# RSVideo: Are Your Vision-Language Models Ready for Remote Sensing Videos?

arXiv: https://arxiv.org/abs/2608.02039 · HTML: https://mlsanity.com/paper/2608.02039/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 18 of 18)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes](https://mlsanity.com/paper/2502.00392/) (2025)
- [UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models](https://mlsanity.com/paper/2412.20742/) (2024)
- [VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing](https://mlsanity.com/paper/2602.07045/) (2026)
- [Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence](https://mlsanity.com/paper/2607.12477/) (2026)
- [UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding](https://mlsanity.com/paper/2603.14336/) (2026)
- [Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation](https://mlsanity.com/paper/2604.05377/) (2026)
- [VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning](https://mlsanity.com/paper/2603.25021/) (2026)
- [Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models](https://mlsanity.com/paper/2605.01662/) (2026)
- [UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs](https://mlsanity.com/paper/2605.12237/) (2026)

## Built on by (most cited first, 1 of 1)

- [ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answering](https://mlsanity.com/paper/2609.35507/) (2026)

## Abstract (arXiv)

Remote-sensing videos enable real-time observation of changes in target attributes, short-term activities, and scene evolution. They record motion, actions, interactions, and scene changes that cannot be captured by isolated images. Existing models primarily target single images or discrete temporal observations spanning a long time range. However, a unified evaluation setting for assessing vision-language models on continuous remote-sensing video understanding remains lacking. We introduce RSVideo-10K, a remote-sensing video dataset comprising 10,773 instances, 1.47 million frames, and 17.02 hours of footage, containing both unmanned aerial vehicles and satellite platforms. Its fixed evaluation benchmark, RSVideo-Bench, contains 2,731 test instances and evaluates two complementary aspects of remote-sensing video understanding: L1 Perception and L2 Reasoning, spanning seven capability groups and 17 tasks. Evaluations show that current vision-language models still struggle to recover small local evidence, track short-lived states, and use scene-constrained spatial relations. Based on this analysis, we further propose RSVideo, a reinforcement learning framework for small-target spatiotemporal focusing that selects question-relevant regions across frames and suppresses redundant background tokens. RSVideo achieves a maximum absolute improvement of 9.01% with InternVL3.5-14B and attains the highest accuracy of 40.63% with Qwen3.6-27B across 26 open-source vision-language backbones. Codes will be available at https://github.com/HongjieZhou0329/RSVideo.