# T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations

arXiv: https://arxiv.org/abs/2610.05731 · HTML: https://mlsanity.com/paper/2610.05731/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Deep multi-scale video prediction beyond mean square error](https://mlsanity.com/paper/1511.05440/) (2015)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](https://mlsanity.com/paper/1902.06148/) (2019)
- [Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data](https://mlsanity.com/paper/2103.16607/) (2021)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Unsupervised Learning of Spatiotemporally Coherent Metrics](https://mlsanity.com/paper/1412.6056/) (2014)
- [No One Knows the State of the Art in Geospatial Foundation Models](https://mlsanity.com/paper/2605.12678/) (2026)
- [A2-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder](https://mlsanity.com/paper/2406.08079/) (2024)
- [SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing](https://mlsanity.com/paper/2412.19237/) (2024)
- [Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction](https://mlsanity.com/paper/2308.04589/) (2023)
- [NITP: Next Implicit Token Prediction for LLM Pre-training](https://mlsanity.com/paper/2605.24956/) (2026)

## Abstract (arXiv)

Earth observation (EO) data provide rich temporal supervision, yet existing remote sensing foundation models mainly exploit sequential observations through imposing predefined pairwise relations or aggregating holistic reconstruction context. We seek to further exploit the sparse and nonuniform temporal sampling inherent in EO sequences as supervisory signals. To this end, we propose T-JEPA, a temporal joint-embedding predictive architecture that learns time-gap-conditioned latent transitions. A shared single-frame encoder processes each observation, while a temporal predictor estimates the complete target latent field from a masked source latent representation and the actual elapsed time. Across multiple temporal intervals, these predictive constraints organize observed states into structured latent trajectories. Asymmetric metadata injection mitigates shortcut learning, and direct supervision across multiple temporal scales proves more effective than recursively rolling out intermediate states. In parallel, masked pixel reconstruction provides complementary supervision for preserving spatial details. Under matched pre-training data and throughput, T-JEPA achieves leading transfer performance on both static and temporal tasks. Analyses further reveal that T-JEPA learns representations with time-gap-dependent transition predictability and coherent latent dynamics, while maintaining strong cross-period consistency, representation diversity, and semantic discriminability.