BigMaQ: 一个连接图像和3D姿态表示的大型猕猴运动与动画数据集
BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations
AI总结：
BigMaQ数据集通过整合动态3D姿态-形状表示，提升动物动作识别的准确性，并提供丰富的资源用于非人类灵长类动物的研究。
摘要：
动态和社会行为识别在动物中的认识对于推进动物学、生态学、医学和神经科学至关重要。近年来深度学习的进步使从视频中自动识别行为成为可能，但准确重建三维（3D）姿态和形状尚未整合到这一过程中。特别是对于非人类灵长类动物，基于网格的跟踪努力落后于其他物种，导致姿态描述受限于稀疏的关键点，无法充分捕捉动作动态的丰富性。为了解决这一差距，我们引入了Big Maque Q 3D运动与动画数据集（BigMaQ），一个包含超过750个互动恒河猴场景的大型数据集，具有详细的3D姿态描述。在扩展先前基于表面的动物跟踪方法的基础上，我们通过适应高质量的猕猴模板网格到个体猴子，构建了具有纹理的主体特定虚拟角色。这使我们能够提供比先前最先进的基于表面的动物跟踪方法更准确的姿态描述。从原始数据集中，我们推导出BigMaQ500，一个动作识别基准，将基于表面的姿态向量与多个个体猴子的单帧链接。通过将从已建立的图像和视频编码器中提取的特征与有无我们的姿态描述器相结合，我们展示了在包含姿态信息时平均平均精度（mAP）有显著提高。通过这些贡献，BigMaQ建立了第一个既将动态3D姿态-形状表示整合到动物动作识别学习任务中，又为推进非人类灵长类动物的视觉外观、姿势和社会互动研究提供丰富资源的数据集。代码和数据可在https://martinivis.github.io/BigMaQ/ 上公开。
英文摘要：
The recognition of dynamic and social behavior in animals is fundamental for advancing ethology, ecology, medicine and neuroscience. Recent progress in deep learning has enabled automated behavior recognition from video, yet an accurate reconstruction of the three-dimensional (3D) pose and shape has not been integrated into this process. Especially for non-human primates, mesh-based tracking efforts lag behind those for other species, leaving pose descriptions restricted to sparse keypoints that are unable to fully capture the richness of action dynamics. To address this gap, we introduce the $\textbf{Big Ma}$ca$\textbf{Q}$ue 3D Motion and Animation Dataset ($\texttt{BigMaQ}$), a large-scale dataset comprising more than 750 scenes of interacting rhesus macaques with detailed 3D pose descriptions. Extending previous surface-based animal tracking methods, we construct subject-specific textured avatars by adapting a high-quality macaque template mesh to individual monkeys. This allows us to provide pose descriptions that are more accurate than previous state-of-the-art surface-based animal tracking methods. From the original dataset, we derive BigMaQ500, an action recognition benchmark that links surface-based pose vectors to single frames across multiple individual monkeys. By pairing features extracted from established image and video encoders with and without our pose descriptors, we demonstrate substantial improvements in mean average precision (mAP) when pose information is included. With these contributions, $\texttt{BigMaQ}$ establishes the first dataset that both integrates dynamic 3D pose-shape representations into the learning task of animal action recognition and provides a rich resource to advance the study of visual appearance, posture, and social interaction in non-human primates. The code and data are publicly available at https://martinivis.github.io/BigMaQ/ .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
