VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised performance on HumanML3D.
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of OpenPose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.
verdicts
UNVERDICTED 9representative citing papers
Introduces ZSSLR problem and ASL-Text dataset; uses text embeddings with 3D-CNN and bi-LSTM video features for zero-shot sign recognition.
Human pose similarity matching with spatial verification outperforms standard content-based image retrieval for discovering composition transfers in art on a manually annotated dataset.
A pipeline using OpenPose keypoints and DTW-1NN classifies gestures in RGB videos with flexibility to add new classes via few examples.
A single-GPU pipeline extracts OpenPose skeletons and Gaze-LLE attention, discards frames, and uses QwQ-32B zero-shot to produce classroom attention summaries and heatmaps, with preliminary evidence of limited spatial reasoning.
A framework for real-time ergonomic pose prediction from 3D volumetric video that trains personalized classifiers on user-labeled poses captured by RGB-D cameras.
An applied system combines quantized YOLOX detection, A2J pose estimation, and a CNN classifier on an AMD Kria K26 SOM with a RealSense D455 camera, reporting component accuracies of 74%, 84.13%, and 75.85% and throughput up to 4.5 FPS.
Applies established seq2seq neural networks to convert text to Spanish sign language for humanoid robot TEO, proposing OpenPose for skeleton data collection to handle sequence length differences and non-manual markers.
Cello Evaluator is a real-time postural feedback system for cellists running on current Android phones via on-device computer vision, validated as user-friendly by experts.
citing papers explorer
-
VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised performance on HumanML3D.
-
Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?
Introduces ZSSLR problem and ASL-Text dataset; uses text embeddings with 3D-CNN and bi-LSTM video features for zero-shot sign recognition.
-
Linking Art through Human Poses
Human pose similarity matching with spatial verification outperforms standard content-based image retrieval for discovering composition transfers in art on a manually annotated dataset.
-
Gesture Recognition in RGB Videos UsingHuman Body Keypoints and Dynamic Time Warping
A pipeline using OpenPose keypoints and DTW-1NN classifies gestures in RGB videos with flexibility to add new classes via few examples.
-
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
A single-GPU pipeline extracts OpenPose skeletons and Gaze-LLE attention, discards frames, and uses QwQ-32B zero-shot to produce classroom attention summaries and heatmaps, with preliminary evidence of limited spatial reasoning.
-
A Machine Learning Framework for Real-Time Personalized Ergonomic Pose Analysis
A framework for real-time ergonomic pose prediction from 3D volumetric video that trains personalized classifiers on user-labeled poses captured by RGB-D cameras.
-
Stereo Vision-Based Fall Prediction and Detection using Human Pose Estimation on the AMD Kria K26 SOM
An applied system combines quantized YOLOX detection, A2J pose estimation, and a CNN classifier on an AMD Kria K26 SOM with a RealSense D455 camera, reporting component accuracies of 74%, 84.13%, and 75.85% and throughput up to 4.5 FPS.
-
Sequence-to-Sequence Natural Language to Humanoid Robot Sign Language
Applies established seq2seq neural networks to convert text to Spanish sign language for humanoid robot TEO, proposing OpenPose for skeleton data collection to handle sequence length differences and non-manual markers.
-
Real-Time Cellist Postural Evaluation With On-Device Computer Vision
Cello Evaluator is a real-time postural feedback system for cellists running on current Android phones via on-device computer vision, validated as user-friendly by experts.