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.
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text
Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior
Improving Multi-Person Pose Tracking with A Confidence Network
Controllable Group Choreography using Contrastive Diffusion
HumanTOMATO: Text-aligned Whole-body Motion Generation
Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey
On the Benefit of Generative Foundation Models for Human Activity Recognition
Unified speech and gesture synthesis using flow matching
Point-Based Radiance Fields for Controllable Human Motion Synthesis
UniQuadric: A SLAM Backend for Unknown Rigid Object 3D Tracking and Light-Weight Modeling
Object Motion Guided Human Motion Synthesis
DROP: Dynamics Responses from Human Motion Prior and Projective Dynamics
For A More Comprehensive Evaluation of 6DoF Object Pose Tracking
Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation
Broadband Ground Motion Synthesis via Generative Adversarial Neural Operators: Development and Validation
MCM: Multi-condition Motion Synthesis Framework for Multi-scenario
DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion
AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism
InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor
Motion In-Betweening with Phase Manifolds
ROAM: Robust and Object-Aware Motion Generation Using Neural Pose Descriptors
Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia
Language-guided Human Motion Synthesis with Atomic Actions
A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis
TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting
NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis
M3Act: Learning from Synthetic Human Group Activities
GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
Motion Capture Dataset for Practical Use of AI-based Motion Editing and Stylization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.