Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rajiv, Manjunath Prasad Holenarasipura, Vidyavathi, B. M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917049174851584
author Rajiv, Manjunath Prasad Holenarasipura
Vidyavathi, B. M.
author_facet Rajiv, Manjunath Prasad Holenarasipura
Vidyavathi, B. M.
contents Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work proposes a vision-language integration framework that unifies pre-trained visual encoders (e.g., CLIP, ViT) and large language models (e.g., GPT-based architectures) to achieve semantic alignment between visual and textual modalities. The goal is to enable robust zero-shot comprehension of scenes by leveraging natural language as a bridge to generalize over unseen categories and contexts. Our approach develops a unified model that embeds visual inputs and textual prompts into a shared space, followed by multimodal fusion and reasoning layers for contextual interpretation. Experiments on Visual Genome, COCO, ADE20K, and custom real-world datasets demonstrate significant gains over state-of-the-art zero-shot models in object recognition, activity detection, and scene captioning. The proposed system achieves up to 18% improvement in top-1 accuracy and notable gains in semantic coherence metrics, highlighting the effectiveness of cross-modal alignment and language grounding in enhancing generalization for real-world scene understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25070
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments
Rajiv, Manjunath Prasad Holenarasipura
Vidyavathi, B. M.
Computer Vision and Pattern Recognition
Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work proposes a vision-language integration framework that unifies pre-trained visual encoders (e.g., CLIP, ViT) and large language models (e.g., GPT-based architectures) to achieve semantic alignment between visual and textual modalities. The goal is to enable robust zero-shot comprehension of scenes by leveraging natural language as a bridge to generalize over unseen categories and contexts. Our approach develops a unified model that embeds visual inputs and textual prompts into a shared space, followed by multimodal fusion and reasoning layers for contextual interpretation. Experiments on Visual Genome, COCO, ADE20K, and custom real-world datasets demonstrate significant gains over state-of-the-art zero-shot models in object recognition, activity detection, and scene captioning. The proposed system achieves up to 18% improvement in top-1 accuracy and notable gains in semantic coherence metrics, highlighting the effectiveness of cross-modal alignment and language grounding in enhancing generalization for real-world scene understanding.
title Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.25070