The paper introduces STAND, a method for remote sensing image change captioning that tackles ambiguities in viewpoint, scale, and prior knowledge. It employs a semantic anchoring constraint to regularize temporal representations, a dual‑granularity disambiguation module that uses global context and frequency‑refocused attention to resolve spatial uncertainties, and a semantic concept anchoring module that leverages language priors during decoding. Experiments demonstrate that STAND outperforms existing approaches and effectively addresses these ambiguities.
Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe perf...
The paper introduces VPRef, the first cross‑domain benchmark for Referring Remote Sensing Image Segmentation, containing 46,972 language‑image‑annotation triplets with a three‑tier linguistic hierarchy. It proposes a parameter‑efficient adaptation method based on the Segment Anything Model and Low‑Rank Adaptation, using pseudo‑label self‑training for visual drift and random multi‑granularity prompt mixing for textual drift. Experiments show the approach improves cross‑domain segmentation while altering only 1.08 % of the base model’s parameters, offering a strong baseline for future research.
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
arXiv:2604. 20623v2 Announce Type: replace-cross Abstract: Traditional change detection identifies where changes occur, but does not explain what changed in natural language.
arXiv:2609.18139v1 Announce Type: new Abstract: Cross-view object geo-localization (CVOGL) locates a target in satellite imagery using drone or street-view queries. Existing methods train separate de...
Cross-view object geo-localization (CVOGL) locates a target in satellite imagery using drone or street-view queries. Existing methods train separate detectors for each viewpoint, leading to parameter...
EventVL introduces the first generative event-based multimodal large language model (MLLM) designed for explicit semantic understanding of event streams. The framework leverages a newly annotated dataset of nearly 1.4 million event–image/video–text pairs and incorporates an Event Spatiotemporal Representation to capture comprehensive event information, along with Dynamic Semantic Alignment to refine sparse semantic spaces. Experiments demonstrate that EventVL outperforms existing MLLM baselines in event captioning and scene description generation tasks, advancing the field of event vision.
arXiv:2606. 28724v1 Announce Type: cross Abstract: Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing.
arXiv:2608. 01856v2 Announce Type: replace Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions.
arXiv:2411. 19758v2 Announce Type: replace-cross Abstract: Remote sensing change detection based on a map reference and an up-to-date image boosts timely observation of the Earth's surface when earlier images are lacking for comparison.
arXiv:2605.17949v2 Announce Type: replace Abstract: Remote sensing vision-language models (RS-VLMs) commonly employ a pretrained vision encoder and a projection module to map image features into the...
arXiv:2606. 00987v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored.