# Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery

arXiv: https://arxiv.org/abs/2404.01571 · HTML: https://mlsanity.com/paper/2404.01571/

## Key facts

- Cited by 3 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 21 of its 33 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## 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, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts](https://mlsanity.com/paper/2311.09127/) (2023)
- [Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection](https://mlsanity.com/paper/1706.03038/) (2017)
- [SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images](https://mlsanity.com/paper/2107.01548/) (2021)
- [Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones](https://mlsanity.com/paper/2311.15033/) (2023)
- [YOLO -- You only look 10647 times](https://mlsanity.com/paper/2201.06159/) (2022)

## Built on by (most cited first, 3 of 3)

- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation](https://mlsanity.com/paper/2505.15928/) (2025)
- [Edge-Optimized Multimodal Learning for UAV Video Understanding via BLIP-2](https://mlsanity.com/paper/2601.08408/) (2026)

## Abstract (arXiv)

In this article, we explore the potential of zero-shot Large Multimodal Models (LMMs) in the domain of drone perception. We focus on person detection and action recognition tasks and evaluate two prominent LMMs, namely YOLO-World and GPT-4V(ision) using a publicly available dataset captured from aerial views. Traditional deep learning approaches rely heavily on large and high-quality training datasets. However, in certain robotic settings, acquiring such datasets can be resource-intensive or impractical within a reasonable timeframe. The flexibility of prompt-based Large Multimodal Models (LMMs) and their exceptional generalization capabilities have the potential to revolutionize robotics applications in these scenarios. Our findings suggest that YOLO-World demonstrates good detection performance. GPT-4V struggles with accurately classifying action classes but delivers promising results in filtering out unwanted region proposals and in providing a general description of the scenery. This research represents an initial step in leveraging LMMs for drone perception and establishes a foundation for future investigations in this area.