HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions-Reference-Cited by-同舟云学术

HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Shah Anshul¹,Roy Aniket¹,Shah Ketul¹,Mishra Shlok²,Jacobs David²,Cherian Anoop³,Chellappa Rama¹

Affiliation:

1. Johns Hopkins University

2. University of Maryland,College Park

3. MERL

Funder

National Science Foundation

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10203218.pdf?arnumber=10203218

Reference61 articles.

1. Revisiting Skeleton-based Action Recognition

2. mixup: Beyond empirical risk minimization;zhang;ArXiv Preprint,2017

3. MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection

4. Cutmix: Regu-larization strategy to train strong classifiers with localizable features;yun;Proceedings of the IEEEICVF International Conference on Computer Vision,2019

5. Robust contrastive learning using negative samples with diminished semantics;ge;Advances in neural information processing systems,2021

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. LANDER: Visual Analysis of Activity and Uncertainty in Surveillance Video;IEEE Transactions on Human-Machine Systems;2024-08

2. Representation modeling learning with multi-domain decoupling for unsupervised skeleton-based action recognition;Neurocomputing;2024-05

3. Hallucination Improves the Performance of Unsupervised Visual Representation Learning;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01