Review of large vision models and visual prompt engineering

Wang, Jiaqi; Liu, Zhengliang; Zhao, Lin; Wu, Zihao; Ma, Chong; Yu, Sigang; Dai, Haixing; Yang, Qiushi; Liu, Yiheng; Zhang, Songyao; Shi, Enze; Pan, Yi; Zhang, Tuo; Zhu, Dajiang; Li, Xiang; Jiang, Xi; Ge, Bao; Yuan, Yixuan; Shen, Dinggang; Liu, Tianming; Zhang, Shu

doi:10.1016/j.metrad.2023.100047

Cited by 50 publications

(6 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, it was observed that ChatGPT 3.5 did not change its answers according to the question, could not determine the upper and lower limits in a question involving inequality, and made a mistake in converting a verbal expression into an algebraic expression in another question. This is in line with the findings of another study that some of the participants had concerns about the accuracy and reliability of ChatGPT as it may provide incorrect or incomplete solutions to mathematical problems (Wu & Yu, 2023). Another study revealed that the majority of participants affirmed ChatGPT's commitment to providing precise and beneficial responses to users' enquiries.…”

Section: Conclusion and Recommendationssupporting

confidence: 86%

“…Also, it is important to note that prompt engineering is crucial in enabling ChatGPT to display its full potential. To do so, an open and purposeful dialogue is required with human guidance, as the system's abilities can be enhanced when provided with appropriate clues (Bozkurt et al, 2023;Short et al, 2023;Wang et al, 2023). As a matter of fact, in recent years, it is known that ChatGPT is able to interpret and contextualize the prompt when formulating a structured review question, creating relevance criteria and scanning the topics according to the level of relevance (Qureshi et al, 2023).…”

Section: Conclusion and Recommendationsmentioning

confidence: 99%

See 1 more Smart Citation

An artificial intelligence application in mathematics education: Evaluating ChatGPT’s academic achievement in a mathematics exam

Korkmaz Guler,

Dertli,

Boran

et al. 2024

PEDAGOGICAL RES

View full text Add to dashboard Cite

The aim of the research is to investigate the academic achievement of ChatGPT, an artificial intelligence based chatbot, in a national mathematics exam. For this purpose, 3.5 and 4 versions of ChatGPT were asked mathematics questions in a national exam. The method of the research is a case study. In the research, 3.5 and 4 versions of ChatGPT were used as data collection tools. The answers given by both versions of ChatGPT were analyzed separately by three researchers. As a result of the analysis of the data, it was found that ChatGPT-4 was more successful in the exam compared to ChatGPT-3,5 version, was better at understanding the questions asked, understood the instructions better and included more details in the question solution, and at the same time, both versions made common and different mistakes. According to the findings of the study, it was concluded that ChatGPT sometimes worked very well, sometimes only worked well and sometimes failed. In the light of the findings of the study, it can be suggested to use ChatGPT versions in mathematics education to obtain basic information and to get supervised help.

show abstract

Section: Conclusion and Recommendationssupporting

confidence: 86%

Section: Conclusion and Recommendationsmentioning

confidence: 99%

An artificial intelligence application in mathematics education: Evaluating ChatGPT’s academic achievement in a mathematics exam

Korkmaz Guler,

Dertli,

Boran

et al. 2024

PEDAGOGICAL RES

View full text Add to dashboard Cite

show abstract

“…In addition, the segmentation of dyed chickens consistently exhibited superior performance across all algorithms when compared to undyed chickens. This can be attributed to the distinct colors of the dyed chickens, which provide a more discernible feature for the model to track, thereby reducing identity switches and enhancing tracking accuracy [ 32 ]. This nuanced capability of TAM to adeptly manage variations in object features further solidifies its position as a versatile and reliable model for chicken tracking applications.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Methods for Tracking the Locomotion of Individual Chickens

Yang,

Bist,

Paneru

et al. 2024

Animals

View full text Add to dashboard Cite

Poultry locomotion is an important indicator of animal health, welfare, and productivity. Traditional methodologies such as manual observation or the use of wearable devices encounter significant challenges, including potential stress induction and behavioral alteration in animals. This research introduced an innovative approach that employs an enhanced track anything model (TAM) to track chickens in various experimental settings for locomotion analysis. Utilizing a dataset comprising both dyed and undyed broilers and layers, the TAM model was adapted and rigorously evaluated for its capability in non-intrusively tracking and analyzing poultry movement by intersection over union (mIoU) and the root mean square error (RMSE). The findings underscore TAM’s superior segmentation and tracking capabilities, particularly its exemplary performance against other state-of-the-art models, such as YOLO (you only look once) models of YOLOv5 and YOLOv8, and its high mIoU values (93.12%) across diverse chicken categories. Moreover, the model demonstrated notable accuracy in speed detection, as evidenced by an RMSE value of 0.02 m/s, offering a technologically advanced, consistent, and non-intrusive method for tracking and estimating the locomotion speed of chickens. This research not only substantiates TAM as a potent tool for detailed poultry behavior analysis and monitoring but also illuminates its potential applicability in broader livestock monitoring scenarios, thereby contributing to the enhancement of animal welfare and management in poultry farming through automated, non-intrusive monitoring and analysis.

show abstract

“…Prompt engineering focuses on the skill of designing and creating effective prompts that guide ChatGPT to produce the best possible output for your task. We followed existing literature [ 8 - 11 ] combined with our expertise and experimentation to provide a framework that yields the best result when developing a digital solution like PAMS ( Figure 1 ).…”

Section: Methodsmentioning

confidence: 99%

Leveraging Generative AI Tools to Support the Development of Digital Solutions in Health Care Research: Case Study

Rodriguez,

Lawrence,

Gonzalez

et al. 2024

JMIR Hum Factors

View full text Add to dashboard Cite

Background Generative artificial intelligence has the potential to revolutionize health technology product development by improving coding quality, efficiency, documentation, quality assessment and review, and troubleshooting. Objective This paper explores the application of a commercially available generative artificial intelligence tool (ChatGPT) to the development of a digital health behavior change intervention designed to support patient engagement in a commercial digital diabetes prevention program. Methods We examined the capacity, advantages, and limitations of ChatGPT to support digital product idea conceptualization, intervention content development, and the software engineering process, including software requirement generation, software design, and code production. In total, 11 evaluators, each with at least 10 years of experience in fields of study ranging from medicine and implementation science to computer science, participated in the output review process (ChatGPT vs human-generated output). All had familiarity or prior exposure to the original personalized automatic messaging system intervention. The evaluators rated the ChatGPT-produced outputs in terms of understandability, usability, novelty, relevance, completeness, and efficiency. Results Most metrics received positive scores. We identified that ChatGPT can (1) support developers to achieve high-quality products faster and (2) facilitate nontechnical communication and system understanding between technical and nontechnical team members around the development goal of rapid and easy-to-build computational solutions for medical technologies. Conclusions ChatGPT can serve as a usable facilitator for researchers engaging in the software development life cycle, from product conceptualization to feature identification and user story development to code generation. Trial Registration ClinicalTrials.gov NCT04049500; https://clinicaltrials.gov/ct2/show/NCT04049500

show abstract

Review of large vision models and visual prompt engineering

Cited by 50 publications

References 60 publications

An artificial intelligence application in mathematics education: Evaluating ChatGPT’s academic achievement in a mathematics exam

An artificial intelligence application in mathematics education: Evaluating ChatGPT’s academic achievement in a mathematics exam

Deep Learning Methods for Tracking the Locomotion of Individual Chickens

Leveraging Generative AI Tools to Support the Development of Digital Solutions in Health Care Research: Case Study

Contact Info

Product

Resources

About