arXiv Computer Vision
CAPE-JEPA - Cross-modal Adversarial Probabilistic Embedding JEPA
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 25
OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding
OptiSAR-Net++ introduces a new cross‑domain remote sensing visual grounding task (CD‑RSVG) and the first large‑scale benchmark dataset, OptSAR‑RSVG. The framework replaces Transformer decoding with a CLIP‑based contrastive approach, employing a patch‑level Low‑Rank Adaptation Mixture of Experts for efficient cross‑domain feature decoupling and a text‑guided dual‑gate fusion module for improved semantic‑visual alignment. Experiments show state‑of‑the‑art performance on OptSAR‑RSVG and DIOR‑RSVG, with notable gains in localization accuracy and computational efficiency.
arXiv AI
Jun 10
Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks
arXiv:2606. 10819v1 Announce Type: cross Abstract: RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery.
arXiv AI
Aug 11
SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery
arXiv:2510. 22665v4 Announce Type: replace-cross Abstract: Synthetic Aperture Radar (SAR) is a critical imaging modality due to its all-weather operational capability.
arXiv Computer Vision
Sep 7
MEOX: Compact Multimodal Mixture-of-Experts for Earth Observation
MEOX is a compact multimodal masked autoencoder designed for Earth Observation that uses a 2.939 million‑parameter encoder and 3.115 million total parameters. It incorporates sensor‑specific adapters, explicit validity signals, and a shared sparse‑expert block to maintain modality‑dependent processing before a learned patch‑wise fusion, followed by fourteen encoder blocks that process a single spatial sequence with four metadata tokens. Pretrained on 1.228 million MMEarth64 samples, MEOX achieves strong performance on GEO‑Bench tasks, surpassing prior CSMoE results, and demonstrates effective sensor‑flexible representation learning with a modest parameter budget.
arXiv Machine Learning
Sep 10
Cross-modal learning for SAR target recognition using optical vision foundation models
The paper proposes a cross‑modal framework that uses a frozen DINOv3 optical vision foundation model to create class‑level prototypes for Synthetic Aperture Radar (SAR) target recognition. By aligning SAR embeddings to these optical prototypes, the SAR model learns to classify SAR images without needing paired optical data. Experiments on the UNICORNv2 dataset show that this prototype alignment improves SAR classification accuracy compared to baseline methods and yields clearer class separation in the embedding space.
arXiv AI
Oct 1
Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking
The paper introduces TSDA-Track, a Template-Search Domain Adaptation framework designed to reduce modality gaps in cross‑modal visual object tracking. Two variants are explored: Pre‑AFA TSDA‑Track uses adversarial alignment before transformer interaction, while Enc‑CFA TSDA‑Track applies contrastive alignment after interaction to strengthen cross‑modal correspondence. Experiments on datasets such as LasHeR, RGBT234, GTOT, and Anti‑UAV‑024 show that both variants outperform state‑of‑the‑art trackers, with Pre‑AFA achieving an SR/PR of 43.2/56.0 on RGBT234 under the modality‑switch protocol.