{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:54:35Z","timestamp":1776696875175,"version":"3.51.2"},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"PNRR MUR projects FAIR","award":["PE0000013-FAIR"],"award-info":[{"award-number":["PE0000013-FAIR"]}]},{"name":"MUMBLE","award":["FAIR-E63C22002150007"],"award-info":[{"award-number":["FAIR-E63C22002150007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>Video-based alarm notification systems play a critical role in safety-critical applications such as fire detection and pedestrian monitoring, because they allow for prompt intervention in the event of dangerous situations. However, existing approaches often struggle to balance high sensitivity and specificity with real-time performance, particularly in complex scenes. To address these limitations, we propose a novel method enabling Fast Alarm Notification with Task-Aware Spatio-Temporal Image Classification (FAN-TAST-IC). It is an innovative and efficient framework that combines a lightweight task-specific object detector with a pre-trained Vision-Language Model (VLM) encoder and a binary classifier. Unlike end-to-end multimodal systems, FAN-TAST-IC leverages the VLM solely as a frozen visual feature extractor, preserving its rich semantic knowledge while ensuring computational efficiency. The object detector performs a rough but real-time filtering of the temporal frames and spatial positions where objects can be. This filtering is then refined in two distinct ways, depending on the time constraints of the specific application, either to discard temporally incoherent detections or to confirm those with high confidence. The selection of such candidates drastically reduces the input space for the VLM and classifier to dubious detections only. Thus, the latter is trained on detector-guided positive and negative samples, enabling precise alarm validation, improving specificity, and preserving sensitivity without requiring extensive labeled datasets or fine-tuning the VLM. Experiments on fire and pedestrian detection tasks demonstrate the effectiveness of our method since FAN-TAST-IC consistently outperforms all the compared approaches, achieving superior F-scores and precision on challenging benchmarks while maintaining real-time capabilities.<\/jats:p>","DOI":"10.1145\/3801157","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T10:53:01Z","timestamp":1773399181000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FAN-TAST-IC: Fast Alarm Notification with Task-Aware Spatio-Temporal Image Classification"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4271-8160","authenticated-orcid":false,"given":"Diego","family":"Gragnaniello","sequence":"first","affiliation":[{"name":"Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5495-2432","authenticated-orcid":false,"given":"Antonio","family":"Greco","sequence":"additional","affiliation":[{"name":"Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Fisciano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8176-6950","authenticated-orcid":false,"given":"Carlo","family":"Sansone","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Napoli, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7687-4929","authenticated-orcid":false,"given":"Bruno","family":"Vento","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Napoli, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"1","volume-title":"2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)","author":"Alkalouti Hanan Nasser","year":"2021","unstructured":"Hanan Nasser Alkalouti and Mayada Ahmed Al Masre. 2021. Encoder-decoder model for automatic video captioning using yolo algorithm. In 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS). IEEE, 1\u20134."},{"key":"e_1_3_2_3_2","first-page":"1","volume-title":"International Joint Conference on Neural Networks (IJCNN)","author":"Ayala Angel","year":"2020","unstructured":"Angel Ayala, Bruno Fernandes, Francisco Cruz, David Mac\u00eado, Adriano Li Oliveira, and Cleber Zanchettin. 2020. Kutralnet: A portable deep learning model for fire recognition. In International Joint Conference on Neural Networks (IJCNN), 1\u20138."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/RTSI61910.2024.10761238","volume-title":"2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","author":"Carletti Vincenzo","year":"2024","unstructured":"Vincenzo Carletti, Antonio Greco, Alessia Saggese, and Bruno Vento. 2024. Enhancing safety by obstacle detection at railway level crossings. In 2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI). IEEE, 482\u2013487."},{"key":"e_1_3_2_6_2","first-page":"401","volume-title":"European Conference on Computer Vision","author":"Chen Hanning","year":"2025","unstructured":"Hanning Chen, Wenjun Huang, Yang Ni, Sanggeon Yun, Yezi Liu, Fei Wen, Alvaro Velasquez, Hugo Latapie, and Mohsen Imani. 2025. Taskclip: Extend large vision-language model for task oriented object detection. In European Conference on Computer Vision. Springer, 401\u2013418."},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1109\/ICEACE63551.2024.10898935","volume-title":"2024 IEEE 2nd International Conference on Electrical, Automation and Computer Engineering (ICEACE)","author":"Chen Qihao","year":"2024","unstructured":"Qihao Chen and Jiaxuan Zheng. 2024. Object detection through simulated annealing for CLIP-YOLO integration. In 2024 IEEE 2nd International Conference on Electrical, Automation and Computer Engineering (ICEACE). IEEE, 1023\u20131029."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08260-2"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1109\/WACV.2018.00201","volume-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Desta Mikyas T.","year":"2018","unstructured":"Mikyas T. Desta, Larry Chen, and Tomasz Kornuta. 2018. Object-based reasoning in VQA. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 1814\u20131823."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23084024"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","first-page":"124783","DOI":"10.1016\/j.eswa.2024.124783","article-title":"Fire and smoke detection from videos: A literature review under a novel taxonomy","author":"Gragnaniello Diego","year":"2024","unstructured":"Diego Gragnaniello, Antonio Greco, Carlo Sansone, and Bruno Vento. 2024. Fire and smoke detection from videos: A literature review under a novel taxonomy. Expert Systems with Applications 255 (2024), 124783.","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"e_1_3_2_12_2","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s12652-024-04939-z","article-title":"Onfire 2023 contest: What did we learn about real time fire detection from cameras?","volume":"16","author":"Gragnaniello Diego","year":"2024","unstructured":"Diego Gragnaniello, Antonio Greco, Carlo Sansone, and Bruno Vento. 2024. Onfire 2023 contest: What did we learn about real time fire detection from cameras? Journal of Ambient Intelligence and Humanized Computing 16, 1 (2024), 253\u2013264 .","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-10963-z"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-024-04939-z"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721291"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.3390\/s25061736"},{"key":"e_1_3_2_17_2","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv:1606.08415. Retrieved from https:\/\/arxiv.org\/abs\/1606.08415"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"e_1_3_2_19_2","unstructured":"Arpit Jadon Mohd Omama Akshay Varshney Mohammad Samar Ansari and Rishabh Sharma. 2019. FireNet: A specialized lightweight fire and smoke detection model for real-time IoT applications. arXiv:1905.11922. Retrieved from https:\/\/arxiv.org\/abs\/1905.11922"},{"key":"e_1_3_2_20_2","first-page":"980","volume-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","author":"Jang Jiho","year":"2023","unstructured":"Jiho Jang, Chaerin Kong, Donghyeon Jeon, Seonhoon Kim, and Nojun Kwak. 2023. Unifying vision-language representation space with single-tower transformer. In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 980\u2013988."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_22_2","unstructured":"Weicheng Kuo Yin Cui Xiuye Gu A. J. Piergiovanni and Anelia Angelova. 2022. F-vlm: Open-vocabulary object detection upon frozen vision and language models. arXiv:2209.15639. Retrieved from https:\/\/arxiv.org\/abs\/2209.15639"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13053148"},{"key":"e_1_3_2_24_2","first-page":"19730","volume-title":"International Conference on Machine Learning","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International Conference on Machine Learning. PMLR, 19730\u201319742."},{"key":"e_1_3_2_25_2","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems 34 (2021), 9694\u20139705.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_26_2","first-page":"6545","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Lin Yutong","year":"2023","unstructured":"Yutong Lin, Yuhui Yuan, Zheng Zhang, Chen Li, Nanning Zheng, and Han Hu. 2023. Detr does not need multi-scale or locality design. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 6545\u20136554."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3538641.3561491"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09832-7"},{"key":"e_1_3_2_31_2","first-page":"167","volume-title":"European Conference on Computer Vision","author":"Nguyen Van-Quang","year":"2022","unstructured":"Van-Quang Nguyen, Masanori Suganuma, and Takayuki Okatani. 2022. Grit: Faster and better image captioning transformer using dual visual features. In European Conference on Computer Vision. Springer, 167\u2013184."},{"key":"e_1_3_2_32_2","first-page":"256","volume-title":"2021 19th OITS International Conference on Information Technology (OCIT)","author":"Priyadarsini Panda Soumya","year":"2021","unstructured":"Soumya Priyadarsini Panda and Navin Chandra. 2021. A visual question answering system using YOLO model. In 2021 19th OITS International Conference on Information Technology (OCIT). IEEE, 256\u2013260."},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1109\/TIP.2020.3034487","article-title":"TJU-DHD: A diverse high-resolution dataset for object detection","author":"Pang Yanwei","year":"2021","unstructured":"Yanwei Pang, Jiale Cao, Yazhao Li, Jin Xie, Hanqing Sun, and Jinfeng Gong. 2021. TJU-DHD: A diverse high-resolution dataset for object detection. IEEE Transactions on Image Processing 30 (2021), 207\u2013219.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_2_34_2","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PmLR, 8748\u20138763."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11276-2"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1109\/ICMLA51294.2020.00030","volume-title":"2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)","author":"Thomson William","year":"2020","unstructured":"William Thomson, Neelanjan Bhowmik, and Toby P. Breckon. 2020. Efficient and compact convolutional neural network architectures for non-temporal real-time fire detection. In 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, 136\u2013141."},{"key":"e_1_3_2_37_2","first-page":"294","volume-title":"International Conference on Image Analysis and Processing","author":"Vincent Grace","year":"2023","unstructured":"Grace Vincent, Laura Desantis, Ethan Patten, and Sambit Bhattacharya. 2023. Rapid fire detection with early exiting. In International Conference on Image Analysis and Processing. Springer, 294\u2013301."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02214-4"},{"key":"e_1_3_2_40_2","first-page":"282","volume-title":"International Conference on Image Analysis and Processing","author":"Zedda Luca","year":"2023","unstructured":"Luca Zedda, Andrea Loddo, and Cecilia Di Ruberto. 2023. FIRESTART: Fire ignition recognition with enhanced smoothing techniques and real-time tracking. In International Conference on Image Analysis and Processing. Springer, 282\u2013293."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:10:16Z","timestamp":1776694216000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":41,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3801157"],"URL":"https:\/\/doi.org\/10.1145\/3801157","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2025-07-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}