Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion

TL;DR

The paper introduces elsarticle.cls, a rewritten LaTeX document class optimized for Elsevier journal submissions and built on article.cls to minimize package conflicts and preserve kernel behavior. It details dependencies, front matter support, and versatile formatting options that accommodate various publication styles, including preprint and two-column layouts. It contrasts elsarticle.cls with the older elsart.cls, emphasizing improved compatibility, streamlined theorem environments, and integrated citation/hyperref features. Installation guidance directs users to Elsevier resources and CTAN, outlining steps to generate the class file and update the TeX database for local use.

Abstract

Human pose estimation, a vital task in computer vision, involves detecting and localising human joints in images and videos. While single-frame pose estimation has seen significant progress, it often fails to capture the temporal dynamics for understanding complex, continuous movements. We propose Poseidon, a novel multi-frame pose estimation architecture that extends the ViTPose model by integrating temporal information for enhanced accuracy and robustness to address these limitations. Poseidon introduces key innovations: (1) an Adaptive Frame Weighting (AFW) mechanism that dynamically prioritises frames based on their relevance, ensuring that the model focuses on the most informative data; (2) a Multi-Scale Feature Fusion (MSFF) module that aggregates features from different backbone layers to capture both fine-grained details and high-level semantics; and (3) a Cross-Attention module for effective information exchange between central and contextual frames, enhancing the model's temporal coherence. The proposed architecture improves performance in complex video scenarios and offers scalability and computational efficiency suitable for real-world applications. Our approach achieves state-of-the-art performance on the PoseTrack21 and PoseTrack18 datasets, achieving mAP scores of 88.3 and 87.8, respectively, outperforming existing methods.