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.
Self-Correcting Self-Consuming Loops for Generative Model Training
Constrained Synthesis with Projected Diffusion Models
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition
Active Generation Network of Human Skeleton for Action Recognition
Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering
Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation
Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker
GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation
Inter-X: Towards Versatile Human-Human Interaction Analysis
APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond
PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments
MACS: Mass Conditioned 3D Hand and Object Motion Synthesis
FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision
EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mapping
MotionScript: Natural Language Descriptions for Expressive 3D Human Motions
Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model
Deep Event Visual Odometry
Motion Flow Matching for Human Motion Synthesis and Editing
BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
Scalable Motion Style Transfer with Constrained Diffusion Generation
HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models
Digital Life Project: Autonomous 3D Characters with Social Intelligence
MMM: Generative Masked Motion Model
EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
AAMDM: Accelerated Auto-regressive Motion Diffusion Model
Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications
OmniMotionGPT: Animal Motion Generation with Limited Data
MoMask: Generative Masked Modeling of 3D Human Motions
AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond
A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis
ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.