The adoption of facial recognition technology for identity verification has seen significant growth in recent years. While state-of-the-art (SOTA) facial recognition systems demonstrate high accuracy, the biometric features extracted and stored in system databases are inherently privacy-sensitive. If compromised, this data poses a serious threat to user privacy. To address this challenge, we propose a novel federated learning-based cancelable template protection framework that combines secure, user-specific transformations with collaborative training. In our approach, each user’s face features are first converted into a cancelable template, revocable representation, and then used to train a shared model through federated learning, which enables multiple clients to jointly update a global model without sharing their raw or transformed biometric data. We evaluate our method across key security properties, including unlinkability, revocability, and resilience to inversion attacks, in compliance with the ISO/IEC 30136 standard for biometric performance and protection. Experiments conducted on the large-scale CelebA and LFW dataset using modern facial recognition architectures demonstrate that our approach achieves competitive recognition performance while significantly enhancing security, while preserving recognition performance.

Human identification at a distance (HID) faces challenges due to the difficulty of acquiring traditional biometric modalities like face and fingerprints. Gait recognition offers a viable solution since it can be captured at a distance. To promote progress in gait recognition and provide a fair evaluation platform, the International Competition on Human Identification at a Distance (HID) has been organized annually since 2020. Since 2023, the competition has adopted the challenging SUSTech-Competition dataset, which includes significant variations in clothing, carried objects, and view angles. No training data is provided, requiring participants to train their models using external datasets. Each year, the competition applies a different random seed to generate distinct evaluation splits, reducing the risk of overfitting and ensuring fair evaluation of cross-domain generalization. Although the previous two competitions (HID 2023 and HID 2024) already utilized this dataset, HID 2025 aimed explicitly to explore whether algorithmic improvements could surpass the accuracy limits observed previously. Despite these heightened challenges, participants again demonstrated significant advancements, with the highest accuracy reaching 94.2%, setting a new benchmark for this dataset. We also analyze key technical trends and outline potential directions for future research on gait recognition.

Gait has emerged as a promising biometric modality due to its noninvasive nature and the ability to capture samples from a distance. Model-based gait recognition using skeleton data conveys rich information that remains invariant to carried objects and clothing variations. However, viewing a person from different angles alters their gait posture, resulting in increased intrasubject variability compared to intersubject variability. Therefore, we propose a novel framework, view-embedding modified residual graph convolutional network (VeMResGCN), for cross-view gait recognition (CVGR) by exploiting two modules: modified residual graph convolutional network (MResGCN) and view-embedding feature extraction (VeFE) for view-invariant features. A state-of-the-art pose estimation algorithm extracts skeleton key points from raw video input, from which multiple features (e.g., relative joint positions, motion velocities, and bone structures) are computed. The final feature vector for gait recognition is computed by consolidating the features from the MResGCN and VeFE modules. To the best of authors’ knowledge, this work is the first to extract view-invariant features in a unified graph convolutional network (GCN) for skeleton-based CVGR. We evaluate our proposed framework on two of the largest publicly available skeleton datasets, CASIA-B and OUMVLP-Pose, under challenging covariates of clothing variation and carried objects. Results demonstrate that VeMResGCN significantly outperforms state-of-the-art methods with average rank-1 accuracies of 90.3%, 80.7%, and 73.4% for normal, carried object, and clothing variations on CASIA-B, and 71.0% on OU-MVLP in terms of skeleton-based CVGR. These results demonstrate the ability of our proposed framework to maintain superior CVGR performance despite the presence of carried objects and clothing variations. The proposed framework holds strong implications for real-world biometric applications, including robust person reidentification and surveillance systems, where maintaining consistent recognition across varying views and covariates is crucial.

Human identification at a distance (HID) faces challenges due to the difficulty of acquiring traditional biometric modalities like face and fingerprints. Gait recognition offers a viable solution since it can be captured at a distance. To advance the algorithm development and provide fair evaluations, the International Competition on Human Identification at a Distance (HID) has been held annually since 2020, with HID 2024 marking the fifth edition. Despite increased difficulty, participants demonstrated remarkable capabilities, surpassing previous accuracy levels. This paper, co-authored by competition organizers and top participants, provides a comprehensive summary of HID 2024, including an overview of the competition, and insights into the methods employed by the top teams. Specifically, inspired by the achievements of the 5 competitions of HID, we also provide the insights for the future directions on gait recognition.

Human Identification at a Distance (HID) is an important research area due to its importance (especially in biometrics) and inherent challenges within this domain. To mitigate some of the constraints, we have introduced the HID challenge. This paper presents an overview of the 4th International Competition on Human Identification at a Distance (HID 2023), which serves as a benchmark for evaluating various methods in the field of human identification at a distance. We have introduced a new dataset, SUSTech-Competition, engulfing a cross-domain challenge. This dataset has 859 subjects, having various variations of clothing, carrying conditions, occlusions, and view angles. With a substantial participation of 254 registered teams, HID 2023 has attracted considerable attention and yielded highly encouraging results. Notably, the top-performing teams achieved significantly good accuracies. In this paper, we provide an introduction to the competition, encompassing the dataset, experimental settings, and competition organization, as well as an analysis of the results obtained by the top teams. Additionally, we delve into the methodologies employed by these leading teams. The progress demonstrated in this competition offers an optimistic outlook on the advancements in gait recognition, highlighting its potential for robust real applications.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that affects social communication and interaction. Early diagnosis of ASD can mitigate the severity and help with ideal treatment direction. Computer vision-based methods with traditional machine learning and deep learning are employed in the literature for automatic diagnosis. Recently, deep learning with a facial image-based ASD classification has gained interest due to its ease of collection and non-invasiveness. We observed that the existing approaches utilized either local or global features of facial images to diagnose ASD. However, its important to consider both local and global features to obtain fine-grained details and larger contextual information for accurate detection and classification. This paper proposes a sequencer-based patch-wise Local Feature Extractor along with a Global Feature Extractor. Finally, the features from these modules are aggregated to obtain the final feature for the classification of ASD. Experiments on a publicly available Autism Facial Image Dataset demonstrate that our proposed framework achieves state-of-the-art performance. We achieved accuracy, precision, recall, and F1-score of 94.7%, 94.0%, 95.3%, and 94.6%, respectively.

In this paper, we describe an uncertainty-aware estimation framework for gait relative attributes. We specifically design a two-stream network model that takes a pair of gait videos as input. It then outputs a corresponding pair of Gaussian distributions of gait absolute attribute scores and annotator-dependent gait relative attribute label distributions. Moreover, we propose a differentiable annotator-independent uncertainty layer to estimate the gait relative attribute score distribution from the absolute distributions then map it to a relative attribute label distribution using the computation of cumulative distribution functions. Furthermore, we propose another annotator-dependent uncertainty layer to estimate the uncertainty on the gait relative attribute labels in terms of a set of trainable transition matrices. Finally, we design a joint loss function on the relative attribute label distribution to learn the model parameters. Experiments on two gait relative attribute datasets demonstrated the effectiveness of the proposed method against baselines in quantitative and qualitative evaluations.

The paper provides a summary of the Competition on Human Identification at a Distance 2022 (HID 2022), which is the third one in a series of competitions. HID 2022 is for promoting the research in human identification at a distance by providing a benchmark to evaluate different methods. The competition attracted 112 valid registered teams. 71 teams and 51 teams submitted their results in the first phase and the second phase, respectively. Very encouraging results have been achieved, and the accuracies of the top teams are much higher than those achieved in the previous two competitions. In this paper, we introduce the competition including the dataset, experimental settings, competition organization, results from the top teams and their analysis. The methods used by the top teams are also presented in the paper. The progress of this competition can give us an optimistic view on gait recognition.

A set of advanced approaches and models on human action, activity, gesture, and behavior recognition related aspects along with associated challenges are summarized in this note. Notably, Video-based human activity recognition, sensor-based activity analysis, skeleton-based activity recognition, assisted daily living, anomaly detection, facial expression and emotion analysis, gesture and sign language are highlighted in the works. This special issue also introduced six new datasets, while exploring a total of 55 different datasets in its 21 research articles. Apart from the the areas covered in this issue, research on multi-modal analysis, action quality assessment, real-time applications, and activity and behavior computing on edge devices are some of the dominant future challenges to deal with. We firmly believe that the original works and ideas presented in this special issue will serve as helpful references for the relevant research communities in the journey towards a brighter future.

The Competition on Human Identification at a Distance 2021 (HID 2021) is to promote the research in human identification at a distance and to provide a benchmark to evaluate different methods. HID 2021 is the second follow-up from the first one, HID 2020. The dataset size and the evaluation protocal are the same with the previous competition, but the data in the test set has been changed. The paper firstly introduces the dataset and the evaluation protocol, then describes the methods from the top teams and their results. The methods show how to achieve state-of-the-art performance on gait recognition. The results in HID 2021 are better than those in HID 2020. From the comparisons and analysis, some useful conclusions can be drawn. We hope more improvements can be achieved by better followup competitions.

Action recognition is a very widely explored research area in computer vision and related fields. We propose Kinematics Posture Feature (KPF) extraction from 3D joint positions based on skeleton data for improving the performance of action recognition. In this approach, we consider the skeleton 3D joints as kinematics sensors. We propose Linear Joint Position Feature (LJPF) and Angular Joint Position Feature (AJPF) based on 3D linear joint positions and angles between bone segments. We then combine these two kinematics features for each video frame for each action to create the KPF feature sets. These feature sets encode the variation of motion in the temporal domain as if each body joint represents kinematics position and orientation sensors. In the next stage, we process the extracted KPF feature descriptor by using a low pass filter, and segment them by using sliding windows with optimized length. This concept resembles the approach of processing kinematics sensor data. From the segmented windows, we compute the Position-based Statistical Feature (PSF). These features consist of temporal domain statistical features (e.g., mean, standard deviation, variance, etc.). These statistical features encode the variation of postures (i.e., joint positions and angles) across the video frames. For performing classification, we explore Support Vector Machine (Linear), RNN, CNNRNN, and ConvRNN model. The proposed PSF feature sets demonstrate prominent performance in both statistical machine learning- and deep learning-based models. For evaluation, we explore five benchmark datasets namely UTKinect-Action3D, Kinect Activity Recognition Dataset (KARD), MSR 3D Action Pairs, Florence 3D, and Office Activity Dataset (OAD). To prevent overfitting, we consider the leave-one-subject-out framework as the experimental setup and perform 10-fold cross-validation. Our approach outperforms several existing methods in these benchmark datasets and achieves very promising classification performance.

Smartphone sensor-based activity recognition seeks broad, high-level knowledge about human behaviors from multitudes of low-level sensor readings, and makes considerable headway in healthcare domain. Our primary contribution is to study the effective pre-processing technique and the extraction of robust features for the classification of sensor data for human activity recognition (HAR). In the pre-processing stages, we investigated multiple filtering parameters for reducing waveform delay, smartphone orientation constraint by introducing magnitude and jerk-based features, and optimum window length for analyzing the trade-off between model performance and latency. Besides, we proposed a feature named "Average Height" that summarizes the average peak to trough distance of the activity and encodes any change of motion for classification. We also proposed two feature selection techniques for offline and real-time faster activity recognition, and analyzed the impact of different feature sets on classifying different activities. Moreover, after performing the classification with optimized hyperparameters, we proposed a Static Postural Transition-based Post-Processing (SPTPP) technique. This post-processing approach analyzes the existence of postural transition from previous window activity to current window activity, and helps to improve the model output by analyzing the posture change. The impact of our proposed techniques are demonstrated on three benchmark datasets named HASC, HAR, and HAPT, where we obtained the state-of-the-art results. We used HASC dataset for optimizing model parameters in different stages, and explored HAR and HAPT datasets as test-beds to verify our optimizations and postprocessing technique.

Recognition of daily human activities in various locomotion and transportation modes has numerous applications like coaching users for behavior modification and maintaining a healthy lifestyle. Besides, applications and user interfaces aware of user mobility through their smartphones can also aid in urban transportation planning, smart parking, and vehicular traffic monitoring. In this paper, we explored smartphone sensor-based two benchmark datasets (Sussex Huawei Locomotion (SHL) and Transportation Mode Detection (TMD)). Firstly, we demonstrated preprocesssing of sensor data, window length optimization based on Akaike Information Criteria (AIC), and introduced smartphone orientation independent features. We also provided an in-depth analysis of different smartphone sensors' importance for classifying daily activities and transportation modes. We justified the sensor relevance by showing the variation of performances with the number of sensors explored. For refining classifier predictions, we also proposed a post-processing approach named "Mode technique". This method primarily concentrates on the statistical analysis of transportation modes and improves the activity recognition rate in statistical classifiers: Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis, Logistic Regression, Support Vectors Machine with RBF kernel, Random Forest, and deep learning-based methods: Artificial Neural Network and Recurrent Neural Network by smoothing the outputs of these classifiers. Besides, we showed the use of magnitude and jerk-based features to overcome the overfitting problem due to smartphone orientation. We obtained 97.2% accuracy in the SHL dataset and 99.13% accuracy in the TMD dataset. These results demonstrate that our approach can profoundly recognize various activities in advanced locomotion and transportation modes compared to existing methods in two large-scale datasets.

Blindness prevents a person from gaining knowledge of the surrounding environment and makes unassisted navigation, object recognition, obstacle avoidance, and reading tasks a major challenge. In this work, we propose a novel visual aid system for the completely blind. Because of its low cost, compact size, and ease-of-integration, Raspberry Pi 3 Model B+ has been used to demonstrate the functionality of the proposed prototype. The design incorporates a camera and sensors for obstacle avoidance and advanced image processing algorithms for object detection. The distance between the user and the obstacle is measured by the camera as well as ultrasonic sensors. The system includes an integrated reading assistant, in the form of the image-to-text converter, followed by an auditory feedback. The entire setup is lightweight and portable and can be mounted onto a regular pair of eyeglasses, without any additional cost and complexity. Experiments are carried out with 60 completely blind individuals to evaluate the performance of the proposed device with respect to the traditional white cane. The evaluations are performed in controlled environments that mimic real-world scenarios encountered by a blind person. Results show that the proposed device, as compared with the white cane, enables greater accessibility, comfort, and ease of navigation for the visually impaired.

In this paper, we propose a novel approach towards human action recognition using spectral domain feature extraction. Action representations can be considered as image templates, which can be useful for understanding various actions or gestures as well as for recognition and analysis. An action recognition scheme is developed based on extracting spectral features from the frames of a video sequence using the two-dimensional discrete Fourier transform (2D-DFT). The proposed spectral feature selection algorithm offers the advantage of very low feature dimensionality and thus lower computational cost. We show that using frequency domain features enhances the distinguishability of different actions, resulting in high within-class compactness and between-class separability of the extracted features, while certain undesirable phenomena, such as camera movement and change in camera distance, are less severe in the frequency domain. Principal component analysis is performed to further reduce the dimensionality of the feature space. Experimental results on a benchmark action recognition database confirm that our proposed method offers not only computational savings but also a high degree of accuracy.

In this paper, we present some spatio-temporal (XYT) approaches for global-based action representation at the top of the motion history image method. Action representations can be considered as image templates, which can be useful for understanding various actions or gestures as well as for recognition and analysis. These spatio-temporal representations can be useful for various games environments. The motion history image represents how motion moves in image sequence. We present our SURF-based history image. In this method, we extract visual features to select candidate points based on the SURF detector. Then we extract motion features to calculate motion vectors at each point by employing optical flow. In this paper, we also propose a method called intensity-accumulated image method that can manage partial occlusion or some missing moving information. Based on our analyses, we strongly feel that our proposed methods - SURF-based motion history image method and the intensity-accumulated image method can be useful for various applications related to games, gesture and action understanding for analyses.

Motion overwriting due to motion self-occlusion is a big concern in motion and activity recognition. This paper presents a directional motion recognition approach that can solve the motion overwriting for complex actions or activities. Optical flow is split into four directions to compute motion templates. These templates are used to create feature vectors by Hu moments. Very satisfactory recognition results are achieved for various complex actions, which encompass motion overwriting. This method is compared with the basic motion history image method and multi-level motion history image method. The latter method professed that it can overcome motion selfocclusion problem and hence we compare these methods for several complex datasets with complex dimensions.

We have presented motion history-based human motion recognition technique with various formats of feature vectors. Since the inception of the motion history image (MHI) template for motion recognition, various progresses have been adopted to improve this basic MHI. Stages of development of appearance-based representation and recognition approach are presented here on the basic motion history-based approach to solve self-occlusion problem using our method. Excellent recognition rate for various motions has been found. This is based on gradient-based optical flow calculation. For recognition, Hu moments are considered to calculate feature vectors. Various feature vectors are considered in this paper.