Related papers: MultiMAE Meets Earth Observation: Pre-training Mul…
Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…
The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal…
Compared to 2D data, the scale of point cloud data in different domains available for training, is quite limited. Researchers have been trying to combine these data of different domains for masked autoencoder (MAE) pre-training to leverage…
Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…
Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. Typically, this approach involves randomly masking patches…
We present EmbodiedMAE, a unified 3D multi-modal representation for robot manipulation. Current approaches suffer from significant domain gaps between training datasets and robot manipulation tasks, while also lacking model architectures…
The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through…
Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this…
Earth Observation (EO) analysis is inherently interactive: resolving uncertainty often requires expanding the region of interest, retrieving historical observations, and switching across sensors such as optical and Synthetic Aperture Radar.…
Predicting the future of surrounding agents and accordingly planning a safe, goal-directed trajectory are crucial for automated vehicles. Current methods typically rely on imitation learning to optimize metrics against the ground truth,…
This work presents SSL4EO-S12 v1.1, a multimodal, multitemporal Earth Observation dataset designed for pretraining large-scale foundation models. Building on the success of SSL4EO-S12, this extension updates the previous version to fix…
Large-scale foundation models in Earth Observation can learn versatile, label-efficient representations by leveraging massive amounts of unlabeled data. However, existing public datasets are often limited in scale, geographic coverage, or…
We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…
Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data. While…
There is an increasing number of real-world problems in computer vision and machine learning requiring to take into consideration multiple interpretation layers (modalities or views) of the world and learn how they relate to each other. For…
This work proposes a unified self-supervised pre-training framework for transferable multi-modal perception representation learning via masked multi-modal reconstruction in Neural Radiance Field (NeRF), namely NeRF-Supervised Masked…
Multiview systems have become a key technology in modern computer vision, offering advanced capabilities in scene understanding and analysis. However, these systems face critical challenges in bandwidth limitations and computational…
Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…
Earth observation (EO) data spans a wide range of spatial, spectral, and temporal resolutions, from high-resolution optical imagery to low resolution multispectral products or radar time series. While recent foundation models have improved…
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised…