Iason-Ioannis Panagos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Iason-Ioannis Panagos has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Angelos P. Giotis
Department of Computer Science and Engineering, University of Ioannina, 45110 Ioannina, Greece
3 shared publications - Christophoros Nikou
Department of Computer Science and Engineering (CSE), University of Ioannina, 45110 Ioannina, Greece
3 shared publications - Giorgos Sfikas
University of West Attica
2 shared publications Christophoros Nikou
1 shared publication- Christophoros Nikou
University of Ioannina
1 shared publication - George Gartzonikas
Department of Computer Science and Engineering, University of Ioannina, 45110 Ioannina, Greece
1 shared publication
Latest Publications
- Open Access
- 14 July 2026
- Published by MDPI AG in Electronics
- Vol. 15 (14) , 3089
Demographic-Aware Multi-Object Tracking for Retail Environments via Temporal Consistency and Joint Association
Reliable identity preservation is essential in retail multi-object tracking because an identity switch may assign dwell time, shelf interactions, or demographic statistics to the wrong consumer trajectory. This challenge is amplified in crowded indoor scenes, where occlusions and appearance ambiguity weaken conventional association cues. This work presents a demographic-aware multi-object tracking framework for retail environments that exploits spatial, motion-based, appearance-based, and demographic cues within a modular tracking-by-detection pipeline. The proposed approach integrates IoU-based spatial association, LSTM-based motion forecasting, ReID appearance embeddings, and apparent demographic information derived from age-group and gender predictions into a common association cost. The core assumption is that demographic attributes should remain consistent across neighboring frames for the same tracked individual; therefore, demographic agreement can serve as a weak semantic cue during detection-to-tracklet association. Unlike conventional pipelines that treat multi-object tracking and demographic estimation as independent stages, the proposed method reuses the outputs of an existing Inception-based apparent demographic classifier to support identity preservation, without introducing a new demographic estimation model or requiring end-to-end retraining. The framework is evaluated on RGB retail tracking sequences from the Consumers dataset under both raw and privacy-aware anonymized settings. The proposed method achieves 84.8% MOTA and 87.8% IDF1 on raw data and 80.0% MOTA and 85.3% IDF1 under anonymization, improving the strongest evaluated baseline by 0.4 and 0.6 percentage points and by 1.0 and 1.3 percentage points, respectively, while preserving the same low ID-switch counts. Although incremental in absolute terms, these gains are consistent across both evaluation settings and are obtained over a strong baseline in challenging indoor retail sequences. The results indicate that even a lightweight demographic-consistency cue can provide measurable complementary information for improving consumer trajectory stability.
- 14 July 2026
- Published by MDPI AG in Electronics
- Vol. 15 (14) , 3089
Open AccessDemographic-Aware Multi-Object Tracking for Retail Environments via Temporal Consistency and Joint Association
Reliable identity preservation is essential in retail multi-object tracking because an identity switch may assign dwell time, shelf interactions, or demographic statistics to the wrong consumer trajectory. This challenge is amplified in crowded indoor scenes, where occlusions and appearance ambiguity weaken conventional association cues. This work presents a demographic-aware multi-object tracking framework for retail environments that exploits spatial, motion-based, appearance-based, and demographic cues within a modular tracking-by-detection pipeline. The proposed approach integrates IoU-based spatial association, LSTM-based motion forecasting, ReID appearance embeddings, and apparent demographic information derived from age-group and gender predictions into a common association cost. The core assumption is that demographic attributes should remain consistent across neighboring frames for the same tracked individual; therefore, demographic agreement can serve as a weak semantic cue during detection-to-tracklet association. Unlike conventional pipelines that treat multi-object tracking and demographic estimation as independent stages, the proposed method reuses the outputs of an existing Inception-based apparent demographic classifier to support identity preservation, without introducing a new demographic estimation model or requiring end-to-end retraining. The framework is evaluated on RGB retail tracking sequences from the Consumers dataset under both raw and privacy-aware anonymized settings. The proposed method achieves 84.8% MOTA and 87.8% IDF1 on raw data and 80.0% MOTA and 85.3% IDF1 under anonymization, improving the strongest evaluated baseline by 0.4 and 0.6 percentage points and by 1.0 and 1.3 percentage points, respectively, while preserving the same low ID-switch counts. Although incremental in absolute terms, these gains are consistent across both evaluation settings and are obtained over a strong baseline in challenging indoor retail sequences. The results indicate that even a lightweight demographic-consistency cue can provide measurable complementary information for improving consumer trajectory stability.
- 14 July 2026
- Published by Springer Nature
- p. 179-192
Energy Data Sharing Through Data Spaces with DATAMITE: Supporting Digital Transformation
- 14 July 2026
- Published by Springer Nature
- p. 179-192
Energy Data Sharing Through Data Spaces with DATAMITE: Supporting Digital Transformation
- Open Access
Designing Practical Models for Isolated Word Visual Speech Recognition
Visual speech recognition (VSR) systems decode spoken words from an input sequence using only the video data. Practical applications of such systems include medical assistance as well as human-machine interactions. A VSR system is typically employed in a complementary role in cases where the audio is corrupt or not available. In order to accurately predict the spoken words, these architectures often rely on deep neural networks in order to extract meaningful representations from the input sequence. While deep architectures achieve impressive recognition performance, relying on such models incurs significant computation costs which translates into increased resource demands in terms of hardware requirements and results in limited applicability in real-world scenarios where resources might be constrained. This factor prevents wider adoption and deployment of speech recognition systems in more practical applications. In this work, we aim to alleviate this issue by developing architectures for VSR that have low hardware costs. Following the standard two-network design paradigm, where one network handles visual feature extraction and another one utilizes the extracted features to classify the entire sequence, we develop lightweight end-to-end architectures by first benchmarking efficient models from the image classification literature, and then adopting lightweight block designs in a temporal convolution network backbone. We create several unified models with low resource requirements but strong recognition performance. Experiments on the largest public database for English words demonstrate the effectiveness and practicality of our developed models. Code and trained models will be made publicly available.
Open AccessDesigning Practical Models for Isolated Word Visual Speech Recognition
Visual speech recognition (VSR) systems decode spoken words from an input sequence using only the video data. Practical applications of such systems include medical assistance as well as human-machine interactions. A VSR system is typically employed in a complementary role in cases where the audio is corrupt or not available. In order to accurately predict the spoken words, these architectures often rely on deep neural networks in order to extract meaningful representations from the input sequence. While deep architectures achieve impressive recognition performance, relying on such models incurs significant computation costs which translates into increased resource demands in terms of hardware requirements and results in limited applicability in real-world scenarios where resources might be constrained. This factor prevents wider adoption and deployment of speech recognition systems in more practical applications. In this work, we aim to alleviate this issue by developing architectures for VSR that have low hardware costs. Following the standard two-network design paradigm, where one network handles visual feature extraction and another one utilizes the extracted features to classify the entire sequence, we develop lightweight end-to-end architectures by first benchmarking efficient models from the image classification literature, and then adopting lightweight block designs in a temporal convolution network backbone. We create several unified models with low resource requirements but strong recognition performance. Experiments on the largest public database for English words demonstrate the effectiveness and practicality of our developed models. Code and trained models will be made publicly available.
- 3 September 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 186, 1-7
Visual speech recognition using compact hypercomplex neural networks
- 3 September 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 186, 1-7
Visual speech recognition using compact hypercomplex neural networks
- Open Access
A New Benchmark for Consumer Visual Tracking and Apparent Demographic Estimation from RGB and Thermal Images
Visual tracking and attribute estimation related to age or gender information of multiple person entities in a scene are mature research topics with the advent of deep learning techniques. However, when it comes to indoor images such as video sequences of retail consumers, data are not always adequate or accurate enough to essentially train effective models for consumer detection and tracking under various adverse factors. This in turn affects the quality of recognizing age or gender for those detected instances. In this work, we introduce two novel datasets: Consumers comprises 145 video sequences compliant to personal information regulations as far as facial images are concerned and BID is a set of cropped body images from each sequence that can be used for numerous computer vision tasks. We also propose an end-to-end framework which comprises CNNs as object detectors, LSTMs for motion forecasting of the tracklet association component in a sequence, along with a multi-attribute classification model for apparent demographic estimation of the detected outputs, aiming to capture useful metadata of consumer product preferences. Obtained results on tracking and age/gender prediction are promising with respect to reference systems while they indicate the proposed model’s potential for practical consumer metadata extraction.
Open AccessA New Benchmark for Consumer Visual Tracking and Apparent Demographic Estimation from RGB and Thermal Images
Visual tracking and attribute estimation related to age or gender information of multiple person entities in a scene are mature research topics with the advent of deep learning techniques. However, when it comes to indoor images such as video sequences of retail consumers, data are not always adequate or accurate enough to essentially train effective models for consumer detection and tracking under various adverse factors. This in turn affects the quality of recognizing age or gender for those detected instances. In this work, we introduce two novel datasets: Consumers comprises 145 video sequences compliant to personal information regulations as far as facial images are concerned and BID is a set of cropped body images from each sequence that can be used for numerous computer vision tasks. We also propose an end-to-end framework which comprises CNNs as object detectors, LSTMs for motion forecasting of the tracklet association component in a sequence, along with a multi-attribute classification model for apparent demographic estimation of the detected outputs, aiming to capture useful metadata of consumer product preferences. Obtained results on tracking and age/gender prediction are promising with respect to reference systems while they indicate the proposed model’s potential for practical consumer metadata extraction.
- Open Access
- 24 August 2022
- Published by MDPI AG in Engineering Proceedings
- Vol. 21 (1) , 17
Tracking Multiple Instances of Retail Consumers from RGB and Thermal Images
Visual tracking of multiple objects is a challenging task that has gained considerable attention recently. The process involves several steps: detection, data association, and re-identification, each with its own set of challenges. Trending methods usually combine some of these steps and report impressive results in tracking benchmarks while running at practical speeds. In this work, we develop an online, real-time multi-object tracking approach that is also able to perform consumer tracking in indoor retail stores, without further tuning its design philosophy. Our model can utilize multi-modal inputs, such as RGB and thermal images when available, to improve its performance while maintaining acceptable speeds at 20FPS. Our key contribution to motion forecasting replaces the standard Kalman filters with an LSTM network to properly model long-term dependencies and target tracking. Numerical experiments of our method on the widely used MOT16 benchmark demonstrate its effectiveness. Additionally, qualitative results in in-house retail image data confirm the method’s capacity for practical multi-consumer tracking. Our proposed system is part of a research project aiming to capture retail consumers’ preferences, as a function of their relative position with respect to particular areas of a store that have been mapped according to the shelves, which are visible for each view area of the installed RGB and thermal cameras. Additionally, the system relies on accurate estimation of consumer age and gender using only body images in a multi-task deep learning framework in order to further taxonomize consumer preferences into age and gender groups. By these means, useful consumer meta-data can be extracted, ready to be employed for marketing campaign customization, which might improve sales and the consumer experience altogether.
- 24 August 2022
- Published by MDPI AG in Engineering Proceedings
- Vol. 21 (1) , 17
Open AccessTracking Multiple Instances of Retail Consumers from RGB and Thermal Images
Visual tracking of multiple objects is a challenging task that has gained considerable attention recently. The process involves several steps: detection, data association, and re-identification, each with its own set of challenges. Trending methods usually combine some of these steps and report impressive results in tracking benchmarks while running at practical speeds. In this work, we develop an online, real-time multi-object tracking approach that is also able to perform consumer tracking in indoor retail stores, without further tuning its design philosophy. Our model can utilize multi-modal inputs, such as RGB and thermal images when available, to improve its performance while maintaining acceptable speeds at 20FPS. Our key contribution to motion forecasting replaces the standard Kalman filters with an LSTM network to properly model long-term dependencies and target tracking. Numerical experiments of our method on the widely used MOT16 benchmark demonstrate its effectiveness. Additionally, qualitative results in in-house retail image data confirm the method’s capacity for practical multi-consumer tracking. Our proposed system is part of a research project aiming to capture retail consumers’ preferences, as a function of their relative position with respect to particular areas of a store that have been mapped according to the shelves, which are visible for each view area of the installed RGB and thermal cameras. Additionally, the system relies on accurate estimation of consumer age and gender using only body images in a multi-task deep learning framework in order to further taxonomize consumer preferences into age and gender groups. By these means, useful consumer meta-data can be extracted, ready to be employed for marketing campaign customization, which might improve sales and the consumer experience altogether.