{"schema":"pith.reference-change-event.v1","doi":"10.1016/j.aej.2024.05.015","canonical_url":"https://pith.science/event/10.1016/j.aej.2024.05.015","json_url":"https://pith.science/event/10.1016/j.aej.2024.05.015.json","not_a_judgment":"This page records that a citing paper's bibliography includes a work with a published notice. It is not a judgment on the citing paper.","primary":{"event_id":422912,"doi":"10.1016/j.aej.2024.05.015","event_type":"correction","event_type_label":"Correction","source":"crossref","source_label":"Crossref","event_date":"2024-05-21","title":"Corrigendum to “Vision transformer-based visual language understanding of the construction process” [Alex. Eng. J. 99 (2024) 242–256]","work_title":"Vision transformer-based visual language understanding of the con- struction process","work_doi":"10.1016/j.aej.2024.05.015","work_arxiv_id":null,"notice_doi":"10.1016/j.aej.2024.05.064","flag_count":0,"flags_open":0,"flags_disputed":0,"latest_flag_at":null,"human_href":"/event/10.1016/j.aej.2024.05.015","json_href":"/event/10.1016/j.aej.2024.05.015.json"},"events":[{"event_id":422912,"doi":"10.1016/j.aej.2024.05.015","event_type":"correction","event_type_label":"Correction","source":"crossref","source_label":"Crossref","event_date":"2024-05-21","title":"Corrigendum to “Vision transformer-based visual language understanding of the construction process” [Alex. Eng. J. 99 (2024) 242–256]","work_title":"Vision transformer-based visual language understanding of the con- struction process","work_doi":"10.1016/j.aej.2024.05.015","work_arxiv_id":null,"notice_doi":"10.1016/j.aej.2024.05.064","flag_count":0,"flags_open":0,"flags_disputed":0,"latest_flag_at":null,"human_href":"/event/10.1016/j.aej.2024.05.015","json_href":"/event/10.1016/j.aej.2024.05.015.json"}],"flags":[{"id":6328,"status":"open","status_label":"Open","citing_arxiv_id":"2604.05210","citing_title":"Integration of Object Detection and Small VLMs for Construction Safety Hazard Identification","ref_index":16,"evidence_raw":"Zhao, Automatic construction site hazard identification integrating construction scene graphs with BERT based domain knowledge, 28 Automation in Construction 142 (2022) 104535. https://doi.org/10.1016/j.autcon.2022.104535. [15] F. Bordes, R.Y. Pang, A. Ajay, A.C. Li, et al. , An Introduction to Vision -Language Modeling, (2024). https://doi.org/10.48550/arXiv.2405.17247. [16] B. Yang, B. Zhang, Y. Han, B. Liu, J. Hu, Y. Jin, Vision transformer -based visual language understanding of the construction process, Alexandria Engineering Journal 99 (2024) 242-256. https://doi.org/10.1016/j.aej.2024.05.015. [17] Z. Chen, H. Chen, M. Imani, R. Chen, F. Imani, Vision language model for interpretable and fine-grained detection of safety compliance in diverse workplaces, Expert Systems","evidence_cleaned":"Zhao, Automatic construction site hazard identification integrating construction scene graphs with BERT based domain knowledge, 28 Automation in Construction 142 (2022) 104535. https://doi.org/10.1016/j.autcon.2022.104535. [15] F. Bordes, R.Y. Pang, A. Ajay, A.C. Li, et al., An Introduction to Vision -Language Modeling, (2024). https://doi.org/10.48550/arXiv.2405.17247. [16] B. Yang, B. Zhang, Y. Han, B. Liu, J. Hu, Y. Jin, Vision transformer -based visual language understanding of the construction process, Alexandria Engineering Journal 99 (2024) 242-256. https://doi.org/10.1016/j.aej.2024.05.015. [17] Z. Chen, H. Chen, M. Imani, R. Chen, F. Imani, Vision language model for interpretable and fine-grained detection of safety compliance in diverse workplaces, Expert Systems","evidence_source_label":"citation context","event_type":"correction","event_type_label":"Correction","source_label":"Crossref","event_date":"2024-05-21","work_title":"Vision transformer-based visual language understanding of the con- struction process","work_doi":"10.1016/j.aej.2024.05.015","event_doi":"10.1016/j.aej.2024.05.015","flag_href":"/flags/6328","event_href":"/event/10.1016/j.aej.2024.05.015","paper_href":"/paper/2604.05210","created_at":"2026-07-11T03:19:15.783975Z","dispute_note":null,"disputed_at":null,"disputed_by":null},{"id":6329,"status":"open","status_label":"Open","citing_arxiv_id":"2607.05859","citing_title":"AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring","ref_index":45,"evidence_raw":"Yang, B., Zhang, B., Han, Y., Liu, B., Hu, J., Jin, Y., 2024b. Vision transformer-based visual language understanding of the con- struction process. Alexandria Engineering Journal 99, 242–256. URL:https://www.sciencedirect.com/science/article/pii/ S1110016824004873, doi:https://doi.org/10.1016/j.aej.2024.05.015","evidence_cleaned":null,"evidence_source_label":"bibliography line","event_type":"correction","event_type_label":"Correction","source_label":"Crossref","event_date":"2024-05-21","work_title":"Vision transformer-based visual language understanding of the con- struction process","work_doi":"10.1016/j.aej.2024.05.015","event_doi":"10.1016/j.aej.2024.05.015","flag_href":"/flags/6329","event_href":"/event/10.1016/j.aej.2024.05.015","paper_href":"/paper/2607.05859","created_at":"2026-07-11T03:19:15.783975Z","dispute_note":null,"disputed_at":null,"disputed_by":null}],"flag_count":2,"flags_open":2,"flags_disputed":0,"desk_url":"https://pith.science/flags"}