Gesture
-
Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
2025-06-01 11:07:25Youngmin Kim, Jiwan Chung, Jisoo Kim, Sunghyun Lee, Sangkyu Lee, Junhyeok Kim, Cheoljong Yang, Youngjae YuAbstract
Nonverbal communication is integral to human interaction, with gestures, facial expressions, and body language conveying critical aspects of intent and emotion. However, existing large language models (LLMs) fail to effectively incorporate these nonverbal elements, limiting their capacity to create fully immersive conversational experiences. We introduce MARS, a multimodal language model designed to understand and generate nonverbal cues alongside text, bridging this gap in conversational AI. Our key innovation is VENUS, a large-scale dataset comprising annotated videos with time-aligned text, facial expressions, and body language. Leveraging VENUS, we train MARS with a next-token prediction objective, combining text with vector-quantized nonverbal representations to achieve multimodal understanding and generation within a unified framework. Based on various analyses of the VENUS datasets, we validate its substantial scale and high effectiveness. Our quantitative and qualitative results demonstrate that MARS successfully generates text and nonverbal languages, corresponding to conversational input.
Abstract (translated)
非言语沟通在人类互动中至关重要，手势、面部表情和身体语言传达了意图和情感的重要方面。然而，现有的大型语言模型（LLM）未能有效地融合这些非言语元素，这限制了它们创造全面沉浸式对话体验的能力。为此，我们推出了MARS，这是一个多模态语言模型，旨在理解并生成与文本相关的非言语线索，在会话AI中填补这一空白。我们的关键创新是VENUS，一个大规模的数据集，包括带有时间对齐的文字、面部表情和身体语言的注释视频。利用VENUS数据集，我们通过结合文字与向量量化后的非言语表示进行训练，以实现多模态理解和生成的一体化框架。基于对VENUS数据集的各种分析，我们验证了其规模庞大且有效性高。我们的定量和定性结果显示，MARS成功地根据对话输入产生了相应的文本和非言语表达。
URL
https://arxiv.org/abs/2506.00958
PDF
-
DiG-Net: Enhancing Quality of Life through Hyper-Range Dynamic Gesture Recognition in Assistive Robotics
2025-05-30 16:47:44Eran Bamani Beeri, Eden Nissinman, Avishai SintovAbstract
Dynamic hand gestures play a pivotal role in assistive human-robot interaction (HRI), facilitating intuitive, non-verbal communication, particularly for individuals with mobility constraints or those operating robots remotely. Current gesture recognition methods are mostly limited to short-range interactions, reducing their utility in scenarios demanding robust assistive communication from afar. In this paper, we introduce a novel approach designed specifically for assistive robotics, enabling dynamic gesture recognition at extended distances of up to 30 meters, thereby significantly improving accessibility and quality of life. Our proposed Distance-aware Gesture Network (DiG-Net) effectively combines Depth-Conditioned Deformable Alignment (DADA) blocks with Spatio-Temporal Graph modules, enabling robust processing and classification of gesture sequences captured under challenging conditions, including significant physical attenuation, reduced resolution, and dynamic gesture variations commonly experienced in real-world assistive environments. We further introduce the Radiometric Spatio-Temporal Depth Attenuation Loss (RSTDAL), shown to enhance learning and strengthen model robustness across varying distances. Our model demonstrates significant performance improvement over state-of-the-art gesture recognition frameworks, achieving a recognition accuracy of 97.3% on a diverse dataset with challenging hyper-range gestures. By effectively interpreting gestures from considerable distances, DiG-Net significantly enhances the usability of assistive robots in home healthcare, industrial safety, and remote assistance scenarios, enabling seamless and intuitive interactions for users regardless of physical limitations
Abstract (translated)
动态手势在辅助人机交互（HRI）中扮演着关键角色，它促进了直观的非语言交流，特别是对于行动受限或远程操作机器人的个人而言。目前的手势识别方法大多局限于短距离互动，这限制了它们在需要远距离可靠辅助通信场景中的实用性。本文介绍了一种专为辅助机器人设计的新方法，能够在长达30米的距离内实现动态手势识别，从而显著提高可访问性和生活质量。 我们提出的距离感知手势网络（DiG-Net）有效地结合了深度条件形变对齐（DADA）模块和时空图模块，能够处理在实际辅助环境中常见的挑战性情况下的手势序列的稳健处理与分类。这些挑战包括物理衰减、分辨率降低以及动态的手势变化等。我们还引入了辐射时空深度衰减损失（RSTDAL），以增强模型的学习能力和跨不同距离的鲁棒性。 我们的模型在包含具有极高难度远距手势的数据集上，相比最先进的手势识别框架取得了显著的性能提升，达到了97.3%的识别准确率。通过有效地从较远的距离解释手势，DiG-Net极大地提升了辅助机器人在家用医疗保健、工业安全和远程援助场景中的可用性，使用户能够不受物理限制地实现无缝直观互动。 这种技术进步不仅提高了机器人的用户体验，还为需要特殊帮助的人群提供了更多的独立性和灵活性。通过改善人机交互的方式，DiG-Net有助于推动智能辅助设备在日常生活中的广泛应用和发展。
URL
https://arxiv.org/abs/2505.24786
PDF
-
SignBot: Learning Human-to-Humanoid Sign Language Interaction
2025-05-30 06:42:09Guanren Qiao, Sixu Lin, Ronglai Zuo Zhizheng Wu, Kui Jia, Guiliang LiuAbstract
Sign language is a natural and visual form of language that uses movements and expressions to convey meaning, serving as a crucial means of communication for individuals who are deaf or hard-of-hearing (DHH). However, the number of people proficient in sign language remains limited, highlighting the need for technological advancements to bridge communication gaps and foster interactions with minorities. Based on recent advancements in embodied humanoid robots, we propose SignBot, a novel framework for human-robot sign language interaction. SignBot integrates a cerebellum-inspired motion control component and a cerebral-oriented module for comprehension and interaction. Specifically, SignBot consists of: 1) Motion Retargeting, which converts human sign language datasets into robot-compatible kinematics; 2) Motion Control, which leverages a learning-based paradigm to develop a robust humanoid control policy for tracking sign language gestures; and 3) Generative Interaction, which incorporates translator, responser, and generator of sign language, thereby enabling natural and effective communication between robots and humans. Simulation and real-world experimental results demonstrate that SignBot can effectively facilitate human-robot interaction and perform sign language motions with diverse robots and datasets. SignBot represents a significant advancement in automatic sign language interaction on embodied humanoid robot platforms, providing a promising solution to improve communication accessibility for the DHH community.
Abstract (translated)
手语是一种自然且视觉化的语言形式，通过手势和面部表情来传达意义，是聋人或听力受损者的重要沟通方式。然而，精通手语的人数仍然有限，这凸显了技术进步在弥合沟通差距、促进与少数群体互动方面的必要性。基于近期有关具身类人机器人的进展，我们提出了一种名为SignBot的新框架，旨在实现人类与机器人之间的手语交流。SignBot集成了一个受小脑启发的运动控制组件和一个面向大脑的理解与互动模块。 具体而言，SignBot包括以下三个部分： 1. 运动重定向：将人类手语数据集转换为机器人兼容的动力学模型。 2. 运动控制：利用基于学习的方法来开发一种稳健的人形机器人控制策略，用于跟踪手语手势。 3. 生成互动：整合翻译器、响应者和手语生成器，从而实现机器人与人之间的自然且有效的沟通。 模拟实验和真实世界实验的结果表明，SignBot能够有效促进人类与机器人的交互，并能在不同类型的机器人和数据集中执行各种手语动作。SignBot在具身类人机器人平台上实现了自动手语互动的重大进展，为提高听力受损社区的通信可访问性提供了有前景的解决方案。
URL
https://arxiv.org/abs/2505.24266
PDF
-
MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
2025-05-29 05:40:46Siyuan Wang, Jiawei Liu, Wei Wang, Yeying Jin, Jinsong Du, Zhi HanAbstract
Co-Speech Gesture Video Generation aims to generate vivid speech videos from audio-driven still images, which is challenging due to the diversity of different parts of the body in terms of amplitude of motion, audio relevance, and detailed features. Relying solely on audio as the control signal often fails to capture large gesture movements in video, leading to more pronounced artifacts and distortions. Existing approaches typically address this issue by introducing additional a priori information, but this can limit the practical application of the task. Specifically, we propose a Motion Mask-Guided Two-Stage Network (MMGT) that uses audio, as well as motion masks and motion features generated from the audio signal to jointly drive the generation of synchronized speech gesture videos. In the first stage, the Spatial Mask-Guided Audio Pose Generation (SMGA) Network generates high-quality pose videos and motion masks from audio, effectively capturing large movements in key regions such as the face and gestures. In the second stage, we integrate the Motion Masked Hierarchical Audio Attention (MM-HAA) into the Stabilized Diffusion Video Generation model, overcoming limitations in fine-grained motion generation and region-specific detail control found in traditional methods. This guarantees high-quality, detailed upper-body video generation with accurate texture and motion details. Evaluations show improved video quality, lip-sync, and gesture. The model and code are available at this https URL.
Abstract (translated)
Co-Speech Gesture Video Generation（伴随言语的手势视频生成）旨在从音频驱动的静止图像中生成生动的讲话视频。由于身体各部位在运动幅度、与音频的相关性以及细节特征上的多样性，这一任务颇具挑战性。单纯依靠音频作为控制信号往往难以捕捉到视频中的大幅度手势动作，导致更为明显的伪影和失真现象。现有的方法通常通过引入额外的先验信息来解决此问题，但这可能会限制该任务的实际应用。 为了解决这些问题，我们提出了一种名为Motion Mask-Guided Two-Stage Network（MMGT）的方法。该网络不仅使用音频信号，还利用从音频信号生成的运动掩码和运动特征共同驱动同步言语手势视频的生成。在第一阶段中，Spatial Mask-Guided Audio Pose Generation（SMGA）网络从音频输入中生成高质量的姿态视频及运动掩码，有效捕捉面部与手势等关键区域的大范围动作变化。在第二阶段中，我们将Motion Masked Hierarchical Audio Attention（MM-HAA）整合进Stabilized Diffusion Video Generation模型之中，克服了传统方法在细粒度运动生成和局部细节控制方面的局限性。这确保了高质量的上半身视频生成，并能准确捕捉纹理及动作细节。 实验评估显示，该方法显著提升了视频质量、唇同步效果以及手势表现。相关模型和代码可在提供的链接中获取：[此URL]。
URL
https://arxiv.org/abs/2505.23120
PDF
-
Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay
2025-05-26 14:37:35Hongsong Wang, Ao Sun, Jie Gui, Liang WangAbstract
Gesture recognition is an important research area in the field of computer vision. Most gesture recognition efforts focus on close-set scenarios, thereby limiting the capacity to effectively handle unseen or novel gestures. We aim to address class-incremental gesture recognition, which entails the ability to accommodate new and previously unseen gestures over time. Specifically, we introduce a Prototype-Guided Pseudo Feature Replay (PGPFR) framework for data-free class-incremental gesture recognition. This framework comprises four components: Pseudo Feature Generation with Batch Prototypes (PFGBP), Variational Prototype Replay (VPR) for old classes, Truncated Cross-Entropy (TCE) for new classes, and Continual Classifier Re-Training (CCRT). To tackle the issue of catastrophic forgetting, the PFGBP dynamically generates a diversity of pseudo features in an online manner, leveraging class prototypes of old classes along with batch class prototypes of new classes. Furthermore, the VPR enforces consistency between the classifier's weights and the prototypes of old classes, leveraging class prototypes and covariance matrices to enhance robustness and generalization capabilities. The TCE mitigates the impact of domain differences of the classifier caused by pseudo features. Finally, the CCRT training strategy is designed to prevent overfitting to new classes and ensure the stability of features extracted from old classes. Extensive experiments conducted on two widely used gesture recognition datasets, namely SHREC 2017 3D and EgoGesture 3D, demonstrate that our approach outperforms existing state-of-the-art methods by 11.8\% and 12.8\% in terms of mean global accuracy, respectively. The code is available on this https URL.
Abstract (translated)
手势识别是计算机视觉领域的一个重要研究方向。大多数的手势识别工作集中在闭合集场景上，这限制了有效处理未见过或新颖手势的能力。我们旨在解决类增量手势识别问题，即随着时间的推移能够适应新的和以前未见过的手势。为此，我们引入了一个名为基于原型指导伪特征回放（Prototype-Guided Pseudo Feature Replay, PGPFR）的数据无需求框架来进行类增量手势识别。该框架包括四个组成部分：使用批次原型进行伪特征生成（Pseudo Feature Generation with Batch Prototypes, PFGBP）、旧类的变分原型回放（Variational Prototype Replay, VPR）、新类的截断交叉熵（Truncated Cross-Entropy, TCE），以及连续分类器重新训练策略（Continual Classifier Re-Training, CCRT）。 为了应对灾难性遗忘的问题，PFGBP动态地以在线方式生成多样化的伪特征，利用旧类别的类别原型和新批次的类别原型。此外，VPR通过类别原型和协方差矩阵来增强模型的稳健性和泛化能力，强制分类器权重与旧类别的原型保持一致。TCE则减轻了由伪特征引起的分类器领域差异的影响。最后，CCRT训练策略旨在防止过度拟合新类，并确保从老类提取的特征稳定性。 在两个广泛使用的手势识别数据集（SHREC 2017 3D和EgoGesture 3D）上进行的大量实验表明，在平均全局准确性方面，我们的方法分别比现有的最先进方法高出11.8% 和12.8%。相关代码可在提供的链接中获取。
URL
https://arxiv.org/abs/2505.20049
PDF
-
Integrating emotional intelligence, memory architecture, and gestures to achieve empathetic humanoid robot interaction in an educational setting
2025-05-26 10:37:41Fuze Sun, Lingyu Li, Shixiangyue Meng, Xiaoming Teng, Terry Payne, Paul CraigAbstract
This study investigates the integration of individual human traits into an empathetically adaptive educational robot tutor system designed to improve student engagement and learning outcomes with corresponding Engagement Vector measurement. While prior research in the field of Human-Robot Interaction (HRI) has examined the integration of the traits, such as emotional intelligence, memory-driven personalization, and non-verbal communication, by themselves, they have thus-far neglected to consider their synchronized integration into a cohesive, operational education framework. To address this gap, we customize a Multi-Modal Large Language Model (LLaMa 3.2 from Meta) deployed with modules for human-like traits (emotion, memory and gestures) into an AI-Agent framework. This constitutes to the robot's intelligent core mimicing the human emotional system, memory architecture and gesture control to allow the robot to behave more empathetically while recognizing and responding appropriately to the student's emotional state. It can also recall the student's past learning record and adapt its style of interaction accordingly. This allows the robot tutor to react to the student in a more sympathetic manner by delivering personalized verbal feedback synchronized with relevant gestures. Our study investigates the extent of this effect through the introduction of Engagement Vector Model which can be a surveyor's pole for judging the quality of HRI experience. Quantitative and qualitative results demonstrate that such an empathetic responsive approach significantly improves student engagement and learning outcomes compared with a baseline humanoid robot without these human-like traits. This indicates that robot tutors with empathetic capabilities can create a more supportive, interactive learning experience that ultimately leads to better outcomes for the student.
Abstract (translated)
这项研究调查了将个体人类特质整合到一种旨在通过相应的参与向量测量提高学生参与度和学习成果的同理心适应性教育机器人辅导系统中的情况。尽管先前关于人机交互（HRI）领域的研究已经分别考察了情感智能、基于记忆的个性化以及非言语交流等特质，但它们尚未考虑将这些特质同步整合到一个连贯的操作教育框架中。为了解决这一空白，我们定制了一个多模态大型语言模型（Meta开发的LLaMa 3.2），并部署具有人类特质模块（情绪、记忆和手势）的人工智能代理框架。这构成了机器人智能核心的基础，模仿了人的情感系统、记忆架构以及手势控制，使机器人能够以更富有同理心的方式行为，并且能够识别和适当响应学生的情绪状态。此外，该机器人还可以回忆学生的过往学习记录并相应地调整互动方式。这一过程使得辅导机器人可以更加同情地回应学生，通过个性化的言语反馈与相关的手势同步进行互动。 我们的研究通过引入参与向量模型来探讨这种效应的程度，这可以作为一种衡量HRI体验质量的指标。定量和定性结果表明，这种富有同理心的响应方式显著提高了学生的参与度和学习成果，相较于没有这些人类特质的人形机器人基线而言效果更为出色。这意味着具备同情能力的辅导机器人能够创造一个更加支持性和互动性的学习环境，从而最终为学生带来更好的成绩。
URL
https://arxiv.org/abs/2505.19803
PDF
-
Multi-task Learning For Joint Action and Gesture Recognition
2025-05-23 13:16:27Konstantinos Spathis, Nikolaos Kardaris, Petros MaragosAbstract
In practical applications, computer vision tasks often need to be addressed simultaneously. Multitask learning typically achieves this by jointly training a single deep neural network to learn shared representations, providing efficiency and improving generalization. Although action and gesture recognition are closely related tasks, since they focus on body and hand movements, current state-of-the-art methods handle them separately. In this paper, we show that employing a multi-task learning paradigm for action and gesture recognition results in more efficient, robust and generalizable visual representations, by leveraging the synergies between these tasks. Extensive experiments on multiple action and gesture datasets demonstrate that handling actions and gestures in a single architecture can achieve better performance for both tasks in comparison to their single-task learning variants.
Abstract (translated)
在实际应用中，计算机视觉任务通常需要同时处理。多任务学习通过联合训练单一的深度神经网络来学习共享表示，从而提高了效率并改进了泛化能力。尽管动作识别和手势识别是紧密相关的任务（它们都关注身体和手部的动作），当前最先进的方法仍倾向于分别处理这些任务。在本文中，我们展示了使用一个多任务学习框架来进行动作和手势识别可以产生更有效、更具鲁棒性和通用性的视觉表示，通过利用这些任务之间的协同效应。在多个动作和手势数据集上进行的广泛实验表明，在单一架构下同时处理动作和手势相比各自的单任务学习变体能够实现更好的性能。
URL
https://arxiv.org/abs/2505.17867
PDF
-
UAV Control with Vision-based Hand Gesture Recognition over Edge-Computing
2025-05-22 21:39:13Sousannah Abdalla, Sabur BaidyaAbstract
Gesture recognition presents a promising avenue for interfacing with unmanned aerial vehicles (UAVs) due to its intuitive nature and potential for precise interaction. This research conducts a comprehensive comparative analysis of vision-based hand gesture detection methodologies tailored for UAV Control. The existing gesture recognition approaches involving cropping, zooming, and color-based segmentation, do not work well for this kind of applications in dynamic conditions and suffer in performance with increasing distance and environmental noises. We propose to use a novel approach leveraging hand landmarks drawing and classification for gesture recognition based UAV control. With experimental results we show that our proposed method outperforms the other existing methods in terms of accuracy, noise resilience, and efficacy across varying distances, thus providing robust control decisions. However, implementing the deep learning based compute intensive gesture recognition algorithms on the UAV's onboard computer is significantly challenging in terms of performance. Hence, we propose to use a edge-computing based framework to offload the heavier computing tasks, thus achieving closed-loop real-time performance. With implementation over AirSim simulator as well as over a real-world UAV, we showcase the advantage of our end-to-end gesture recognition based UAV control system.
Abstract (translated)
手势识别为与无人机（UAV）交互提供了一条有前景的途径，因其直观性和潜在的精确互动能力。本研究对基于视觉的手势检测方法进行了全面的比较分析，这些方法专门用于UAV控制。现有的涉及裁剪、缩放和基于颜色分割的手势识别方法，在动态条件下效果不佳，并且随着距离增加和环境噪声加剧，性能会下降。我们提出了一种新的方法，利用手部关键点绘制与分类进行手势识别，从而实现基于UAV的控制。通过实验结果表明，相较于现有的方法，我们的方法在准确性、抗噪性和不同距离下的有效性方面表现更佳，因此能够提供稳健的控制决策。然而，在无人机上部署深度学习驱动的手势识别算法面临计算资源有限的问题。为此，我们提出了一种基于边缘计算框架的方法来卸载繁重的计算任务，从而实现闭环实时性能。通过在AirSim模拟器和实际UAV上的实施，展示了我们的端到端手势识别控制系统的优势。
URL
https://arxiv.org/abs/2505.17303
PDF
-
EVA: Expressive Virtual Avatars from Multi-view Videos
2025-05-21 11:22:52Hendrik Junkawitsch, Guoxing Sun, Heming Zhu, Christian Theobalt, Marc HabermannAbstract
With recent advancements in neural rendering and motion capture algorithms, remarkable progress has been made in photorealistic human avatar modeling, unlocking immense potential for applications in virtual reality, augmented reality, remote communication, and industries such as gaming, film, and medicine. However, existing methods fail to provide complete, faithful, and expressive control over human avatars due to their entangled representation of facial expressions and body movements. In this work, we introduce Expressive Virtual Avatars (EVA), an actor-specific, fully controllable, and expressive human avatar framework that achieves high-fidelity, lifelike renderings in real time while enabling independent control of facial expressions, body movements, and hand gestures. Specifically, our approach designs the human avatar as a two-layer model: an expressive template geometry layer and a 3D Gaussian appearance layer. First, we present an expressive template tracking algorithm that leverages coarse-to-fine optimization to accurately recover body motions, facial expressions, and non-rigid deformation parameters from multi-view videos. Next, we propose a novel decoupled 3D Gaussian appearance model designed to effectively disentangle body and facial appearance. Unlike unified Gaussian estimation approaches, our method employs two specialized and independent modules to model the body and face separately. Experimental results demonstrate that EVA surpasses state-of-the-art methods in terms of rendering quality and expressiveness, validating its effectiveness in creating full-body avatars. This work represents a significant advancement towards fully drivable digital human models, enabling the creation of lifelike digital avatars that faithfully replicate human geometry and appearance.
Abstract (translated)
随着神经渲染和动作捕捉算法的最新进展，逼真的数字人类模型取得了显著进步，为虚拟现实、增强现实、远程通信以及游戏、电影和医学等行业带来了巨大的潜力。然而，现有的方法由于面部表情和身体运动表示纠缠不清的问题，无法提供对数字人偶完整、忠实且富有表现力的控制。在本工作中，我们引入了具有表现力的虚拟人偶（EVA），这是一种特定于演员的、完全可控的表现力强的人类模型框架，它能够实现实时高保真度、栩栩如生的渲染，并允许独立控制面部表情、身体运动和手部动作。 具体来说，我们的方法将人类模型设计为两层：一个具有表现力的模板几何层和一个3D高斯外观层。首先，我们提出了一种利用粗到细优化技术从多视角视频中准确恢复身体运动、面部表情和非刚性变形参数的表现力模板跟踪算法。接着，我们提出了一个新的解耦3D高斯外观模型，旨在有效区分人体和面部的外观特征。与统一的高斯估计方法不同，我们的方法采用了两个专门且独立的模块来分别建模身体和脸部。 实验结果表明，EVA在渲染质量和表现力方面超越了现有的最先进技术，验证了其创建全身数字人偶的有效性。这项工作代表了向完全可控的数字化人类模型发展的重要一步，能够创造出忠实再现人体几何结构和外观特征的栩栩如生的数字人偶。
URL
https://arxiv.org/abs/2505.15385
PDF
-
Intentional Gesture: Deliver Your Intentions with Gestures for Speech
2025-05-21 07:24:51Pinxin Liu, Haiyang Liu, Luchuan Song, Chenliang XuAbstract
When humans speak, gestures help convey communicative intentions, such as adding emphasis or describing concepts. However, current co-speech gesture generation methods rely solely on superficial linguistic cues (\textit{e.g.} speech audio or text transcripts), neglecting to understand and leverage the communicative intention that underpins human gestures. This results in outputs that are rhythmically synchronized with speech but are semantically shallow. To address this gap, we introduce \textbf{Intentional-Gesture}, a novel framework that casts gesture generation as an intention-reasoning task grounded in high-level communicative functions. % First, we curate the \textbf{InG} dataset by augmenting BEAT-2 with gesture-intention annotations (\textit{i.e.}, text sentences summarizing intentions), which are automatically annotated using large vision-language models. Next, we introduce the \textbf{Intentional Gesture Motion Tokenizer} to leverage these intention annotations. It injects high-level communicative functions (\textit{e.g.}, intentions) into tokenized motion representations to enable intention-aware gesture synthesis that are both temporally aligned and semantically meaningful, achieving new state-of-the-art performance on the BEAT-2 benchmark. Our framework offers a modular foundation for expressive gesture generation in digital humans and embodied AI. Project Page: this https URL
Abstract (translated)
当人类说话时，手势有助于传达沟通意图，例如增加强调或描述概念。然而，目前的同步言语生成手势方法仅依赖于表面语言线索（如语音音频或文本转录），忽略了理解并利用支撑人类手势的交流意图。这导致生成的手势虽然与讲话节奏同步，但在语义上较为浅薄。为解决这一缺口，我们引入了**Intentional-Gesture**，这是一个将手势生成视为基于高层次沟通功能的目的推理任务的新颖框架。 首先，通过增加手势-目的标注（即总结意图的文本句子），我们将BEAT-2数据集扩展为**InG**数据集，并使用大型视觉语言模型自动进行这些目的标注。接下来，我们介绍了**Intentional Gesture Motion Tokenizer**来利用这些目的标注。该方法将高层次沟通功能（如意图）注入到标记化的运动表示中，从而实现既在时间上对齐又语义上有意义的手势合成，在BEAT-2基准测试上实现了新的最先进性能。 我们的框架为数字人类和具身人工智能中的表现力手势生成提供了一个模块化基础。项目页面：[此链接](this https URL)
URL
https://arxiv.org/abs/2505.15197
PDF
-
AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
2025-05-21 03:28:53Tianbao Zhang, Jian Zhao, Yuer Li, Zheng Zhu, Ping Hu, Zhaoxin Fan, Wenjun Wu, Xuelong LiAbstract
Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans and enhancing the capabilities of interactive virtual agents, with wide-ranging applications in virtual reality, digital entertainment, and remote communication. Existing approaches often generate audio-driven facial expressions and gestures independently, which introduces a significant limitation: the lack of seamless coordination between facial and gestural elements, resulting in less natural and cohesive animations. To address this limitation, we propose AsynFusion, a novel framework that leverages diffusion transformers to achieve harmonious expression and gesture synthesis. The proposed method is built upon a dual-branch DiT architecture, which enables the parallel generation of facial expressions and gestures. Within the model, we introduce a Cooperative Synchronization Module to facilitate bidirectional feature interaction between the two modalities, and an Asynchronous LCM Sampling strategy to reduce computational overhead while maintaining high-quality outputs. Extensive experiments demonstrate that AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations, consistently outperforming existing methods in both quantitative and qualitative evaluations.
Abstract (translated)
全身音频驱动的虚拟化身姿态和表情生成是创建逼真的数字人类并增强交互式虚拟代理能力的关键任务，其在虚拟现实、数字娱乐以及远程通信等领域有着广泛的应用。现有方法通常独立生成音频驱动的表情和手势，这带来了显著限制：面部与体态元素之间缺乏无缝协调，导致动画显得不自然且连贯性差。为解决这一问题，我们提出了AsynFusion框架，它利用扩散变换器实现和谐的表达和动作合成。该方法基于双分支DiT架构，能够在并行生成面部表情和手势的同时，通过引入合作同步模块促进两者之间双向特征交互，并采用异步LCM采样策略减少计算负担同时保持高质量输出。 实验结果表明，在实时同步全身动画生成方面，AsynFusion达到了目前的最佳性能，在定性和定量评估中均显著优于现有方法。
URL
https://arxiv.org/abs/2505.15058
PDF
-
Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign Language
2025-05-20 00:15:51Dinh Nam Pham, Eleftherios AvramidisAbstract
Sign Language Recognition (SLR) systems primarily focus on manual gestures, but non-manual features such as mouth movements, specifically mouthing, provide valuable linguistic information. This work directly classifies mouthing instances to their corresponding words in the spoken language while exploring the potential of transfer learning from Visual Speech Recognition (VSR) to mouthing recognition in German Sign Language. We leverage three VSR datasets: one in English, one in German with unrelated words and one in German containing the same target words as the mouthing dataset, to investigate the impact of task similarity in this setting. Our results demonstrate that multi-task learning improves both mouthing recognition and VSR accuracy as well as model robustness, suggesting that mouthing recognition should be treated as a distinct but related task to VSR. This research contributes to the field of SLR by proposing knowledge transfer from VSR to SLR datasets with limited mouthing annotations.
Abstract (translated)
手语识别（SLR）系统主要关注手动手势，但非手动特征如嘴部动作——尤其是口型——提供了有价值的语言信息。本研究直接将口型实例分类到对应的口语词汇中，并探索从视觉语音识别（VSR）向德国手语中的口型识别转移学习的潜力。我们利用三个VSR数据集：一个英文的，一个德文但包含不相关的词语，以及另一个德文且包含与口型数据集相同目标词的数据集，来研究该设置下的任务相似性影响。我们的结果表明，在这种情况下，多任务学习可以提高口型识别和VSR的准确性以及模型鲁棒性，这表明应该将口型识别视为与VSR相关但独立的任务。这项研究通过从VSR向具有有限口型注释的手语数据集进行知识转移，为SLR领域做出了贡献。
URL
https://arxiv.org/abs/2505.13784
PDF
-
From Grunts to Grammar: Emergent Language from Cooperative Foraging
2025-05-19 08:57:30Maytus Piriyajitakonkij, Rujikorn Charakorn, Weicheng Tao, Wei Pan, Mingfei Sun, Cheston Tan, Mengmi ZhangAbstract
Early cavemen relied on gestures, vocalizations, and simple signals to coordinate, plan, avoid predators, and share resources. Today, humans collaborate using complex languages to achieve remarkable results. What drives this evolution in communication? How does language emerge, adapt, and become vital for teamwork? Understanding the origins of language remains a challenge. A leading hypothesis in linguistics and anthropology posits that language evolved to meet the ecological and social demands of early human cooperation. Language did not arise in isolation, but through shared survival goals. Inspired by this view, we investigate the emergence of language in multi-agent Foraging Games. These environments are designed to reflect the cognitive and ecological constraints believed to have influenced the evolution of communication. Agents operate in a shared grid world with only partial knowledge about other agents and the environment, and must coordinate to complete games like picking up high-value targets or executing temporally ordered actions. Using end-to-end deep reinforcement learning, agents learn both actions and communication strategies from scratch. We find that agents develop communication protocols with hallmark features of natural language: arbitrariness, interchangeability, displacement, cultural transmission, and compositionality. We quantify each property and analyze how different factors, such as population size and temporal dependencies, shape specific aspects of the emergent language. Our framework serves as a platform for studying how language can evolve from partial observability, temporal reasoning, and cooperative goals in embodied multi-agent settings. We will release all data, code, and models publicly.
Abstract (translated)
早期的人类穴居人依靠手势、声音和简单的信号来协调行动、规划任务、避免捕食者以及共享资源。而今天，人类则使用复杂的语言来进行协作并取得显著成果。推动这种沟通演变的动力是什么？语言是如何产生、适应并在团队合作中变得至关重要呢？了解语言的起源仍然是一个挑战。语言学和人类学中的一个主流假设认为，语言是为了满足早期人类合作所面临的生态和社会需求而进化的。语言并非孤立地形成，而是通过共享生存目标共同发展起来的。 受这一观点启发，我们研究了多智能体觅食游戏中语言的出现。这些环境的设计旨在反映被认为是影响沟通进化的心智和生态约束条件。代理人在一个共享的网格世界中运作，仅对其他代理人及周围环境具有部分了解，并且必须通过协调来完成诸如拾取高价值目标或执行时间有序行动等游戏任务。 我们利用端到端深度强化学习方法让智能体从零开始学习动作策略和沟通策略。发现这些代理会发展出具备自然语言特征的通信协议：任意性、互换性、位移性、文化传播以及组合性。我们量化了每种属性，并分析不同因素，例如群体规模和时间依赖性如何影响新兴语言的具体方面。 我们的框架为研究如何在具有部分可观察性和合作目标的身体多智能体环境中进化出沟通提供了一个平台。我们将公开发布所有数据、代码及模型。
URL
https://arxiv.org/abs/2505.12872
PDF
-
Enhancing Mathematics Learning for Hard-of-Hearing Students Through Real-Time Palestinian Sign Language Recognition: A New Dataset
2025-05-16 19:14:25Fidaa khandaqji, Huthaifa I. Ashqar, Abdelrahem AtawnihAbstract
The study aims to enhance mathematics education accessibility for hard-of-hearing students by developing an accurate Palestinian sign language PSL recognition system using advanced artificial intelligence techniques. Due to the scarcity of digital resources for PSL, a custom dataset comprising 41 mathematical gesture classes was created, and recorded by PSL experts to ensure linguistic accuracy and domain specificity. To leverage state-of-the-art-computer vision techniques, a Vision Transformer ViTModel was fine-tuned for gesture classification. The model achieved an accuracy of 97.59%, demonstrating its effectiveness in recognizing mathematical signs with high precision and reliability. This study highlights the role of deep learning in developing intelligent educational tools that bridge the learning gap for hard-of-hearing students by providing AI-driven interactive solutions to enhance mathematical comprehension. This work represents a significant step toward innovative and inclusive frosting digital integration in specialized learning environments. The dataset is hosted on Hugging Face at this https URL.
Abstract (translated)
该研究旨在通过使用先进的人工智能技术开发一个准确的巴勒斯坦手语（PSL）识别系统，提高听力受损学生的数学教育可及性。由于缺乏数字资源，创建了一个包含41个数学手势类别的定制数据集，并由PSL专家录制以确保语言准确性与领域专属性。为了利用最先进的计算机视觉技术，对Vision Transformer (ViT) 模型进行了微调用于手势分类。该模型实现了97.59%的准确率，证明了其在识别数学符号时具有高精度和可靠性。本研究强调深度学习在开发智能教育工具中的作用，这些工具通过提供AI驱动的互动解决方案来缩小听力受损学生的学业差距，从而增强他们的数学理解能力。这项工作标志着向创新和包容性数字化整合专业学习环境迈出的重要一步。数据集托管于Hugging Face平台上的此链接：[请参见原文]。 注意：原始文本中的URL无法直接复制粘贴到翻译结果中，请访问原始文档获取具体链接地址。
URL
https://arxiv.org/abs/2505.17055
PDF
-
Maximizing Asynchronicity in Event-based Neural Networks
2025-05-16 12:07:50Haiqing Hao, Nikola Zubi\'c, Weihua He, Zhipeng Sui, Davide Scaramuzza, Wenhui WangAbstract
Event cameras deliver visual data with high temporal resolution, low latency, and minimal redundancy, yet their asynchronous, sparse sequential nature challenges standard tensor-based machine learning (ML). While the recent asynchronous-to-synchronous (A2S) paradigm aims to bridge this gap by asynchronously encoding events into learned representations for ML pipelines, existing A2S approaches often sacrifice representation expressivity and generalizability compared to dense, synchronous methods. This paper introduces EVA (EVent Asynchronous representation learning), a novel A2S framework to generate highly expressive and generalizable event-by-event representations. Inspired by the analogy between events and language, EVA uniquely adapts advances from language modeling in linear attention and self-supervised learning for its construction. In demonstration, EVA outperforms prior A2S methods on recognition tasks (DVS128-Gesture and N-Cars), and represents the first A2S framework to successfully master demanding detection tasks, achieving a remarkable 47.7 mAP on the Gen1 dataset. These results underscore EVA's transformative potential for advancing real-time event-based vision applications.
Abstract (translated)
事件相机提供具有高时间分辨率、低延迟和最小冗余的视觉数据，但它们异步且稀疏的特性给传统的基于张量的方法在机器学习（ML）中带来了挑战。尽管最近提出的异步到同步（A2S）范式旨在通过将事件异步编码为适合于机器学习流水线的学习表示来弥合这一差距，但现有的A2S方法通常牺牲了与密集、同步方法相比的表达能力和泛化能力。本文介绍了EVA（EVent Asynchronous 表示学习），这是一种新颖的A2S框架，用于生成高度表达和通用化的事件到事件表示。受事件与语言之间类比的启发，EVA独特地借鉴了线性注意力和自监督学习在语言建模中的进展来构建自身。实验表明，EVA在识别任务（DVS128-Gesture 和 N-Cars）上超越了先前的A2S方法，并且是首个成功掌握具有挑战性的检测任务的A2S框架，在Gen1数据集上达到了惊人的47.7 mAP。这些结果突显了EVA对实时事件基础视觉应用发展的变革潜力。
URL
https://arxiv.org/abs/2505.11165
PDF
-
NeoLightning: A Modern Reimagination of Gesture-Based Sound Design
2025-05-15 20:09:00Yonghyun Kim, Sangheon Park, Marcus Parker, Donghoon Seu, Alexandria SmithAbstract
This paper introduces NeoLightning, a modern reinterpretation of the Buchla Lightning. NeoLightning preserves the innovative spirit of Don Buchla's "Buchla Lightning" (introduced in the 1990s) while making its gesture-based interaction accessible to contemporary users. While the original Buchla Lightning and many other historical instruments were groundbreaking in their time, they are now largely unsupported, limiting user interaction to indirect experiences. To address this, NeoLightning leverages MediaPipe for deep learning-based gesture recognition and employs Max/MSP and Processing for real-time multimedia processing. The redesigned system offers precise, low-latency gesture recognition and immersive 3D interaction. By merging the creative spirit of the original Lightning with modern advancements, NeoLightning redefines gesture-based musical interaction, expanding possibilities for expressive performance and interactive sound design.
Abstract (translated)
本文介绍了NeoLightning，这是对Buchla Lightning的现代重新诠释。NeoLightning保留了唐·布查拉（Don Buchla）于上世纪90年代推出的"Buchla Lightning"创新精神的同时，使其基于手势的操作方式更适合当代用户使用。尽管原始的Buchla Lightning和其他许多历史乐器在其时代具有开创性意义，但由于目前缺乏支持，这些设备如今已限制了用户的直接互动体验。为解决这一问题，NeoLightning利用MediaPipe进行深度学习驱动的手势识别，并采用Max/MSP和Processing技术实现实时多媒体处理。重新设计的系统提供了精确且低延迟的手势识别功能以及沉浸式的3D交互体验。通过将原始闪电装置的创意精神与现代技术进步相结合，NeoLightning重新定义了基于手势的音乐互动方式，扩展了表演表现力及交互声音设计的可能性。
URL
https://arxiv.org/abs/2505.10686
PDF
-
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
2025-05-14 17:11:07Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou, Saining Xie, Silvio Savarese, Le Xue, Caiming Xiong, Ran XuAbstract
Unifying image understanding and generation has gained growing attention in recent research on multimodal models. Although design choices for image understanding have been extensively studied, the optimal model architecture and training recipe for a unified framework with image generation remain underexplored. Motivated by the strong potential of autoregressive and diffusion models for high-quality generation and scalability, we conduct a comprehensive study of their use in unified multimodal settings, with emphasis on image representations, modeling objectives, and training strategies. Grounded in these investigations, we introduce a novel approach that employs a diffusion transformer to generate semantically rich CLIP image features, in contrast to conventional VAE-based representations. This design yields both higher training efficiency and improved generative quality. Furthermore, we demonstrate that a sequential pretraining strategy for unified models-first training on image understanding and subsequently on image generation-offers practical advantages by preserving image understanding capability while developing strong image generation ability. Finally, we carefully curate a high-quality instruction-tuning dataset BLIP3o-60k for image generation by prompting GPT-4o with a diverse set of captions covering various scenes, objects, human gestures, and more. Building on our innovative model design, training recipe, and datasets, we develop BLIP3-o, a suite of state-of-the-art unified multimodal models. BLIP3-o achieves superior performance across most of the popular benchmarks spanning both image understanding and generation tasks. To facilitate future research, we fully open-source our models, including code, model weights, training scripts, and pretraining and instruction tuning datasets.
Abstract (translated)
将图像理解和生成统一起来在多模态模型的近期研究中获得了越来越多的关注。尽管对于图像理解的设计选择已经进行了广泛的研究，但针对集成图像生成的一体化框架的最佳模型架构和训练方案仍然有待探索。鉴于自回归和扩散模型在高质量生成和可扩展性方面具有强大的潜力，我们对这些模型在统一多模态设置中的使用进行了一项全面研究，并重点探讨了图像表示、建模目标以及训练策略。 基于这些调查结果，我们提出了一种新颖的方法，采用扩散变换器来生成语义丰富的CLIP图像特征，这与传统的VAE（变分自编码器）表示形成了鲜明对比。该设计不仅提高了训练效率，还提升了生成质量。此外，我们证明了统一模型的顺序预训练策略——首先针对图像理解进行训练，然后是图像生成——具有实际优势，在保持图像理解能力的同时培养强大的图像生成能力。 最后，为了促进高质量指令调优数据集BLIP3o-60k的创建，我们在一系列涵盖各种场景、物体、人体姿态等多样的描述基础上，使用GPT-4o模型进行了提示。基于我们的创新性模型设计、训练方案和数据集，我们开发了BLIP3-o，一套处于业界前沿的一体化多模态模型集合。 BLIP3-o在跨越图像理解和生成任务的大部分流行基准测试中均取得了卓越性能。为了支持未来的研究发展，我们全面开源了包括代码、模型权重、训练脚本以及预训练和指令调优数据集在内的所有资源。
URL
https://arxiv.org/abs/2505.09568
PDF
-
M3G: Multi-Granular Gesture Generator for Audio-Driven Full-Body Human Motion Synthesis
Abstract
Generating full-body human gestures encompassing face, body, hands, and global movements from audio is a valuable yet challenging task in virtual avatar creation. Previous systems focused on tokenizing the human gestures framewisely and predicting the tokens of each frame from the input audio. However, one observation is that the number of frames required for a complete expressive human gesture, defined as granularity, varies among different human gesture patterns. Existing systems fail to model these gesture patterns due to the fixed granularity of their gesture tokens. To solve this problem, we propose a novel framework named Multi-Granular Gesture Generator (M3G) for audio-driven holistic gesture generation. In M3G, we propose a novel Multi-Granular VQ-VAE (MGVQ-VAE) to tokenize motion patterns and reconstruct motion sequences from different temporal granularities. Subsequently, we proposed a multi-granular token predictor that extracts multi-granular information from audio and predicts the corresponding motion tokens. Then M3G reconstructs the human gestures from the predicted tokens using the MGVQ-VAE. Both objective and subjective experiments demonstrate that our proposed M3G framework outperforms the state-of-the-art methods in terms of generating natural and expressive full-body human gestures.
Abstract (translated)
从音频生成包括面部、身体和手部动作在内的全身人类姿态是一项在虚拟化身创建中既有价值又具挑战性的任务。以往的系统主要侧重于逐帧地将人体姿态进行标记，并根据输入的音频预测每帧的姿态标记。然而，一个值得注意的现象是，完成一个具有表现力的人体姿态所需的帧数（定义为粒度）因不同的姿态模式而异。现有的系统由于其固定化的姿态标记粒度无法建模这些多样的姿态模式。为了克服这个问题，我们提出了一种名为多重粒度手势生成器（M3G）的全新框架，用于基于音频驱动的整体手势生成。 在M3G中，我们提出了一个创新性的多重粒度矢量量化变分自编码器（MGVQ-VAE），该模型能够以不同的时间粒度来标记运动模式并重构运动序列。接着，我们设计了一种多粒度令牌预测器，它可以从音频中提取多种不同时间尺度的信息，并预测相应的动作令牌。然后，M3G利用MGVQ-VAE从预测的令牌重建人类姿态。 无论是客观测试还是主观评估都表明，我们的M3G框架在生成自然且富有表现力的整体人体姿势方面优于现有的最先进技术。
URL
https://arxiv.org/abs/2505.08293
PDF
-
DeepSORT-Driven Visual Tracking Approach for Gesture Recognition in Interactive Systems
2025-05-11 20:35:11Tong Zhang, Fenghua Shao, Runsheng Zhang, Yifan Zhuang, Liuqingqing YangAbstract
Based on the DeepSORT algorithm, this study explores the application of visual tracking technology in intelligent human-computer interaction, especially in the field of gesture recognition and tracking. With the rapid development of artificial intelligence and deep learning technology, visual-based interaction has gradually replaced traditional input devices and become an important way for intelligent systems to interact with users. The DeepSORT algorithm can achieve accurate target tracking in dynamic environments by combining Kalman filters and deep learning feature extraction methods. It is especially suitable for complex scenes with multi-target tracking and fast movements. This study experimentally verifies the superior performance of DeepSORT in gesture recognition and tracking. It can accurately capture and track the user's gesture trajectory and is superior to traditional tracking methods in terms of real-time and accuracy. In addition, this study also combines gesture recognition experiments to evaluate the recognition ability and feedback response of the DeepSORT algorithm under different gestures (such as sliding, clicking, and zooming). The experimental results show that DeepSORT can not only effectively deal with target occlusion and motion blur but also can stably track in a multi-target environment, achieving a smooth user interaction experience. Finally, this paper looks forward to the future development direction of intelligent human-computer interaction systems based on visual tracking and proposes future research focuses such as algorithm optimization, data fusion, and multimodal interaction in order to promote a more intelligent and personalized interactive experience. Keywords-DeepSORT, visual tracking, gesture recognition, human-computer interaction
Abstract (translated)
基于DeepSORT算法，本研究探讨了视觉跟踪技术在智能人机交互中的应用，特别是在手势识别和跟踪领域。随着人工智能和深度学习技术的迅速发展，基于视觉的互动逐渐取代传统输入设备，并成为智能系统与用户交流的重要方式。DeepSORT算法结合卡尔曼滤波器和深度学习特征提取方法，在动态环境中能够实现精准的目标追踪，尤其适用于复杂场景中的多目标追踪及快速移动情况。本研究通过实验验证了DeepSORT在手势识别和跟踪方面的优越性能：可以准确捕捉并跟踪用户的动作轨迹，并且在实时性和准确性方面优于传统的追踪方法。 此外，该研究还结合手势识别试验来评估不同手势（如滑动、点击、缩放等）下DeepSORT算法的识别能力和反馈响应。实验结果表明，DeepSORT不仅能有效处理目标遮挡和运动模糊问题，还能在多目标环境中稳定跟踪，从而实现流畅的人机交互体验。 最后，本文展望了基于视觉追踪的智能人机交互系统未来的发展方向，并提出诸如算法优化、数据融合及多模态互动等未来研究重点，以促进更加智能化和个人化的交互体验。关键词包括：DeepSORT、视觉跟踪、手势识别、人机交互。
URL
https://arxiv.org/abs/2505.07110
PDF
-
TSLFormer: A Lightweight Transformer Model for Turkish Sign Language Recognition Using Skeletal Landmarks
2025-05-11 14:30:56Kutay Ert\"urk, Furkan Alt{\i}n{\i}\c{s}{\i}k, \.Irem Sar{\i}alt{\i}n, \"Omer Nezih GerekAbstract
This study presents TSLFormer, a light and robust word-level Turkish Sign Language (TSL) recognition model that treats sign gestures as ordered, string-like language. Instead of using raw RGB or depth videos, our method only works with 3D joint positions - articulation points - extracted using Google's Mediapipe library, which focuses on the hand and torso skeletal locations. This creates efficient input dimensionality reduction while preserving important semantic gesture information. Our approach revisits sign language recognition as sequence-to-sequence translation, inspired by the linguistic nature of sign languages and the success of transformers in natural language processing. Since TSLFormer uses the self-attention mechanism, it effectively captures temporal co-occurrence within gesture sequences and highlights meaningful motion patterns as words unfold. Evaluated on the AUTSL dataset with over 36,000 samples and 227 different words, TSLFormer achieves competitive performance with minimal computational cost. These results show that joint-based input is sufficient for enabling real-time, mobile, and assistive communication systems for hearing-impaired individuals.
Abstract (translated)
本研究提出了TSLFormer，这是一种轻量且鲁棒的土耳其手语（TSL）单词级识别模型，将手势视为有序的语言字符串。与使用原始RGB或深度视频不同，我们的方法仅利用通过Google的Mediapipe库提取的手部和躯干骨骼位置的3D关节坐标作为输入。这在减少输入维度的同时保留了重要的语义手势信息。我们借鉴手语语言学性质及Transformer模型在自然语言处理中的成功经验，重新审视手语识别为序列到序列翻译问题。由于TSLFormer采用自注意力机制，它能够有效捕捉手势序列内的时间共现关系，并突出展示动作模式的含义。经过包含超过36,000个样本和227个不同单词的AUTSL数据集评估后，TSLFormer在计算成本最小化的情况下实现了竞争性的性能表现。这些结果表明基于关节输入足以支持听障人士所需的实时、便携及辅助通信系统。
URL
https://arxiv.org/abs/2505.07890
PDF
