Event Streams Research Articles

رۆڵ ‌و به‌شداریی سه‌ربازیی كورد له‌ جوڵانه‌وه‌ی مایسی 1941دا

The Military Role of the Kurds and their Participation in the May 1941 Movement The Iraqis’ movement in May 1941 is considered as an important event in contemporary history of this country. This movement was led to change and switch the British-Iraqi relations form political conflict to a direct military confrontation. The results of the movement and event streams had an important and extreme impact on the army, in general, military officers and other commissioned and non-commissioned officers of Iraqi-army, in particular. The Kurdish soldiers’ active participation, as an influential ethnic in Iraqi’s army units and formation has its own significance on the mentioned movement and events. These being multiethnic armed forces require some multidimensional studies to find out the role of the main and various ethnic groups and components of the army in that movement. Thus, the current study, which is conducted for the mentioned purpose, aims at addressing the role, participation, and participation approaches of Kurdish soldiers and their influences on the movement in March 1941. For conducting this study, the descriptive and analytical historical research methods are used to answer the following research questions: (1) What and how much was the role of Kurdish soldiers in the army among the event streams of movement in March 1941? (2) How was the influence of Kurds and their status in leading the army, and in different units of Iraqi army during the movement? The study has reached some outcomes which are presented in the last section.

VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows.

Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency. In practice, visible cameras can better perceive texture details and slow motion, while event cameras can be free from motion blurs and have a larger dynamic range which enables them to work well under fast motion and low illumination (LI). Therefore, the two sensors can cooperate with each other to achieve more reliable object tracking. In this work, we propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task. Our dataset consists of 820 video pairs captured under LI, high speed, and background clutter scenarios, and it is divided into a training and a testing subset, each of which contains 500 and 320 videos, respectively. Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods by extending current single-modality trackers into dual-modality versions. More importantly, we further build a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data. Extensive experiments on the proposed VisEvent dataset, FE108, COESOT, and two simulated datasets (i.e., OTB-DVS and VOT-DVS), validated the effectiveness of our model. The dataset and source code have been released on: https://github.com/wangxiao5791509/VisEvent_SOT_Benchmark.

Neuromorphic Camera Denoising Using Graph Neural Network-Driven Transformers.

Neuromorphic vision is a bio-inspired technology that has triggered a paradigm shift in the computer vision community and is serving as a key enabler for a wide range of applications. This technology has offered significant advantages, including reduced power consumption, reduced processing needs, and communication speedups. However, neuromorphic cameras suffer from significant amounts of measurement noise. This noise deteriorates the performance of neuromorphic event-based perception and navigation algorithms. In this article, we propose a novel noise filtration algorithm to eliminate events that do not represent real log-intensity variations in the observed scene. We employ a graph neural network (GNN)-driven transformer algorithm, called GNN-Transformer, to classify every active event pixel in the raw stream into real log-intensity variation or noise. Within the GNN, a message-passing framework, referred to as EventConv, is carried out to reflect the spatiotemporal correlation among the events while preserving their asynchronous nature. We also introduce the known-object ground-truth labeling (KoGTL) approach for generating approximate ground-truth labels of event streams under various illumination conditions. KoGTL is used to generate labeled datasets, from experiments recorded in challenging lighting conditions, including moon light. These datasets are used to train and extensively test our proposed algorithm. When tested on unseen datasets, the proposed algorithm outperforms state-of-the-art methods by at least 8.8% in terms of filtration accuracy. Additional tests are also conducted on publicly available datasets (ETH Zürich Color-DAVIS346 datasets) to demonstrate the generalization capabilities of the proposed algorithm in the presence of illumination variations and different motion dynamics. Compared to state-of-the-art solutions, qualitative results verified the superior capability of the proposed algorithm to eliminate noise while preserving meaningful events in the scene.

The Impact of Social Media as a Part of Fashion Marketing and its Impact on Youngsters

Abstract: This research is aimed to understand the impact of social media as a part of fashion marketing and its impact on youngsters, social media on the face of global society has created a new network of social connection with youngsters. Their relationship with influencers on “#outfit of the day” on Instagram is attractive to youngsters, social media marketing can benefit fashion brand in many ways. Including target audience, brand awareness and so far social media platforms by designers to promote, their own brand. Social media platform have also become a key tool for fashion brand, to showcase their collection and engage with consumers through live streaming event and social media campaigns. It has impacted the fashion industry through the democratization of fashion. Personalized fashion recommendations are becoming more popular, making it easier for consumers to discover new styles and brands that align with their individual tastes. People want to offer real-time interactions with them through an active presence in social media; social media might consider digital advertising highly impactful and more valuable and authentic than traditional advertising. Social media platform such as Instagram has recently become the most popular social networking site among the young people. In addition, selling and marketing the product in the virtual store on Instagram represent a new shopping most of the consumers. In survey the constant stream of New Style encourages us to buy, even if we do not need them. People want to fit into society and have the coolest or most desired product out there which influences the spread of new items becoming popular on social media network. This research paper emphasizes more on understanding the mindset of youth and their views on social media as a part of fashion marketing. All together of50 respondents as youth of age group (18-30yrs) were taken, Primary research has been taken as Google form survey as questionnaire. The increased diversity and representation that social media has brought to the fashion industry is very positive development, and it will be interesting to see how this continues to evolve in the future

Event-Based Non-rigid Reconstruction of Low-Rank Parametrized Deformations from Contours

Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In recent years, event cameras have gained significant attention due to their bio-inspired properties, such as high temporal resolution and high dynamic range. In this paper, we propose a novel approach for reconstructing such deformations using event measurements. Under the assumption of a static background, where all events are generated by the motion, our approach estimates the deformation of objects from events generated at the object contour in a probabilistic optimization framework. It associates events to mesh faces on the contour and maximizes the alignment of the line of sight through the event pixel with the associated face. In experiments on synthetic and real data of human body motion, we demonstrate the advantages of our method over state-of-the-art optimization and learning-based approaches for reconstructing the motion of human arms and hands. In addition, we propose an efficient event stream simulator to synthesize realistic event data for human motion.

Faces in Event Streams (FES): An Annotated Face Dataset for Event Cameras.

The use of event-based cameras in computer vision is a growing research direction. However, despite the existing research on face detection using the event camera, a substantial gap persists in the availability of a large dataset featuring annotations for faces and facial landmarks on event streams, thus hampering the development of applications in this direction. In this work, we address this issue by publishing the first large and varied dataset (Faces in Event Streams) with a duration of 689 min for face and facial landmark detection in direct event-based camera outputs. In addition, this article presents 12 models trained on our dataset to predict bounding box and facial landmark coordinates with an mAP50 score of more than 90%. We also performed a demonstration of real-time detection with an event-based camera using our models.

Short‐term effects of Storm Daniel on Salmo farioides (Karaman, 1938) in a high‐gradient stream

AbstractClimate change is expected to increase the magnitude, frequency, and intensity of extreme natural phenomena such as droughts and floods. These events can have devastating impacts on aquatic biota, thus there is a dire need to assess species' natural dynamics and to incorporate them into species' conservation actions and flood management decisions. In September 2023, an extreme meteorological event (Storm Daniel) occurred over the eastern Mediterranean, causing unprecedented high flooding events in many streams and rivers of central Greece. Almost 2 months after the event, we investigated the effects of the storm on Salmo farioides in a high‐altitude stream (Kraniotiko stream, Acheloos river basin) by comparing pre‐flood (June and August 2023) with post‐flood (October 2023) data on fish population abundances and size structure. Our results provide direct evidence that the population of S. farioides was almost wipedout from the investigated stream, as post‐flood fish densities were 9.3% of the pre‐flood data (August) densities. Small‐sized individuals (6–10 cm) were extirpated, indicating a 99% decrease during the post‐flood period, totally reversing the increasing trend observed from June to August (pre‐flood period). In conclusion, the profound and rapid decline observed in the population of S. farioides following the extreme flooding event highlights the urgent need for proactive conservation measures and adaptive management strategies to safeguard vulnerable aquatic species in the face of escalating climate‐related challenges.

Reliable Event Generation With Invertible Conditional Normalizing Flow.

Event streams provide a novel paradigm to describe visual scenes by capturing intensity variations above specific thresholds along with various types of noise. Existing event generation methods usually rely on one-way mappings using hand-crafted parameters and noise rates, which may not adequately suit diverse scenarios and event cameras. To address this limitation, we propose a novel approach to learn a bidirectional mapping between the feature space of event streams and their inherent parameters, enabling the generation of reliable event streams with enhanced generalization capabilities. We first randomly generate a vast number of parameters and synthesize massive event streams using an event simulator. Subsequently, an event-based normalizing flow network is proposed to learn the invertible mapping between the representation of a synthetic event stream and its parameters. The invertible mapping is implemented by incorporating an intensity-guided conditional affine simulation mechanism, facilitating better alignment between event features and parameter spaces. Additionally, we impose constraints on event sparsity, edge distribution, and noise distribution through novel event losses, further emphasizing event priors in the bidirectional mapping. Our framework surpasses state-of-the-art methods in video reconstruction, optical flow estimation, and parameter estimation tasks on synthetic and real-world datasets, exhibiting excellent generalization across diverse scenes and cameras.

Event encryption: rethinking privacy exposure for neuromorphic imaging

Bio-inspired neuromorphic cameras sense illumination changes on a per-pixel basis and generate spatiotemporal streaming events within microseconds in response, offering visual information with high temporal resolution over a high dynamic range. Such devices often serve in surveillance systems due to their applicability and robustness in environments with high dynamics and harsh lighting, where they can still supply clearer recordings than traditional imaging. In other words, when it comes to privacy-relevant cases, neuromorphic cameras also expose more sensitive data and pose serious security threats. Therefore, asynchronous event streams necessitate careful encryption before transmission and usage. This work discusses several potential attack scenarios and approaches event encryption from the perspective of neuromorphic noise removal, in which we inversely introduce well-crafted noise into raw events until they are obfuscated. Our evaluations show that the encrypted events can effectively protect information from attacks of low-level visual reconstruction and high-level neuromorphic reasoning, and thus feature dependable privacy-preserving competence. The proposed solution gives impetus to the security of event data and paves the way to a highly encrypted technique for privacy-protective neuromorphic imaging.

ERS-HDRI: Event-Based Remote Sensing HDR Imaging

High dynamic range imaging (HDRI) is an essential task in remote sensing, enhancing low dynamic range (LDR) remote sensing images and benefiting downstream tasks, such as object detection and image segmentation. However, conventional frame-based HDRI methods may encounter challenges in real-world scenarios due to the limited information inherent in a single image captured by conventional cameras. In this paper, an event-based remote sensing HDR imaging framework is proposed to address this problem, denoted as ERS-HDRI, which reconstructs the remote sensing HDR image from a single-exposure LDR image and its concurrent event streams. The proposed ERS-HDRI leverages a coarse-to-fine framework, incorporating the event-based dynamic range enhancement (E-DRE) network and the gradient-enhanced HDR reconstruction (G-HDRR) network. Specifically, to efficiently achieve dynamic range fusion from different domains, the E-DRE network is designed to extract the dynamic range features from LDR frames and events and perform intra- and cross-attention operations to adaptively fuse multi-modal data. A denoise network and a dense feature fusion network are then employed for the generation of the coarse, clean HDR image. Then, the G-HDRR network, with its gradient enhancement module and multiscale fusion module, performs structure enforcement on the coarse HDR image and generates a fine informative HDR image. In addition, this work introduces a specialized hybrid imaging system and a novel, real-world event-based remote sensing HDRI dataset that contains aligned remote sensing LDR images, remote sensing HDR images, and concurrent event streams for evaluation. Comprehensive experiments have demonstrated the effectiveness of the proposed method. Specifically, it improves state-of-the-art PSNR by about 30% and the SSIM score by about 9% on the real-world dataset.

Measuring diameters and velocities of artificial raindrops with a neuromorphic event camera

Abstract. Hydrometers that measure size and velocity distributions of precipitation are needed for research and corrections of rainfall estimates from weather radars and microwave links. Existing optical disdrometers measure droplet size distributions, but underestimate small raindrops and are impractical for widespread always-on IoT deployment. We study the feasibility of measuring droplet size and velocity using a neuromorphic event camera. These dynamic vision sensors asynchronously output a sparse stream of pixel brightness changes. Droplets falling through the plane of focus of a steeply down-looking camera create events generated by the motion of the droplet across the field of view. Droplet size and speed are inferred from the hourglass-shaped stream of events. Using an improved hard disk arm actuator to reliably generate artificial raindrops with a range of small sizes, our experiments show maximum errors of 7 % (mean absolute percentage error) for droplet sizes from 0.3 to 2.5 mm and speeds from 1.3 to 8.0 m s−1. Measurements with the same setup from a commercial PARSIVEL disdrometer show similar results. Both devices slightly overestimate the small droplet volume with a volume overestimation of 25 % from the event camera measurements and 50 % from the PARSIVEL instrument. Each droplet requires processing of 5000 to 50 000 brightness change events, potentially enabling low-power always-on disdrometers that consume power proportional to the rainfall rate. Data and code are available at the paper website https://sites.google.com/view/dvs-disdrometer/home (Micev et al., 2023).

A robust autofocusing method for microscopic imaging based on an event camera

Autofocusing is a crucial method for enhancing the efficiency of biological detection workflows. Traditional methods involve calculating various focus metrics on images captured by standard frame-based cameras at multiple static positions to determine the focal point, which can be time-consuming. In contrast, event cameras have the capability to asynchronously detect brightness changes within the field of view of the microscope and provide a continuous stream of events triggered by axial motion. A completely automated coarse-to-fine method is proposed for event based autofocusing, independent of the objective-sample distance. Two criteria for autofocusing in sufficient and low illumination are respectively proposed. The results show that the dynamic accuracy and dynamic repeatability is less than 5 mm.

Continuous-time Object Segmentation using High Temporal Resolution Event Camera.

Event cameras are novel bio-inspired sensors, where individual pixels operate independently and asynchronously, generating intensity changes as events. Leveraging the microsecond resolution (no motion blur) and high dynamic range (compatible with extreme light conditions) of events, there is considerable promise in directly segmenting objects from sparse and asynchronous event streams in various applications. However, different from the rich cues in video object segmentation, it is challenging to segment complete objects from the sparse event stream. In this paper, we present the first framework for continuous-time object segmentation from event stream. Given the object mask at the initial time, our task aims to segment the complete object at any subsequent time in event streams. Specifically, our framework consists of a Recurrent Temporal Embedding Extraction (RTEE) module based on a novel ResLSTM, a Cross-time Spatiotemporal Feature Modeling (CSFM) module which is a transformer architecture with long-term and short-term matching modules, and a segmentation head. The historical events and masks (reference sets) are recurrently fed into our framework along with current-time events. The temporal embedding is updated as new events are input, enabling our framework to continuously process the event stream. To train and test our model, we construct both real-world and simulated event-based object segmentation datasets, each comprising event streams, APS images, and object annotations. Extensive experiments on our datasets demonstrate the effectiveness of the proposed recurrent architecture. Our code and dataset are available at https://sites.google.com/view/ecos-net/.

Spiking Transfer Learning from RGB Image to Neuromorphic Event Stream.

Recent advances in bio-inspired vision with event cameras and associated spiking neural networks (SNNs) have provided promising solutions for low-power consumption neuromorphic tasks. However, as the research of event cameras is still in its infancy, the amount of labeled event stream data is much less than that of the RGB database. The traditional method of converting static images into event streams by simulation to increase the sample size cannot simulate the characteristics of event cameras such as high temporal resolution. To take advantage of both the rich knowledge in labeled RGB images and the features of the event camera, we propose a transfer learning method from the RGB to the event domain in this paper. Specifically, we first introduce a transfer learning framework named R2ETL (RGB to Event Transfer Learning), including a novel encoding alignment module and a feature alignment module. Then, we introduce the temporal centered kernel alignment (TCKA) loss function to improve the efficiency of transfer learning. It aligns the distribution of temporal neuron states by adding a temporal learning constraint. Finally, we theoretically analyze the amount of data required by the deep neuromorphic model to prove the necessity of our method. Numerous experiments demonstrate that our proposed framework outperforms the state-of-the-art SNN and artificial neural network (ANN) models trained on event streams, including N-MNIST, CIFAR10-DVS and N-Caltech101. This indicates that the R2ETL framework is able to leverage the knowledge of labeled RGB images to help the training of SNN on event streams.

General purpose data streaming platform for log analysis, anomaly detection and security protection

INFN-CNAF is one of the Worldwide LHC Computing Grid (WLCG) Tier-1 data centres, providing computing, networking and storage resources to a wide variety of scientific collaborations, not limited to the four LHC (Large Hadron Collider) experiments. The INFN-CNAF data centre will move to a new location next year. At the same time, the requirements from our experiments and users are becoming increasingly challenging and new scientific communities have started or will soon start exploiting our resources. Currently, we are reengineering several services, in particular our monitoring infrastructure, in order to improve the day-by-day operations and to cope with the increasing complexity of the use cases and with the future expansion of the centre. This scenario led us to implement a data streaming infrastructure designed to enable log analysis, anomaly detection, threat hunting, integrity monitoring and incident response. Such data streaming platform has been organised to manage different kinds of data coming from heterogeneous sources, to support multi-tenancy and to be scalable. Moreover, we will be able to provide an on demand end-to-end data streaming application to those users/communities requesting such kind of facility. The infrastructure is based on the Apache Kafka platform, which provides streaming of events at large scale, with authorization and authentication configured at the topic level for ensuring data isolation and protection. Data can be consumed by different applications, such as those devoted to log analysis, which provide the capability to index large amounts of data and implement appropriate access policies to inspect and visualise information. In this contribution we will present and motivate our technological choices for the definition of the infrastructure, we will describe its components and we will depict use cases which can be addressed with this platform.

EventHDR: From Event to High-Speed HDR Videos and Beyond.

Event cameras are innovative neuromorphic sensors that asynchronously capture the scene dynamics. Due to the event-triggering mechanism, such cameras record event streams with much shorter response latency and higher intensity sensitivity compared to conventional cameras. On the basis of these features, previous works have attempted to reconstruct high dynamic range (HDR) videos from events, but have either suffered from unrealistic artifacts or failed to provide sufficiently high frame rates. In this paper, we present a recurrent convolutional neural network that reconstruct high-speed HDR videos from event sequences, with a key frame guidance to prevent potential error accumulation caused by the sparse event data. Additionally, to address the problem of severely limited real dataset, we develop a new optical system to collect a real-world dataset with paired high-speed HDR videos and event streams, facilitating future research in this field. Our dataset provides the first real paired dataset for event-to-HDR reconstruction, avoiding potential inaccuracies from simulation strategies. Experimental results demonstrate that our method can generate high-quality, high-speed HDR videos. We further explore the potential of our work in cross-camera reconstruction and downstream computer vision tasks, including object detection, panoramic segmentation, optical flow estimation, and monocular depth estimation under HDR scenarios.

Tackling Event-Based Lip-Reading by Exploring Multigrained Spatiotemporal Clues.

Automatic lip-reading (ALR) is the task of recognizing words based on visual information obtained from the speaker's lip movements. In this study, we introduce event cameras, a novel type of sensing device, for ALR. Event cameras offer both technical and application advantages over conventional cameras for ALR due to their higher temporal resolution, less redundant visual information, and lower power consumption. To recognize words from the event data, we propose a novel multigrained spatiotemporal features learning framework, which is capable of perceiving fine-grained spatiotemporal features from microsecond time-resolved event data. Specifically, we first convert the event data into event frames of multiple temporal resolutions to avoid losing too much visual information at the event representation stage. Then, they are fed into a multibranch subnetwork where the branch operating on low-rate frames can perceive spatially complete but temporally coarse features, while the branch operating on high frame rate can perceive spatially coarse but temporally fine features. Thus, fine-grained spatial and temporal features can be simultaneously learned by integrating the features perceived by different branches. Furthermore, to model the temporal relationships in the event stream, we design a temporal aggregation subnetwork to aggregate the features perceived by the multibranch subnetwork. In addition, we collect two event-based lip-reading datasets (DVS-Lip and DVS-LRW100) for the study of the event-based lip-reading task. Experimental results demonstrate the superiority of the proposed model over the state-of-the-art event-based action recognition models and video-based lip-reading models.

Adaptive Unsupervised Learning-Based 3D Spatiotemporal Filter for Event-Driven Cameras.

In the evolving landscape of robotics and visual navigation, event cameras have gained important traction, notably for their exceptional dynamic range, efficient power consumption, and low latency. Despite these advantages, conventional processing methods oversimplify the data into 2 dimensions, neglecting critical temporal information. To overcome this limitation, we propose a novel method that treats events as 3D time-discrete signals. Drawing inspiration from the intricate biological filtering systems inherent to the human visual apparatus, we have developed a 3D spatiotemporal filter based on unsupervised machine learning algorithm. This filter effectively reduces noise levels and performs data size reduction, with its parameters being dynamically adjusted based on population activity. This ensures adaptability and precision under various conditions, like changes in motion velocity and ambient lighting. In our novel validation approach, we first identify the noise type and determine its power spectral density in the event stream. We then apply a one-dimensional discrete fast Fourier transform to assess the filtered event data within the frequency domain, ensuring that the targeted noise frequencies are adequately reduced. Our research also delved into the impact of indoor lighting on event stream noise. Remarkably, our method led to a 37% decrease in the data point cloud, improving data quality in diverse outdoor settings.

Backlight and dim space object detection based on a novel event camera.

For space object detection tasks, conventional optical cameras face various application challenges, including backlight issues and dim light conditions. As a novel optical camera, the event camera has the advantages of high temporal resolution and high dynamic range due to asynchronous output characteristics, which provides a new solution to the above challenges. However, the asynchronous output characteristic of event cameras makes them incompatible with conventional object detection methods designed for frame images. Asynchronous convolutional memory network (ACMNet) for processing event camera data is proposed to solve the problem of backlight and dim space object detection. The key idea of ACMNet is to first characterize the asynchronous event streams with the Event Spike Tensor (EST) voxel grid through the exponential kernel function, then extract spatial features using a feed-forward feature extraction network, and aggregate temporal features using a proposed convolutional spatiotemporal memory module ConvLSTM, and finally, the end-to-end object detection using continuous event streams is realized. Comparison experiments among ACMNet and classical object detection methods are carried out on Event_DVS_space7, which is a large-scale space synthetic event dataset based on event cameras. The results show that the performance of ACMNet is superior to the others, and the mAP is improved by 12.7% while maintaining the processing speed. Moreover, event cameras still have a good performance in backlight and dim light conditions where conventional optical cameras fail. This research offers a novel possibility for detection under intricate lighting and motion conditions, emphasizing the superior benefits of event cameras in the realm of space object detection.

RGBE-Gaze: A Large-scale Event-based Multimodal Dataset for High Frequency Remote Gaze Tracking.

High-frequency gaze tracking demonstrates significant potential in various critical applications, such as foveated rendering, gaze-based identity verification, and the diagnosis of mental disorders. However, existing eye-tracking systems based on CCD/CMOS cameras either provide tracking frequencies below 200 Hz or employ high-speed cameras, leading to substantial power consumption and increased device volume. While there have been some high-speed eye-tracking datasets and methods based on event cameras, they are primarily tailored for near-eye camera scenarios. They lack the advantages associated with remote camera scenarios, such as the absence of the need for direct contact, enhanced user comfort and convenience, and the freedom of head pose in natural environments. In this work, we present RGBE-Gaze, the first large-scale and multimodal dataset for remote gaze tracking in high-frequency through synchronizing RGB and event cameras. This dataset is collected from 66 participants with diverse genders and age groups. The custom hybrid RGB-Event camera setup is leveraged to collect 3.6 million full-face high spatial resolution RGB images and 26.3 billion high temporal resolution event samples. Additionally, the dataset includes 10.7 million gaze references from the Gazepoint GP3 HD eye tracker and 15,972 sparse points of gaze (PoG) ground truth obtained through manual stimuli clicks by participants. We also present the dataset distribution across characteristics such as head pose and distance, gaze direction, pupil size, and tracking frequency. Furthermore, we introduce a hybrid frame-event based gaze estimation method specifically designed for the collected dataset. Moreover, we perform extensive evaluations of this method along with existing frame-based gaze estimation methods under various gaze-related factors, including different subjects, gaze directions, head poses, head distances, and pupil diameters. The evaluation results illustrate that introducing event stream as a new modality into the dataset improves gaze tracking frequency and demonstrates greater estimation robustness across diverse gaze-related factors.