Image de couverture de livre

Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yuxuan, Chen, Yuming, Li, Yunheng, Cheng, Ming-Ming, Li, Xiang, Yang, Jian
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection
par: Li, Yuxuan, et autres
Publié: (2024)

Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection
par: Yuan, Xinbin, et autres
Publié: (2025)

LSKNet: A Foundation Lightweight Backbone for Remote Sensing
par: Li, Yuxuan, et autres
Publié: (2024)

Visual Instruction Pretraining for Domain-Specific Foundation Models
par: Li, Yuxuan, et autres
Publié: (2025)

Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
par: Li, Yunheng, et autres
Publié: (2024)

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
par: Li, Yunheng, et autres
Publié: (2024)

YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection
par: Chen, Yuming, et autres
Publié: (2023)

PR-MIM: Delving Deeper into Partial Reconstruction in Masked Image Modeling
par: Li, Zhong-Yu, et autres
Publié: (2024)

Zone Evaluation: Revealing Spatial Bias in Object Detection
par: Zheng, Zhaohui, et autres
Publié: (2023)

RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark
par: Zhang, Xin, et autres
Publié: (2025)

CrossKD: Cross-Head Knowledge Distillation for Object Detection
par: Wang, Jiabao, et autres
Publié: (2023)

From Pixels to Prose: Advancing Multi-Modal Language Models for Remote Sensing
par: Sun, Xintian, et autres
Publié: (2024)

SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
par: Guo, Xin, et autres
Publié: (2023)

Any2Any: Unified Arbitrary Modality Translation for Remote Sensing
par: Chen, Haoyang, et autres
Publié: (2026)

VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
par: Li, Xiang, et autres
Publié: (2024)

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment
par: Zhang, Shi-Chen, et autres
Publié: (2025)

Text-Guided Channel Perturbation and Pretrained Knowledge Integration for Unified Multi-Modality Image Fusion
par: Li, Xilai, et autres
Publié: (2025)

GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
par: Zhou, Yue, et autres
Publié: (2024)

OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation
par: Yin, Bo-Wen, et autres
Publié: (2025)

UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models
par: Li, Yujie, et autres
Publié: (2024)

High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
par: Zeng, Quan-Sheng, et autres
Publié: (2024)

Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models
par: Li, Xiaohe, et autres
Publié: (2026)

UniRoute: Unified Routing Mixture-of-Experts for Modality-Adaptive Remote Sensing Change Detection
par: Shu, Qingling, et autres
Publié: (2026)

Rethinking the Key Factors for the Generalization of Remote Sensing Stereo Matching Networks
par: Jiang, Liting, et autres
Publié: (2024)

DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
par: Ni, Kang, et autres
Publié: (2025)

DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing
par: Han, Shengdong, et autres
Publié: (2025)

Advancing Textual Prompt Learning with Anchored Attributes
par: Li, Zheng, et autres
Publié: (2024)

SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing
par: Zhang, Yingying, et autres
Publié: (2025)

WOW-Seg: A Word-free Open World Segmentation Model
par: Li, Danyang, et autres
Publié: (2026)

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
par: Zeng, Quan-Sheng, et autres
Publié: (2025)

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
par: Li, Yunheng, et autres
Publié: (2025)

Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model
par: Wen, Congcong, et autres
Publié: (2025)

u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model
par: Xu, Jinjin, et autres
Publié: (2023)

GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning
par: Li, Wenshuai, et autres
Publié: (2026)

A Unified Foundation Model for All-in-One Multi-Modal Remote Sensing Image Restoration and Fusion with Language Prompting
par: Cui, Yongchuan, et autres
Publié: (2026)

Lightweight Change Detection in Heterogeneous Remote Sensing Images with Online All-Integer Pruning Training
par: Zhang, Chengyang, et autres
Publié: (2024)

SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
par: Li, Yuxuan, et autres
Publié: (2024)

Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation
par: Liu, Chenying, et autres
Publié: (2024)

Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder
par: Peng, Bowen, et autres
Publié: (2026)

DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images
par: Dai, Yimian, et autres
Publié: (2024)