https://github.com/chakkritte/eeea-net
공식 코드EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.
A common benchmark for this task is MPII Human Pose
<span style="color:grey; opacity: 0.6">( Image credit: Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses
Spatio-temporal Vision Transformer for Super-resolution Microscopy
Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation
Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization
OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting
Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis
HybridPose: 6D Object Pose Estimation under Hybrid Representations
DeblurSR: Event-Based Motion Deblurring Under the Spiking Representation
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation
iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
EgoVSR: Towards High-Quality Egocentric Video Super-Resolution
Render-and-Compare: Cross-View 6 DoF Localization from Noisy Prior
Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
FocalPose++: Focal Length and Object Pose Estimation via Render and Compare
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation
On the Generalization of BasicVSR++ to Video Deblurring and Denoising
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.