Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.4
2.4
Journals
Data
Special Issues
Vision-Based AI in the Real World: Data, Robustness and Deployment
share announcement

Vision-Based AI in the Real World: Data, Robustness and Deployment

A Special Issue of Data (ISSN 2306-5729) belonging to the section "Information Systems and Data Management".

Deadline for manuscript submissions: 31 July 2027 | Viewed by 3210

Editors

Dr. Daqian Shi

E-Mail Website
Guest Editor
UCL Institute of Health Informatics, London, UK
Interests: machine learning; generative AI; multimodal AI; knowledge-enhanced AI; AI for healthcare; computer vision; digital health; health informatics
Prof. Dr. Wei Kong

E-Mail Website
Guest Editor
College of Information Engineering, Shanghai Maritime University, Shanghai, China
Interests: pattern recognition; bioinformatics; multi-omics data analysis; image genetics; multimodal brain imaging; neurodegenerative diseases; cancer analysis
Dr. Yuqi Ouyang

E-Mail Website
Guest Editor
College of Computer Science, Sichuan University, Chengdu 610207, China
Interests: computer vision; video analytics; medical imaging; multi-agent systems; open-world learning; concept drift
Dr. Haonan Zhao

E-Mail Website
Guest Editor Assistant
School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China
Interests: artificial intelligence; human–computer interaction; data mining; cognitive computing; machine learning

Special Issue Information

Dear Colleagues,

Recent advances in vision-based artificial intelligence have led to significant progress in visual recognition tasks under controlled settings. However, deploying these models in real-world environments remains challenging due to the complex, dynamic, and often imperfect nature of real-world data. Issues such as data heterogeneity, distribution shift, limited annotations, and long-tail scenarios can significantly degrade model performance outside laboratory conditions.

In response, there is a growing shift toward data-centric approaches, emphasizing the critical role of data quality, curation, and governance in building reliable vision systems. At the same time, robustness and generalization have become central concerns, requiring models that can adapt to unseen conditions and maintain performance across diverse environments. Furthermore, the practical deployment of vision-based AI systems raises additional challenges related to scalability, efficiency, and integration into real-world workflows.

This Special Issue aims to bring together recent advances at the intersection of data-centric AI, robust visual recognition, and real-world deployment. We welcome contributions addressing challenges such as dataset construction and curation, weak and noisy supervision, domain adaptation, multimodal data integration, and real-world evaluation protocols. Applications may span healthcare, industrial inspection, autonomous systems, and other real-world scenarios.

By focusing on the interplay between data, robustness, and deployment, this Special Issue seeks to bridge the gap between theoretical advances and practical, real-world vision systems.

Dr. Daqian Shi
Prof. Dr. Wei Kong
Dr. Yuqi Ouyang
Guest Editors

Dr. Haonan Zhao
Guest Editor Assistant

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Data is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • real-world vision AI
  • data-centric AI
  • robust visual recognition
  • domain generalization
  • out-of-distribution robustness
  • multimodal learning
  • trustworthy AI
  • foundation models
  • vision-language models
  • real-world deployment

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review, Other

31 pages, 87601 KB  
Article
Towards Robust Underwater Object Detection: UWOD Dataset and Transfer Learning Insights
by Nouf A. Alrowais, Anfal M. Alawajy, Nada A. Almugrem, Hadeel M. Aljami, Abdulaziz O. Alobaid, Masheal M. Alghamdi, Walaa A. Alsumari, Hassan R. Alqaeri, Aljwhara Almutairi, Remass Alsaeed, Royouf Alotaibi, Aghadir A. Jammah and Eman Bin Khunayn
Data 2026, 11(9), 236; https://doi.org/10.3390/data11090236 - 11 Sep 2026
Abstract
Underwater object detection faces significant challenges including uneven lighting, low contrast, and scattering-induced distortions. Existing underwater datasets are limited in scale, class diversity, and annotation consistency, which hinders robust model development. This work addresses these limitations by creating the UWOD dataset through the [...] Read more.
Underwater object detection faces significant challenges including uneven lighting, low contrast, and scattering-induced distortions. Existing underwater datasets are limited in scale, class diversity, and annotation consistency, which hinders robust model development. This work addresses these limitations by creating the UWOD dataset through the integration of seven publicly available underwater datasets, comprising over 107 K images with approximately 374 K annotations across 39 classes. We employ a semi-automatic annotation pipeline that combines manual labeling with iterative model-in-the-loop training to ensure high-quality ground truth, As a final verification step, all auto-generated labels were manually inspected and corrected as needed. We benchmark state-of-the-art object detectors—including YOLOv8, YOLOv7, YOLOv5, FCOS, EfficientDet, YOLOX, RT-DETR, SSD, and Faster R-CNN—establishing comprehensive performance baselines; YOLOv8 and YOLOv7 achieve the best accuracy–efficiency trade-off. Our transfer learning analysis shows that domain-specific pretraining substantially often outperforms pretraining on general-purpose datasets, yielding up to more than 50% improvement in low-data regimes versus training from scratch, with markedly lower seed-to-seed variance than scratch training. Sequential pretraining on COCO followed by UWOD achieves the strongest results on our most challenging dataset. Due to upstream licensing constraints, we release trained model weights and an automated annotation pipeline that encapsulate the learned underwater-domain knowledge, enabling immediate application to new imagery while respecting intellectual property. Full article
(This article belongs to the Special Issue Vision-Based AI in the Real World: Data, Robustness and Deployment)
27 pages, 11115 KB  
Article
Learning Adaptive Cross-Modal Interactions for Multimodal Sentiment Analysis
by Chuhan Cheng, Hangcheng Wu, Junqiao Wang and Yuqi Ouyang
Data 2026, 11(8), 209; https://doi.org/10.3390/data11080209 - 20 Aug 2026
Viewed by 353
Abstract
Multimodal sentiment analysis aims to integrate heterogeneous textual, visual, and acoustic information for effective emotion understanding. However, existing methods often suffer from insufficient cross-modal interaction modeling, limited adaptability in multimodal fusion, and inadequate suppression of modality-specific noise under complex conversational scenarios. To address [...] Read more.
Multimodal sentiment analysis aims to integrate heterogeneous textual, visual, and acoustic information for effective emotion understanding. However, existing methods often suffer from insufficient cross-modal interaction modeling, limited adaptability in multimodal fusion, and inadequate suppression of modality-specific noise under complex conversational scenarios. To address these challenges, this paper proposes a framework for learning adaptive cross-modal interactions for multimodal sentiment analysis. The proposed framework consists of three stages: modality-aware preprocessing, heterogeneous representation learning, and adaptive multimodal fusion. First, a unified preprocessing strategy is designed to improve cross-modal consistency through textual normalization, speaker-aware visual alignment, and utterance-level acoustic representation enhancement. Second, modality-specific encoders are constructed to capture complementary semantic, spatial, and utterance-level acoustic characteristics from textual, visual, and acoustic modalities, respectively. Third, an adaptive fusion framework is introduced to explicitly model cross-modal interactions, dynamically estimate the importance of different modality combinations, and further calibrate discriminative feature channels through channel attention. By jointly performing modality-level interaction learning and channel-wise feature refinement, the proposed framework effectively enhances multimodal representation capability for sentiment classification. Extensive experiments conducted on the CMU-MOSI and MELD benchmark datasets demonstrate that our framework consistently outperforms previous methods. In particular, the proposed model achieves 90.27% accuracy and 90.26% F1-score on CMU-MOSI, together with 66.57% accuracy and 66.21% F1-score on MELD. Additional ablation studies and qualitative analyses further validate the effectiveness of the proposed preprocessing strategy, modality-specific representation learning, and adaptive fusion mechanism. Full article
(This article belongs to the Special Issue Vision-Based AI in the Real World: Data, Robustness and Deployment)
►▼ Show Figures

Figure 1

19 pages, 4439 KB  
Article
An Algorithm for Fine-Grained Content Extraction and Understanding in Short Videos
by Yanqi Wan, Shuya Zhang, Yi Xu, Kunfang Zhang, Heyi Wang and Mingzheng Liu
Data 2026, 11(7), 179; https://doi.org/10.3390/data11070179 - 20 Jul 2026
Viewed by 620
Abstract
We integrated communication theory with advanced computer vision techniques to propose a novel approach for fine-grained content extraction from short videos. Unlike methods focused on summarization or subtitle generation for longer videos, our approach emphasizes extracting detailed content and understanding the intricate narrative [...] Read more.
We integrated communication theory with advanced computer vision techniques to propose a novel approach for fine-grained content extraction from short videos. Unlike methods focused on summarization or subtitle generation for longer videos, our approach emphasizes extracting detailed content and understanding the intricate narrative structure of short videos. By employing scene segmentation, similarity-based filtering algorithms, and support vector machines, the method identifies keyframes that capture precise visual details. Further, it generates semantically accurate textual descriptions using the mPLUG model, enabling an in-depth understanding of video content. Using a dataset of short videos from the cultural and tourism domain, we validated the proposed method. Experimental results demonstrate that our approach achieves high precision in identifying and understanding detailed visual elements, effectively bridging the gap between visual representation and semantic meaning. Additionally, the study explores the influence of different video content types, interference factors, and image description models on fine-grained content extraction, highlighting its potential for improving intelligent analysis of short-video data. Full article
(This article belongs to the Special Issue Vision-Based AI in the Real World: Data, Robustness and Deployment)
►▼ Show Figures

Figure 1

Review

Jump to: Research, Other

33 pages, 7164 KB  
Review
A Survey of Multi-Model Collaboration in Video Understanding
by Yi Chen, Jianwei Zhang, Lei Zhang, Chang Liu, Rui Gao, Zhixian Lu, Jun Qi and Qiyu Lei
Data 2026, 11(9), 230; https://doi.org/10.3390/data11090230 - 7 Sep 2026
Viewed by 162
Abstract
The rapid development of multimodal foundation models has shifted video understanding from perception-centered recognition toward more general semantic interpretation, reasoning, and decision-making over dynamic visual content. As video understanding tasks increasingly require fine-grained perception, long-range temporal modeling, multimodal grounding, and adaptive reasoning, collaboration [...] Read more.
The rapid development of multimodal foundation models has shifted video understanding from perception-centered recognition toward more general semantic interpretation, reasoning, and decision-making over dynamic visual content. As video understanding tasks increasingly require fine-grained perception, long-range temporal modeling, multimodal grounding, and adaptive reasoning, collaboration among heterogeneous functional units, including specialized models, modules, agents, memory systems, and external tools, has emerged as an important system-level paradigm. However, existing surveys mainly organize video understanding methods by architectures, learning strategies, or task categories, leaving the collaborative structure of modern systems insufficiently examined. This survey provides a structured narrative review of multi-model collaboration in video understanding, which we formulate as collaborative video understanding. We introduce a unified analytical framework that characterizes collaborative systems through functional units, inter-unit communication mechanisms, and collaborative state representations, and organize existing methods according to their coordination dynamics into static collaboration and dynamic collaboration, with the latter further distinguished into controller-based and agent-based collaboration. We further review representative benchmarks, evaluation metrics, and empirical analysis, showing that current evaluation protocols mainly capture task-level performance but provide limited insight into collaborative organization, memory use, adaptive execution, and system-level collaborative capability. Finally, we discuss key challenges and future directions, including adaptive task decomposition, semantically aligned inter-unit communication, persistent shared memory, uncertainty-aware error containment, evidence-grounded reasoning, and collaboration-centric evaluation. By reinterpreting video understanding from a collaborative systems perspective, this survey aims to provide a structured foundation for developing more adaptive, reliable, and scalable video understanding systems. Full article
(This article belongs to the Special Issue Vision-Based AI in the Real World: Data, Robustness and Deployment)
►▼ Show Figures

Figure 1

Other

Jump to: Research, Review

12 pages, 8317 KB  
Data Descriptor
RGB Image Dataset of White Maize Kernels with Visible Quality Defects for Computer Vision-Based Assessment of Mycotoxin Contamination Risk and Grain Quality
by Liston Kiwoli, Devotha Godfrey Nyambo, Bonny Mgawe, Neema Kassim and Mussa Ally
Data 2026, 11(7), 175; https://doi.org/10.3390/data11070175 - 13 Jul 2026
Viewed by 785
Abstract
Maize (Zea mays L.) is a major staple crop vulnerable to post-harvest deterioration caused by fungal infection and mycotoxin contamination. Visual defects such as discoloration, breakage, insect damage, and mold growth are commonly associated with reduced grain quality and increased contamination risk. [...] Read more.
Maize (Zea mays L.) is a major staple crop vulnerable to post-harvest deterioration caused by fungal infection and mycotoxin contamination. Visual defects such as discoloration, breakage, insect damage, and mold growth are commonly associated with reduced grain quality and increased contamination risk. This article presents a publicly available RGB image dataset of white maize kernels deposited in Harvard Dataverse for the development of computer vision models for automated grain quality assessment. The dataset contains 5143 high-resolution RGB images acquired using Samsung Galaxy A12 and Samsung Galaxy A54 smartphone cameras under semi-controlled imaging conditions. Images contain either single or multiple kernels and were annotated at the instance level using the YOLO format, resulting in 13,533 labeled kernel instances. Annotations were assigned by experts experienced in mycotoxin-related grain quality inspection. Labels are based solely on visual surface characteristics and do not represent direct chemical measurements of aflatoxins, fumonisins, or other mycotoxins. The dataset provides a practical resource for developing and evaluating machine learning models for maize kernel defect detection, quality screening, and risk-oriented grain inspection applications. Full article
(This article belongs to the Special Issue Vision-Based AI in the Real World: Data, Robustness and Deployment)
►▼ Show Figures

Graphical abstract

20 pages, 10249 KB  
Data Descriptor
UVInsDet: A Ground-Based Robotic Inspection Dataset for Insulator Detection and Instance Segmentation in High-Voltage Substations
by Alexandra I. Khalyasmaa, Pavel V. Matrenin and Irina F. Iumanova
Data 2026, 11(7), 171; https://doi.org/10.3390/data11070171 - 9 Jul 2026
Viewed by 748
Abstract
Existing publicly available datasets for insulator recognition primarily focus on overhead transmission lines and are commonly acquired using unmanned aerial vehicles. As a result, they often do not reflect the visual complexity of high-voltage substation environments, which are characterized by dense equipment arrangements, [...] Read more.
Existing publicly available datasets for insulator recognition primarily focus on overhead transmission lines and are commonly acquired using unmanned aerial vehicles. As a result, they often do not reflect the visual complexity of high-voltage substation environments, which are characterized by dense equipment arrangements, structured industrial backgrounds, frequent occlusions, and substantial variation in object scale. To address this gap, we present UVInsDet, a real-world dataset for insulator-string detection and instance segmentation collected during ground-based robotic inspections of an operational 220 kV substation. The dataset comprises 591 visible-spectrum RGB images acquired using a narrow-angle diagnostic inspection camera and contains 1415 manually annotated insulator-string instances represented by pixel-wise segmentation masks. The images cover daytime and nighttime conditions, varying weather scenarios, different viewing angles, and both target-object and negative samples corresponding to realistic inspection workflows. The dataset includes annotations for glass and porcelain insulator strings and provides data in both LabelMe and COCO formats. UVInsDet is intended as a specialized resource for computer vision research in industrial inspection environments. The dataset can support the development and evaluation of object detection and instance segmentation methods, studies of small-object recognition in complex scenes, robustness assessment under varying observation conditions, domain adaptation research, and the development of intelligent monitoring and inspection systems for power infrastructure. Full article
(This article belongs to the Special Issue Vision-Based AI in the Real World: Data, Robustness and Deployment)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop