Related papers: SkeletonMAE: Spatial-Temporal Masked Autoencoders …
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…
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…
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…
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.…
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…
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,…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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,…
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…