arXiv Computer Vision

Evaluation of Vision-Language Models Across Diverse Coastal Environments

The paper introduces a densely labeled coastal dataset of over 1,000 images from Oahu, Hawaii, featuring 18 semantic classes and 7,400 annotated instances. Seven modern vision‑language models were evaluated using text‑to‑mask, mask‑to‑mask, and mask‑to‑text alignment experiments. Results show that broad landscape classes are recognized more accurately than conventional object and coastal classes, with coastal concepts posing the greatest challenge; however, performance differences are not solely due to environmental context, and alternative textual labels improve recognition of several coastal concepts.

arXiv AI

Oct 15

Exploring the Underwater World Segmentation without Extra Training

The paper introduces AquaOV255, a large-scale underwater segmentation dataset with 255 categories and over 20,000 images, and establishes the UOVSBench benchmark by combining it with five other datasets. It also presents Earth2Ocean, a training‑free open‑vocabulary segmentation framework that adapts terrestrial vision‑language models to underwater scenes using a Geometric‑guided Visual Mask Generator and a Category‑visual Semantic Alignment module. Experiments on UOVSBench show that Earth2Ocean significantly improves performance while keeping inference efficient.

By Bingyu Li, Tao Huo, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li

llms rag computer-vision multimodal benchmarks safety

arXiv AI

Oct 27

MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding

arXiv:2610.33478v1 Announce Type: cross Abstract: Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, i...

By Quang-Trung Truong, Thanh-Nghia Nguyen, Phu-Phong Vo, Jaeyeon Kim, Cheng Chen, Jie Zhang, Binh-Son Hua, Duc Thanh Nguyen, Ivor Tsang, Sai-Kit Yeung

llms nlp benchmarks

arXiv Computer Vision

Oct 22

AOV-GS: Active Open-Vocabulary Semantic Mapping with 3D Gaussian Splatting

AOV-GS is an active 3D Gaussian mapping system that uses frozen foundation models (SAM and CLIP) to guide exploration toward semantically informative regions. During coarse exploration, it re‑ranks geometrically promising views based on CLIP mask‑embedding novelty from SAM instance segmentation, biasing the robot’s trajectory. The system fits a lightweight scene‑specific language field offline to the collected CLIP embeddings, enabling open‑vocabulary text‑query segmentation on novel views and improving language‑field mIoU by 1.3–1.8 percentage points over geometry‑only planning on Replica and Matterport3D.

By Rodion Shkokov, Tatiana Zemskova, Dmitry Yudin

rag computer-vision robotics

arXiv Machine Learning

Jul 20

More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe

arXiv:2607. 15942v1 Announce Type: cross Abstract: Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks.

By Stefan Maria Ailuro (INSAIT, Sofia University "St. Kliment Ohridski"), Mario Markov (INSAIT, Sofia University "St. Kliment Ohridski"), Mohammad Mahdi (INSAIT, Sofia University "St. Kliment Ohridski"), Luc Van Gool (INSAIT, Sofia University "St. Kliment Ohridski"), Danda Pani Paudel (INSAIT, Sofia University "St. Kliment Ohridski")

llms computer-vision reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Oct 23

Data-Driven Vision-Language Models for Remote Sensing: A Survey

The paper surveys data-driven vision-language models (VLMs) for remote sensing (RS), highlighting a shift from model-centric to data-centric research. It reviews RS datasets designed for VLMs and offers a practical guide covering data construction, fine-tuning, and evaluation. The goal is to foster diverse, high-quality RS vision-language corpora that support broader AI development in the field.

By Yue Zhou, Shujun Zhao, Xue Yang, Ruigang Li, Tianwen Zhang, Mengcheng Lan, Chaofeng Chen, Lingfei Ma, Hongjie He, Jonathan Li

llms fine-tuning multimodal

arXiv Computer Vision

Aug 25

WADE: A Reasoning-Annotated Benchmark for Multi-Instance Floating-Waste Grounding with Compact Vision-Language Models

arXiv:2608.22950v1 Announce Type: new Abstract: Floating waste in inland waterways threatens aquatic ecosystems and requires timely monitoring under cluttered, multi-object conditions. Existing aquat...

By Md. Asaduzzaman Shuvo, Ahsan Farabi, Md. Abdul Ahad Minhaz, Mahedi Hasan, Israt Khandaker, Ibrahim Khalil Shanto, Muhammad Nomani Kabir

llms fine-tuning multimodal benchmarks safety

arXiv AI

Aug 11

GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views

arXiv:2608. 09270v1 Announce Type: cross Abstract: Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation.

By Jiahui Cui, Yan Zhao, Kan Wei, Enze Zhu, Peirong Zhang, Lei Wang, Yiru Wang

robotics multimodal benchmarks safety

Hugging Face Trending Papers

Oct 22

Data-Driven Vision-Language Models for Remote Sensing: A Survey

During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However, wit...

llms fine-tuning multimodal

arXiv Computer Vision

Oct 27

GeoPrompt: Geometry-Conditioned Prompt Learning for Underwater Open-Vocabulary Instance Segmentation

arXiv:2610.34190v1 Announce Type: new Abstract: Open-vocabulary instance segmentation (OVIS) provides a promising solution for marine perception by recognizing and segmenting categories beyond predef...

By Shanshan Han, Yuxi Wang, Can Qin, Yujie Chen, Cong Pan, Haitao Li, Guoqiang Zhong

rag computer-vision multimodal benchmarks safety

arXiv Computer Vision

Aug 28

UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-Localization

UniGeo is a multimodal large language model designed for text-guided drone geo‑localization, enabling the identification of target regions in large image galleries from natural‑language descriptions. It integrates geo‑semantic understanding, cross‑view semantic generation, and candidate‑level verification within a shared vision‑language framework, establishing stable correspondences among local scene elements, spatial relations, and language. A multi‑stage training strategy progressively refines geo‑semantic learning, cross‑view mapping, and fine‑grained verification, yielding significant performance gains on GeoText‑1652, with R@10 and mAP improvements of 13.59 and 2.83 percentage points respectively.

By Jiahao Wen, Hang Yu, Zhedong Zheng

llms robotics multimodal

arXiv Computer Vision

Sep 23

A Multimodal Large Language Model-Driven Framework for Context-Aware UAV Emergency Landing Site Selection

arXiv:2602.01163v2 Announce Type: replace Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, tempora...

By Chunliang Hua, Lei Zhang, Jiayang Sun, Chunlan Zeng, Xiao Hu

llms agents computer-vision multimodal benchmarks

arXiv AI

Jun 24

Listening makes Vision Clear for VLMs

arXiv:2606. 23763v1 Announce Type: cross Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens.

By Yiyang Chen, Yixin Tan, Binrui Shen

safety

Related stories