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

• URL: http://arxiv.org/abs/2501.08446v1
• Date: Tue, 14 Jan 2025 21:34:34 GMT
• Title: Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion
• Authors: Cesare Davide Pace, Alessandro Marco De Nunzio, Claudio De Stefano, Francesco Fontanella, Mario Molinara,
• Abstract summary: Single-frame pose estimation has seen significant progress, but 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. Our approach achieves state-of-the-art performance on the PoseTrack21 and PoseTrack18 datasets, achieving mAP scores of 88.3 and 87.8, respectively.
• Score: 43.59385149982744
• License:
• 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.

Related papers

• Learning semantical dynamics and spatiotemporal collaboration for human pose estimation in video [3.2195139886901813]
  We present a novel framework that learns multi-level semantical dynamics and multi-frame human pose estimation. Specifically, we first design a multi-masked context and pose reconstruction strategy. This strategy stimulates the model to explore multi-temporal semantic relationships among frames by progressively masking the features of optical (patch) cubes and frames.
  arXiv  Detail & Related papers  (2025-02-15T00:35:34Z)
• Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation [52.36691633451968]
  ViTaM-D is a visual-tactile framework for dynamic hand-object interaction reconstruction. DF-Field is a distributed force-aware contact representation model. Our results highlight the superior performance of ViTaM-D in both rigid and deformable object reconstruction.
  arXiv  Detail & Related papers  (2024-11-14T16:29:45Z)
• Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling [67.94143911629143]
  We propose a generative Transformer VAE architecture to model hand pose and action. To faithfully model the semantic dependency and different temporal granularity of hand pose and action, we decompose the framework into two cascaded VAE blocks. Results show that our joint modeling of recognition and prediction improves over isolated solutions.
  arXiv  Detail & Related papers  (2023-11-29T05:28:39Z)
• DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation [16.32910684198013]
  We present DiffPose, a novel diffusion architecture that formulates video-based human pose estimation as a conditional heatmap generation problem. We show two unique characteristics from DiffPose on pose estimation task: (i) the ability to combine multiple sets of pose estimates to improve prediction accuracy, particularly for challenging joints, and (ii) the ability to adjust the number of iterative steps for feature refinement without retraining the model.
  arXiv  Detail & Related papers  (2023-07-31T14:00:23Z)
• Implicit Temporal Modeling with Learnable Alignment for Video Recognition [95.82093301212964]
  We propose a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H.
  arXiv  Detail & Related papers  (2023-04-20T17:11:01Z)
• Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes [25.712707161201802]
  Multi-frame methods improve monocular depth estimation over single-frame approaches. Recent methods tend to propose complex architectures for feature matching and dynamic scenes. We show that a simple learning framework, together with designed feature augmentation, leads to superior performance.
  arXiv  Detail & Related papers  (2023-03-26T05:26:30Z)
• Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video [16.32910684198013]
  We present a novel multi-frame human pose estimation framework, which employs temporal differences across frames to model dynamic contexts. To be specific, we design a multi-stage entangled learning sequences conditioned on multi-stage differences to derive informative motion representation sequences. These place us to rank No.1 in the Crowd Pose Estimation in Complex Events Challenge on benchmark HiEve.
  arXiv  Detail & Related papers  (2023-03-15T09:29:03Z)
• TimeLens: Event-based Video Frame Interpolation [54.28139783383213]
  We introduce Time Lens, a novel indicates equal contribution method that leverages the advantages of both synthesis-based and flow-based approaches. We show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods.
  arXiv  Detail & Related papers  (2021-06-14T10:33:47Z)
• Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions [12.900524511984798]
  We show a systematic design for how conventional networks and other forms of constraints can be incorporated into the attention framework. We achieve this by adapting temporal receptive field via a multi-scale structure of dilated convolutions. Our method achieves the state-of-the-art performance and outperforms existing methods by reducing the mean per joint position error to 33.4 mm on Human3.6M dataset.
  arXiv  Detail & Related papers  (2021-03-04T17:26:51Z)
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond [62.730497582218284]
  We develop a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data.
  arXiv  Detail & Related papers  (2020-04-30T03:23:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.