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.
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns
LEAD: Latent Realignment for Human Motion Diffusion
Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling
ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras
OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
Versatile Motion Language Models for Multi-Turn Interactive Agents
Towards a GENEA Leaderboard -- an Extended, Living Benchmark for Evaluating and Advancing Conversational Motion Synthesis
DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control
Attainable Force Approximation and Full-Pose Tracking Control of an Over-Actuated Thrust-Vectoring Modular Team UAV
Real-time Diverse Motion In-betweening with Space-time Control
GS-EVT: Cross-Modal Event Camera Tracking based on Gaussian Splatting
Unimotion: Unifying 3D Human Motion Synthesis and Understanding
Whole-body End-Effector Pose Tracking
V-Hands: Touchscreen-based Hand Tracking for Remote Whiteboard Interaction
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation
LawDNet: Enhanced Audio-Driven Lip Synthesis via Local Affine Warping Deformation
Decoupling Contact for Fine-Grained Motion Style Transfer
Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformers
MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds
InterTrack: Tracking Human Object Interaction without Object Templates
T3M: Text Guided 3D Human Motion Synthesis from Speech
Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models
TextIM: Part-aware Interactive Motion Synthesis from Text
MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls
Scalable Group Choreography via Variational Phase Manifold Learning
Keypoint Promptable Re-Identification
Length-Aware Motion Synthesis via Latent Diffusion
Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation
SRPose: Two-view Relative Pose Estimation with Sparse Keypoints
Infinite Motion: Extended Motion Generation via Long Text Instructions
SeamPose: Repurposing Seams as Capacitive Sensors in a Shirt for Upper-Body Pose Tracking
FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models
Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.