Papers with Code 아카이브
Pose Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 3
- 보존된 평가 기록
- 16
Pose Tracking is the task of estimating multi-person human poses in videos and assigning unique instance IDs for each keypoint across frames. Accurate estimation of human keypoint-trajectories is useful for human action recognition, human interaction understanding, motion capture and animation.
Source: LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation
Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies
DeepGesture: A conversational gesture synthesis system based on emotions and semantics
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions
DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling
PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis
RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking
Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation
DanceChat: Large Language Model-Guided Music-to-Dance Generation
Fluoroscopic Shape and Pose Tracking of Catheters with Custom Radiopaque Markers
SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach
MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation
MotionPro: A Precise Motion Controller for Image-to-Video Generation
One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion
Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes
Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
Text-driven Motion Generation: Overview, Challenges and Directions
Dyadic Mamba: Long-term Dyadic Human Motion Synthesis
M3G: Multi-Granular Gesture Generator for Audio-Driven Full-Body Human Motion Synthesis
Comparison of Visual Trackers for Biomechanical Analysis of Running
Deterministic-to-Stochastic Diverse Latent Feature Mapping for Human Motion Synthesis
Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion
GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field
Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions
Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation
Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
Multi-person Physics-based Pose Estimation for Combat Sports
MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer
Embracing Dynamics: Dynamics-aware 4D Gaussian Splatting SLAM
DanceMosaic: High-Fidelity Dance Generation with Multimodal Editability
Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions
FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.