SOTAVerified

Category-Agnostic Pose Estimation

Category-Agnostic Pose Estimation (CAPE) aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–15 of 15 papers

TitleStatusHype
A Graph-Based Approach for Category-Agnostic Pose EstimationCode2
Pose for Everything: Towards Category-Agnostic Pose EstimationCode2
Prototypical Networks for Few-shot LearningCode2
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose EstimationCode1
Edge Weight Prediction For Category-Agnostic Pose EstimationCode1
CapeX: Category-Agnostic Pose Estimation from Textual Point ExplanationCode1
Meta-Point Learning and Refining for Category-Agnostic Pose EstimationCode1
Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose EstimationCode1
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksCode1
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models—0
SCAPE: A Simple and Strong Category-Agnostic Pose EstimatorCode0
Category-Agnostic Pose Estimation for Point Clouds—0
ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose EstimationCode0
Dynamic Support Information Mining for Category-Agnostic Pose Estimation—0
Revisiting Fine-tuning for Few-shot Learning—0
Show:102550

No leaderboard results yet.