98%
921
2 minutes
20
Advancements in deep learning have revolutionized numerous real-world applications, including image recognition, visual question answering, and image captioning. Among these, image captioning has emerged as a critical area of research, with substantial progress achieved in Arabic, Chinese, Uyghur, Hindi, and predominantly English. However, despite Urdu being a morphologically rich and widely spoken language, research in Urdu image captioning remains underexplored due to a lack of resources. This study creates a new Urdu Image Captioning Dataset (UCID) called UC-23-RY to fill in the gaps in Urdu image captioning. The Flickr30k dataset inspired the 159,816 Urdu captions in the dataset. Additionally, it suggests deep learning architectures designed especially for Urdu image captioning, including NASNetLarge-LSTM and ResNet-50-LSTM. The NASNetLarge-LSTM and ResNet-50-LSTM models achieved notable BLEU-1 scores of 0.86 and 0.84 respectively, as demonstrated through evaluation in this study accessing the model's impact on caption quality. Additionally, it provides useful datasets and shows how well-suited sophisticated deep learning models are for improving automatic Urdu image captioning.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12129323 | PMC |
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0320701 | PLOS |
IEEE Trans Pattern Anal Mach Intell
September 2025
Camouflaged Object Segmentation (COS) faces significant challenges due to the scarcity of annotated data, where meticulous pixel-level annotation is both labor-intensive and costly, primarily due to the intricate object-background boundaries. Addressing the core question, "Can COS be effectively achieved in a zero-shot manner without manual annotations for any camouflaged object?", we propose an affirmative solution. We analyze the learned attention patterns for camouflaged objects and introduce a robust zero-shot COS framework.
View Article and Find Full Text PDFSci Rep
August 2025
Computer Science Department, College of Computing and Informatics, Saudi Electronic University, 11673, Riyadh, Saudi Arabia.
With the rapid urban development and initiatives such as Saudi Vision 2030, efforts have been directed toward improving services and quality of life in Saudi cities. As a result, multiple environmental challenges have emerged, including visual pollution (VP), which significantly impacts the quality of life. Current approaches to these challenges rely on reporting through an online application managed by the Ministry of Municipalities and Housing, which is prone to errors due to manual data entry.
View Article and Find Full Text PDFNeural Netw
August 2025
National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, 610064, PR China; College of Computer Science, Sichuan University, Chengdu, 610065, PR China. Electronic address:
The primary goal of change captioning is to identify subtle visual differences between two similar images and express them in natural language. Existing research has been significantly influenced by the task of vision change detection and has mainly concentrated on the identification and description of visual changes. However, we contend that an effective change captioner should go beyond mere detection and description of what has changed.
View Article and Find Full Text PDFNat Mach Intell
August 2025
cerebrUM, Département de Psychologie, Université de Montréal, Montreal, Quebec Canada.
The human brain extracts complex information from visual inputs, including objects, their spatial and semantic interrelations, and their interactions with the environment. However, a quantitative approach for studying this information remains elusive. Here we test whether the contextual information encoded in large language models (LLMs) is beneficial for modelling the complex visual information extracted by the brain from natural scenes.
View Article and Find Full Text PDFIEEE Trans Image Process
January 2025
Video summarization aims to generate a compact summary of the original video by selecting and combining the most representative parts. Most existing approaches only focus on recognizing key video segments to generate the summary, which lacks holistic considerations. The transitions between selected video segments are usually abrupt and inconsistent, making the summary confusing.
View Article and Find Full Text PDF