From Coordinates to Candidate Regions: Temporal Change Localization via Region Selection in Remote Sensing Multimodal LLMs

• URL: http://arxiv.org/abs/2609.08391v1
• Date: Tue, 08 Sep 2026 07:59:21 GMT
• Title: From Coordinates to Candidate Regions: Temporal Change Localization via Region Selection in Remote Sensing Multimodal LLMs
• Abstract summary: multimodal large language models (RS-MLLMs) have advanced scene understanding and visual question answering over satellite imagery.<n>We present an RS-specific formulation of the region selection paradigm, previously explored in natural-image MLLMs.<n>Our framework employs a text-conditioned region proposal module, encodes each candidate as special tokens carrying per-frame visual features enriched with spatial and temporal cues.
• Score: 48.93485452013392
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Remote sensing multimodal large language models (RS-MLLMs) have advanced scene understanding and visual question answering over satellite imagery, yet localizing specific objects or changed regions remains challenging. Existing approaches rely on generating bounding box coordinates as token sequences, which is fragile for the small, densely packed objects common in remote sensing and increasingly error-prone when multiple targets must be localized simultaneously. In this work, we present an RS-specific formulation of the region selection paradigm, previously explored in natural-image MLLMs, and extend it to temporal change localization over multi-image sequences. Our framework employs a text-conditioned region proposal module, encodes each candidate as special tokens carrying per-frame visual features enriched with spatial and temporal cues, and lets the LLM localize targets by selecting region tokens in its response. We construct a multi-task training and evaluation suite spanning localization, referring expression, visual grounding, and understanding tasks across single-image and multi-temporal settings. Experiments show that our approach substantially outperforms coordinate-generation baselines on temporal change localization, while improving single-image visual grounding and maintaining competitive understanding performance. Oracle analysis decomposes the contributions of the region proposer and the LLM selector, providing diagnostic insight unique to this framework. Our code will be available at https://github.com/juwan-kr/RS-RegionSelect.

Related papers

• PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle [31.234013315817858]
  PixVL is a self-supervised post-training framework for pixel-level multimodal large language models.<n>It generates and self-verify regional descriptions and learn from unlabeled data.<n> Experiments demonstrate that PixVL improves both region understanding and segmentation task.
  arXiv  Detail & Related papers  (2026-08-02T16:13:52Z)
• One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting [51.09550363815034]
  Scene text spotting requires high-precision alignment between textual recognition and spatial localization.<n>We propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token.<n>We show that SPaTS consistently and significantly outperforms both frontier closed-source MLLMs and OCR MLLMs.
  arXiv  Detail & Related papers  (2026-07-30T09:17:48Z)
• Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO [43.173161414861966]
  Cycle Group Relative Policy Optimization (CycleGRPO) jointly optimize region understanding and localization for Multimodal Large Language Models (MLLMs)<n>A single MLLM first acts as the actor to generate region captions, then immediately transitions to a critic to ground its generated text back in the spatial domain.<n>A quality-aware token-level cycle-consistency reward is employed to assess the semantic discriminability of text captions.
  arXiv  Detail & Related papers  (2026-07-13T14:00:57Z)
• VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models [33.748083718525756]
  Text-to-point-cloud (T2P) localization aims to infer precise spatial positions within 3D point cloud maps from natural language descriptions.<n>We propose VLM-Loc, a framework that leverages the spatial reasoning capability of large vision-language models.<n>Experiments on CityLoc demonstrate VLM-Loc achieves superior accuracy and robustness compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-10T15:48:25Z)
• GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning [8.819428500071007]
  Vision-language pretraining models have made significant progress in bridging remote sensing imagery with natural language.<n>We propose GeoAlignCLIP, a unified framework that achieves fine-grained alignment in remote sensing tasks.<n>We construct RSFG-100k, a fine-granular remote sensing dataset containing scene descriptions, region-level annotations, and challenging hard-negative samples.
  arXiv  Detail & Related papers  (2026-03-10T12:12:11Z)
• Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought [55.65577137924979]
  We propose a framework that enables MLLMs to reason over images using continuous numerical coordinates.<n> NV-CoT expands the MLLM action space from discrete vocabulary tokens to a continuous Euclidean space.<n>Experiments on three benchmarks demonstrate that NV-CoT significantly improves localization precision and final answer accuracy.
  arXiv  Detail & Related papers  (2026-02-27T12:04:07Z)
• GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing [50.961694646995376]
  We propose a parameter-efficient fine-tuning (PEFT) strategy called Guided Region-Aware Sparse Prompting (GRASP)<n>GRASP introduces spatially structured soft prompts associated with spatial blocks extracted from a frozen visual token grid.<n>Experiments on multiple RSVQA benchmarks show that GRASP achieves competitive performance compared to existing fine-tuning and prompt-based methods.
  arXiv  Detail & Related papers  (2026-01-23T10:12:59Z)
• Teaching VLMs to Localize Specific Objects from In-context Examples [56.797110842152]
  We find that present-day Vision-Language Models (VLMs) lack a fundamental cognitive ability: learning to localize specific objects in a scene by taking into account the context.<n>This work is the first to explore and benchmark personalized few-shot localization for VLMs.
  arXiv  Detail & Related papers  (2024-11-20T13:34:22Z)
• R-MAE: Regions Meet Masked Autoencoders [113.73147144125385]
  We explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked region autoencoding to learn from groups of pixels or regions.
  arXiv  Detail & Related papers  (2023-06-08T17:56:46Z)
• Progressive Localization Networks for Language-based Moment Localization [56.54450664871467]
  This paper focuses on the task of language-based moment localization. Most existing methods prefer to first sample sufficient candidate moments with various temporal lengths, and then match them with the given query to determine the target moment. We propose a novel multi-stage Progressive localization Network (PLN) which progressively localizes the target moment in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2021-02-02T03:45:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.