American Psychological Association 6th edition

Mir, T. H., Wei, J.-C., Simanjuntak, M., Cheng, W.-S., Lee, Y.-H., Zhang, Y.-C., Chen, J.-B., & Dai, H.-J. (2025). Multi-label advertising image classification using traditional deep neural networks and vision language models: dataset and annotation agreement method. Multimedia Tools & Applications, 84(37), 45923-45952. https://doi.org/10.1007/s11042-025-20940-w

ISO-690 (author-date, English)

MIR, Tatheer Hussain, WEI, Jui-Cheng, SIMANJUNTAK, Mutiara, CHENG, Wan-Shu, LEE, Yi-Hsun, ZHANG, You-Chen, CHEN, Jia-Bin und DAI, Hong-Jie, 2025. Multi-label advertising image classification using traditional deep neural networks and vision language models: dataset and annotation agreement method. Multimedia Tools & Applications. 25 November 2025. Vol. 84, no. 37, p. 45923-45952. DOI 10.1007/s11042-025-20940-w.

Modern Language Association 9th edition

Mir, T. H., J.-C. Wei, M. Simanjuntak, W.-S. Cheng, Y.-H. Lee, Y.-C. Zhang, J.-B. Chen, und H.-J. Dai. „Multi-Label Advertising Image Classification Using Traditional Deep Neural Networks and Vision Language Models: Dataset and Annotation Agreement Method.“. Multimedia Tools & Applications, Bd. 84, Nr. 37, November 2025, S. 45923-52, https://doi.org/10.1007/s11042-025-20940-w.

Mohr Siebeck - Recht (Deutsch - Österreich)

Mir, Tatheer Hussain/Wei, Jui-Cheng/Simanjuntak, Mutiara/Cheng, Wan-Shu/Lee, Yi-Hsun/Zhang, You-Chen u. a.: Multi-label advertising image classification using traditional deep neural networks and vision language models: dataset and annotation agreement method., Multimedia Tools & Applications 2025, 45923-45952.

Emerald - Harvard

Mir, T.H., Wei, J.-C., Simanjuntak, M., Cheng, W.-S., Lee, Y.-H., Zhang, Y.-C., Chen, J.-B. und Dai, H.-J. (2025), „Multi-label advertising image classification using traditional deep neural networks and vision language models: dataset and annotation agreement method.“, Multimedia Tools & Applications, Vol. 84 No. 37, S. 45923-45952.

Achtung: Diese Zitate sind unter Umständen nicht zu 100% korrekt.