mlsanityData to 13 Oct 2026

Motion-R3: Fast and Accurate Motion Annotation via Representation-based Representativeness Ranking

arXiv 2304.01672 ↗First posted 4 Apr 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we follow a data-centric philosophy and propose a novel motion annotation method based on the inherent representativeness of motion data in a given dataset. Specifically, we propose a Representation-based Representativeness Ranking R3 method that ranks all motion data in a given dataset according to their representativeness in a learned motion representation space. We further propose a novel dual-level motion constrastive learning method to learn the motion representation space in a more informative way. Thanks to its high efficiency, our method is particularly responsive to frequent requirements change and enables agile development of motion annotation models. Experimental results on the HDM05 dataset against state-of-the-art methods demonstrate the superiority of our method.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 27 of its 67 references that are in the map. First posted on arXiv 4 Apr 2023.

Builds on

27 of 67 references.

References · 27

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,492
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,860
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,850
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,285
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,841
  9. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,378
  10. 2019Contrastive Multiview Codingcited by 1,297
  11. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,129
  12. 2016Colorful Image Colorizationcited by 1,114
15 more
  1. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,009
  2. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 263
  3. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  4. 20213D Human Action Representation Learning via Cross-View Consistency Pursuitcited by 105
  5. 2020MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognitioncited by 92
  6. 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 89
  7. 2020Spatial Temporal Transformer Network for Skeleton-based Action Recognitioncited by 76
  8. 2021Skeleton-Contrastive 3D Action Representation Learningcited by 76
  9. 2016Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networkscited by 63
  10. 2017Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networkscited by 62
  11. 2020Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognitioncited by 59
  12. 2016Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networkscited by 28
  13. 2018Human Activity Recognition using Recurrent Neural Networkscited by 10
  14. 2022Bootstrapped Representation Learning for Skeleton-Based Action Recognitioncited by 8
  15. 2016Learning Multi-level Features For Sensor-based Human Action Recognitioncited by 2

Built on by

Not cited yet.