paper-with-me

홈 › Papers

Explicit Spatiotemporal Joint Relation Learning for Tracking Human Pose

2018-11-17 · Xiao Sun, Chuankang Li, Stephen Lin

We present a method for human pose tracking that is based on learning spatiotemporal relationships among joints. Beyond generating the heatmap of a joint in a given frame, our system also learns to predict the offset of the joint from a neighboring joint in the frame. Additionally, it is trained to predict the displacement of the joint from its position in the previous frame, in a manner that can account for possibly changing joint appearance, unlike optical flow. These relational cues in the spatial domain and temporal domain are inferred in a robust manner by attending only to relevant areas in the video frames. By explicitly learning and exploiting these joint relationships, our system achieves state-of-the-art performance on standard benchmarks for various pose tracking tasks including 3D body pose tracking in RGB video, 3D hand pose tracking in depth sequences, and 3D hand gesture tracking in RGB video.

📄 PDF Abstract BibTeX arXiv:1811.07123

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow EstimationPose EstimationPose TrackingPositionRelation

Methods 이 논문이 사용한 방법론

Heatmap 설명 없음

Similar Papers 제목 키워드 기반

Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction

2022-04-04 · Jiajun Fu, Fuxing Yang, Yonghao Dang, Xiaoli Liu 외

Human motion prediction is challenging due to the complex spatiotemporal feature modeling. Among all methods, graph convolution networks (GCNs) are extensively utilized because of their superiority in explicit connection…

Human motion predictionmotion prediction

Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

2023-08-17 · ICCV 2023 1 · Xiaozheng Zheng, Zhuo Su, Chao Wen, Zhou Xue 외

To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-time body tracking with only the head-mo…

ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation

2025-01-01 · CVPR 2025 1 · Ling-An Zeng, Guohong Huang, Yi-Lin Wei, Shengbo Gu 외

We propose ChainHOI, a novel approach for text-driven human-object interaction (HOI) generation that explicitly models interactions at both the joint and kinetic chain levels. Unlike existing methods that implicit…

Human-Object Interaction DetectionHuman-Object Interaction Generation

Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow

2026-02-15 · Shenhan Qian, Ganlin Zhang, Shangzhe Wu, Daniel Cremers arxiv

Reconstructing and tracking dynamic 3D scenes is a fundamental challenge in computer vision. Existing methods typically decouple geometry from motion: static multi-view reconstruction systems assume a rigid world, wherea…

Camera Pose EstimationScene Understanding

GRAE-3DMOT: Geometry Relation-Aware Encoder for Online 3D Multi-Object Tracking

2025-01-01 · CVPR 2025 1 · Hyunseop Kim, Hyo-Jun Lee, Yonguk Lee, Jinu Lee 외

Recently, 3D multi-object tracking (MOT) has widely adopted the standard tracking-by-detection paradigm, which solves the association problem between detections and tracks. Many tracking-by-detection approaches estab…

3D Multi-Object TrackingMulti-Object TrackingObject TrackingRelation