Zainy M. Malakan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zainy M. Malakan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Ajmal Mian
The University of Western Australia
5 shared publications - Ghulam Mubashar Hassan
Computer Science and Software Engineering, The University of Western Australia, Perth, Australia
3 shared publications - Abdullah M. Algamdi
Department of Computer Science and Artificial Intelligence, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
1 shared publication Ghulam Mubashar Hassan
The University of Western Australia 6009 Perth WA Australia
1 shared publication- Haitian Wang
Western Australia Machine Intelligence Group Pty Ltd, Nedlands, Western Australia, Australia, Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, Western Australia, Australia, and School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, Western Australia, Australia
1 shared publication - Hezam Albaqami
Department of Computer Science and Artificial Intelligence, College of Computer Science and Engineering, University of Jeddah, Jeddah 21493, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 14155-14170
LiDAR, GNSS, and IMU Sensor Fine Alignment Through Dynamic Time Warping to Construct 3-D City Maps
(LiDAR)-based 3-D mapping suffers from cumulative drift causing global misalignment, particularly in global navigation satellite system (GNSS)-constrained environments. To address this, we propose a unified framework that fuses LiDAR, GNSS, and inertial measurement unit (IMU) data for high-resolution city-scale mapping. The method performs velocity-based temporal alignment using dynamic time warping and refines GNSS and IMU signals via extended Kalman filtering. Local maps are built using normal distributions transform-based registration and pose graph optimization with loop closure detection, while global consistency is enforced using GNSS-constrained anchors followed by fine registration of overlapping segments. We also introduce a large-scale multimodal dataset captured in Perth, Western Australia to facilitate future research in this direction. Our dataset comprises 144 000 frames acquired with a 128-channel Ouster LiDAR, synchronized RTK–GNSS trajectories, and MEMS–IMU measurements across 21 urban loops. To assess geometric consistency, we evaluated our method using alignment metrics based on road centerlines and intersections to capture both global and local accuracy. The proposed framework reduces the average global alignment error from 3.32 to 1.24 m, achieving a 61.4% improvement, and significantly decreases the intersection centroid offset from 13.22 to 2.01 m, corresponding to an 84.8% enhancement. The constructed high-fidelity map and raw dataset are publicly available through IEEE Dataport and its visualization can be viewed in the provided Demo. This dataset and method together establish a new benchmark for evaluating 3D city mapping in GNSS-constrained environments, with source code available at GitHub Repository.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 14155-14170
Open AccessLiDAR, GNSS, and IMU Sensor Fine Alignment Through Dynamic Time Warping to Construct 3-D City Maps
(LiDAR)-based 3-D mapping suffers from cumulative drift causing global misalignment, particularly in global navigation satellite system (GNSS)-constrained environments. To address this, we propose a unified framework that fuses LiDAR, GNSS, and inertial measurement unit (IMU) data for high-resolution city-scale mapping. The method performs velocity-based temporal alignment using dynamic time warping and refines GNSS and IMU signals via extended Kalman filtering. Local maps are built using normal distributions transform-based registration and pose graph optimization with loop closure detection, while global consistency is enforced using GNSS-constrained anchors followed by fine registration of overlapping segments. We also introduce a large-scale multimodal dataset captured in Perth, Western Australia to facilitate future research in this direction. Our dataset comprises 144 000 frames acquired with a 128-channel Ouster LiDAR, synchronized RTK–GNSS trajectories, and MEMS–IMU measurements across 21 urban loops. To assess geometric consistency, we evaluated our method using alignment metrics based on road centerlines and intersections to capture both global and local accuracy. The proposed framework reduces the average global alignment error from 3.32 to 1.24 m, achieving a 61.4% improvement, and significantly decreases the intersection centroid offset from 13.22 to 2.01 m, corresponding to an 84.8% enhancement. The constructed high-fidelity map and raw dataset are publicly available through IEEE Dataport and its visualization can be viewed in the provided Demo. This dataset and method together establish a new benchmark for evaluating 3D city mapping in GNSS-constrained environments, with source code available at GitHub Repository.
- Open Access
Vision Transformer Based Model for Describing a Set of Images as a Story
Visual Story-Telling is the process of forming a multi-sentence story from a set of images. Appropriately including visual variation and contextual information captured inside the input images is one of the most challenging aspects of visual storytelling. Consequently, stories developed from a set of images often lack cohesiveness, relevance, and semantic relationship. In this paper, we propose a novel Vision Transformer Based Model for describing a set of images as a story. The proposed method extracts the distinct features of the input images using a Vision Transformer (ViT). Firstly, input images are divided into 16X16 patches and bundled into a linear projection of flattened patches. The transformation from a single image to multiple image patches captures the visual variety of the input visual patterns. These features are used as input to a Bidirectional-LSTM which is part of the sequence encoder. This captures the past and future image context of all image patches. Then, an attention mechanism is implemented and used to increase the discriminatory capacity of the data fed into the language model, i.e. a Mogrifier-LSTM. The performance of our proposed model is evaluated using the Visual Story-Telling dataset (VIST), and the results show that our model outperforms the current state of the art models.
Open AccessVision Transformer Based Model for Describing a Set of Images as a Story
Visual Story-Telling is the process of forming a multi-sentence story from a set of images. Appropriately including visual variation and contextual information captured inside the input images is one of the most challenging aspects of visual storytelling. Consequently, stories developed from a set of images often lack cohesiveness, relevance, and semantic relationship. In this paper, we propose a novel Vision Transformer Based Model for describing a set of images as a story. The proposed method extracts the distinct features of the input images using a Vision Transformer (ViT). Firstly, input images are divided into 16X16 patches and bundled into a linear projection of flattened patches. The transformation from a single image to multiple image patches captures the visual variety of the input visual patterns. These features are used as input to a Bidirectional-LSTM which is part of the sequence encoder. This captures the past and future image context of all image patches. Then, an attention mechanism is implemented and used to increase the discriminatory capacity of the data fed into the language model, i.e. a Mogrifier-LSTM. The performance of our proposed model is evaluated using the Visual Story-Telling dataset (VIST), and the results show that our model outperforms the current state of the art models.
- Open Access
- 10 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 70805-70818
Sequential Vision to Language as Story: A Storytelling Dataset and Benchmarking
Storytelling is a remarkable human skill that plays a significant role in learning and experiencing everyday life. Developing narratives is central to human mental health development, simultaneously encapsulating broad details such as psychology, morality and common sense. Contemporary deep-learning algorithms require similar skills to be able to tell a story from a visual perspective. However, most algorithms function at a superficial or factual level, aligning descriptive text with images in a one-to-one manner without considering the temporal relation. Stories are more expressive in style, language and content, involving imaginary concepts not explicit in the images. An ideal deep learning system should learn and develop cohesive, meaningful, and causal stories. Unfortunately, most existing storytelling methods are trained and evaluated on a single dataset, i.e., the VIsual STorytelling (VIST) dataset. Multiple datasets are essential to test the generalization ability of algorithms. We bridge the gap and present a new dataset for expressive and coherent story creation. We present the Sequential Storytelling Image Dataset (SSID), consisting of open-source video frames accompanied by story-like annotations. We provide four annotations (stories) for each set of five images. The image sets are collected manually from publicly available videos in three domains: documentaries, lifestyle, and movies, and then annotated manually using Amazon Mechanical Turk. We perform a detailed analysis and benchmarking of the current VIST dataset and our new SSID dataset and show that both datasets exhibit high variance within their multiple ground truth stories corresponding to the same image set. Moreover, our dataset achieves lower mean average scores across all metrics, meaning that the ground truth stories of our dataset are more diverse. Finally, we train and evaluate existing state-of-the-art rhetorical storytelling methods on both datasets and show that our dataset is more challenging and requires sophisticated techniques to accurately detect a significant variety of events.
- 10 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 70805-70818
Open AccessSequential Vision to Language as Story: A Storytelling Dataset and Benchmarking
Storytelling is a remarkable human skill that plays a significant role in learning and experiencing everyday life. Developing narratives is central to human mental health development, simultaneously encapsulating broad details such as psychology, morality and common sense. Contemporary deep-learning algorithms require similar skills to be able to tell a story from a visual perspective. However, most algorithms function at a superficial or factual level, aligning descriptive text with images in a one-to-one manner without considering the temporal relation. Stories are more expressive in style, language and content, involving imaginary concepts not explicit in the images. An ideal deep learning system should learn and develop cohesive, meaningful, and causal stories. Unfortunately, most existing storytelling methods are trained and evaluated on a single dataset, i.e., the VIsual STorytelling (VIST) dataset. Multiple datasets are essential to test the generalization ability of algorithms. We bridge the gap and present a new dataset for expressive and coherent story creation. We present the Sequential Storytelling Image Dataset (SSID), consisting of open-source video frames accompanied by story-like annotations. We provide four annotations (stories) for each set of five images. The image sets are collected manually from publicly available videos in three domains: documentaries, lifestyle, and movies, and then annotated manually using Amazon Mechanical Turk. We perform a detailed analysis and benchmarking of the current VIST dataset and our new SSID dataset and show that both datasets exhibit high variance within their multiple ground truth stories corresponding to the same image set. Moreover, our dataset achieves lower mean average scores across all metrics, meaning that the ground truth stories of our dataset are more diverse. Finally, we train and evaluate existing state-of-the-art rhetorical storytelling methods on both datasets and show that our dataset is more challenging and requires sophisticated techniques to accurately detect a significant variety of events.
- 3 December 2022
- Published by Springer Nature
- p. 15-28
Vision Transformer Based Model for Describing a Set of Images as a Story
- 3 December 2022
- Published by Springer Nature
- p. 15-28
Vision Transformer Based Model for Describing a Set of Images as a Story
- Open Access
- 1 January 2021
- Published by INSTICC
- p. 196-205
Contextualise, Attend, Modulate and Tell: Visual Storytelling
- 1 January 2021
- Published by INSTICC
- p. 196-205
Open AccessContextualise, Attend, Modulate and Tell: Visual Storytelling