigo, Chamira U. S. Edussooriya
We address these limitations in existing capsule network based approaches by proposing PointCaps, a novel convolutional capsule architecture with parameter sharing.
1 code implementation • 5 Nov 2021 • Kalana Abeywardena, Shechem Sumanthiran, Sakuna Jayasundara, Sachira Karunasena, Ranga Rodrigo, Peshala Jayasekara
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
1 code implementation • 22 Oct 2021 • Oshada Jayasinghe, Sahan Hemachandra, Damith Anhettigama, Shenali Kariyawasam, Ranga Rodrigo, Peshala Jayasekara
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.
no code implementations • 22 Oct 2021 • Oshada Jayasinghe, Damith Anhettigama, Sahan Hemachandra, Shenali Kariyawasam, Ranga Rodrigo, Peshala Jayasekara
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
no code implementations • 6 Jul 2021 • Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Alex Xavier, Sanath Jayasena, Subha Fernando, Ranga Rodrigo
The network parameters pose as the parameters of those distributions.
no code implementations • 6 Jul 2021 • Dumindu Tissera, Rukshan Wijessinghe, Kasun Vithanage, Alex Xavier, Subha Fernando, Ranga Rodrigo
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.
no code implementations • 9 Feb 2021 • 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.
1 code implementation • 2 Jan 2021 • Ramesha Karunasena, Piumi Sandarenu, Madushi Pinto, Achala Athukorala, Ranga Rodrigo, Peshala Jayasekara
Humanoid robots that act as human-robot interfaces equipped with social skills can assist people in many of their daily activities.
no code implementations • 25 Oct 2020 • 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.
no code implementations • 24 Jun 2020 • Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Kumara Kahatapitiya, Subha Fernando, Ranga Rodrigo
As opposed to conventional network widening, multi-path architectures restrict the quadratic increment of complexity to a linear scale.
1 code implementation • 26 Nov 2019 • Hirunima Jayasekara, Vinoj Jayasundara, Mohamed Athif, Jathushan Rajasegaran, Sandaru Jayasekara, Suranga Seneviratne, Ranga Rodrigo
Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks.
no code implementations • 26 Jul 2019 • Dumindu Tissera, Kumara Kahatapitiya, Rukshan Wijesinghe, Subha Fernando, Ranga Rodrigo
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
1 code implementation • 26 Jul 2019 • Kumara Kahatapitiya, Ranga Rodrigo
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years.
1 code implementation • 7 May 2019 • Kumara Kahatapitiya, Dumindu Tissera, Ranga Rodrigo
Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal.
5 code implementations • CVPR 2019 • Jathushan Rajasegaran, Vinoj Jayasundara, Sandaru Jayasekara, Hirunima Jayasekara, Suranga Seneviratne, Ranga Rodrigo
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.
3 code implementations • 17 Apr 2019 • Vinoj Jayasundara, Sandaru Jayasekara, Hirunima Jayasekara, Jathushan Rajasegaran, Suranga Seneviratne, Ranga Rodrigo
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
no code implementations • 16 Oct 2018 • Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
We propose three schemas for combining static and motion components: based on a variance ratio, principal components, and Cholesky decomposition.