English
Related papers

Related papers: SkeletonMAE: Spatial-Temporal Masked Autoencoders …

200 papers

Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning (masking ratio, patch size, encoder/decoder layers) when…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Anthony Bisulco , Rahul Ramesh , Randall Balestriero , Pratik Chaudhari

Despite its practical importance across a wide range of modalities, recent advances in self-supervised learning (SSL) have been primarily focused on a few well-curated domains, e.g., vision and language, often relying on their…

Machine Learning · Computer Science 2023-10-26 Huiwon Jang , Jihoon Tack , Daewon Choi , Jongheon Jeong , Jinwoo Shin

Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal scenarios. However, their direct application to 3D human…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Siyuan Yang , Jun Liu , Hao Cheng , Chong Wang , Shijian Lu , Hedvig Kjellstrom , Weisi Lin , Alex C. Kot

This paper studies a conceptually simple extension of Masked Autoencoders (MAE) to spatiotemporal representation learning from videos. We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Christoph Feichtenhofer , Haoqi Fan , Yanghao Li , Kaiming He

We approached the goal of applying meta-learning to self-supervised masked autoencoders for spatiotemporal learning in three steps. Broadly, we seek to understand the impact of applying meta-learning to existing state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Faraz Waseem , Pratyush Muthukumar

Masked image modeling (MIM) is a highly popular and effective self-supervised learning method for image understanding. Existing MIM-based methods mostly focus on spatial feature modeling, neglecting spectral feature modeling. Meanwhile,…

Image and Video Processing · Electrical Eng. & Systems 2023-11-09 Junyan Lin , Feng Gao , Xiaocheng Shi , Junyu Dong , Qian Du

Unsupervised visual anomaly detection conveys practical significance in many scenarios and is a challenging task due to the unbounded definition of anomalies. Moreover, most previous methods are application-specific, and establishing a…

Computer Vision and Pattern Recognition · Computer Science 2022-11-02 Haiming Yao , Xue Wang , Wenyong Yu

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to exploit masked autoencoding for learning 3D representations…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Renrui Zhang , Ziyu Guo , Rongyao Fang , Bin Zhao , Dong Wang , Yu Qiao , Hongsheng Li , Peng Gao

Action recognition from well-segmented 3D skeleton video has been intensively studied. However, due to the difficulty in representing the 3D skeleton video and the lack of training data, action detection from streaming 3D skeleton video…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 Bo Li , Huahui Chen , Yucheng Chen , Yuchao Dai , Mingyi He

Wearable accelerometers are widely used for continuous monitoring of physical activity. Supervised machine learning and deep learning algorithms have long been used to extract meaningful activity information from raw accelerometry data, but…

Signal Processing · Electrical Eng. & Systems 2025-05-28 Niels R. Lorenzen , Poul J. Jennum , Emmanuel Mignot , Andreas Brink-Kjaer

Current state-of-the-art methods for skeleton-based temporal action segmentation are predominantly supervised and require annotated data, which is expensive to collect. In contrast, existing unsupervised temporal action segmentation methods…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Uzay Gökay , Federico Spurio , Dominik R. Bach , Juergen Gall

Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primarily focused on aligning visual and semantic representations…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Wenhan Wu , Zhishuai Guo , Chen Chen , Hongfei Xue , Aidong Lu

Distributed fiber-optic acoustic sensing (DAS) has emerged as a transformative approach for distributed vibration measurement with high spatial resolution and long measurement range while maintaining cost-efficiency. However, the…

Signal Processing · Electrical Eng. & Systems 2025-12-15 Junyi Duan , Jiageng Chen , Zuyuan He

Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users' privacy concerns, high labeling costs, or lack of expertise. However, current Federated…

Machine Learning · Computer Science 2023-03-22 Nan Yang , Xuanyu Chen , Charles Z. Liu , Dong Yuan , Wei Bao , Lizhen Cui

Generating semantic segmentation datasets has consistently been laborious and time-consuming, particularly in the context of large models or specialized domains(i.e. Medical Imaging or Remote Sensing). Specifically, large models necessitate…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Jiaru Jia , Mingzhe Liu , Jiake Xie , Xin Chen , Hong Zhang , Feixiang Zhao , Aiqing Yang

Affective video facial analysis (AVFA) has emerged as a key research field for building emotion-aware intelligent systems, yet this field continues to suffer from limited data availability. In recent years, the self-supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Xuecheng Wu , Junxiao Xue , Xinyi Yin , Yunyun Shi , Liangyu Fu , Danlei Huang , Yifan Wang , Jia Zhang , Jiayu Nie , Jun Wang

Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Arafat Rahman , Shashwat Kumar , Laura E. Barnes , Anuj Srivastava

Multivariate Time Series forecasting has been an increasingly popular topic in various applications and scenarios. Recently, contrastive learning and Transformer-based models have achieved good performance in many long-term series…

Machine Learning · Computer Science 2023-01-24 Zhe Li , Zhongwen Rao , Lujia Pan , Pengyun Wang , Zenglin Xu

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Renaud Vandeghen , Fida Mohammad Thoker , Marc Van Droogenbroeck , Bernard Ghanem

Recent advances in the masked autoencoder (MAE) paradigm have significantly propelled self-supervised skeleton-based action recognition. However, most existing approaches limit reconstruction targets to raw joint coordinates or their simple…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Shengkai Sun , Zefan Zhang , Jianfeng Dong , Zhiyong Cheng , Xiaojun Chang , Meng Wang