{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T05:01:56Z","timestamp":1784955716591,"version":"3.55.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/ecai69016.2026.11613601","type":"proceedings-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:08:39Z","timestamp":1784920119000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Images: Metadata-Augmented Multimodal Fusion for Wildlife Classification"],"prefix":"10.1109","author":[{"given":"Anuruddha","family":"Paul","sequence":"first","affiliation":[{"name":"Deemed to be University","place":["Bhubaneswar, Odisha, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahendra Kumar","family":"Gourisaria","sequence":"additional","affiliation":[{"name":"Deemed to be University","place":["Bhubaneswar, Odisha, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amitkumar V.","family":"Jha","sequence":"additional","affiliation":[{"name":"KIIT Deemed to be University","place":["Bhubaneswar, Odisha, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhargav","family":"Appasani","sequence":"additional","affiliation":[{"name":"KIIT Deemed to be University","place":["Bhubaneswar, Odisha, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicu","family":"Bizon","sequence":"additional","affiliation":[{"name":"University POLITEHNICA Bucharest Pite\u015fti University Centre","place":["Pitesti, Romania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satyabrata","family":"Roy","sequence":"additional","affiliation":[{"name":"Manipal University Jaipur","place":["Jaipur, Rajasthan, India"],"department":["Dept. of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2015.26"},{"issue":"6","key":"ref2","first-page":"142","volume-title":"YOLO advances to its genesis: A decadal and comprehensive review of the You Only Look Once (YOLO) series","volume":"57","author":"Liu","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-27980-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01197"},{"key":"ref5","article-title":"Efficient pipeline for camera trap image review","author":"Beery","year":"2021"},{"key":"ref6","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"Akbari","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","first-page":"103048","article-title":"Multimodal fusion learning with dual attention for medical image segmentation","volume":"92","author":"Dhar","year":"2024","journal-title":"Medical Image Analysis"},{"issue":"1","key":"ref8","first-page":"2341","article-title":"LGMMFusion: A LiDAR-guided multi-modal fusion framework for 3D object detection","volume":"9","author":"Liang","year":"2022","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"ref9","first-page":"102716","article-title":"Metadata augmented deep neural networks for wild animal classification","volume":"82","author":"Gomez-Villa","year":"2024","journal-title":"Ecological Informatics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/crv.2018.00052"},{"key":"ref11","article-title":"MDA: An interpretable and scalable multi-modal fusion under missing modalities and intrinsic noise conditions","author":"Fan","year":"2024"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3429"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101919"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/make5040083"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","author":"Nagrani","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref18","first-page":"1168048","article-title":"Data augmentation for deep learning based semantic segmentation and classification tasks in medical imaging","volume":"5","author":"Lu","year":"2023","journal-title":"Frontiers in Computer Science"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref20","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Glorot"},{"key":"ref21","article-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"ref22","article-title":"YOLOv11: An overview of the key architectural enhancements","author":"Wang","year":"2024"},{"key":"ref23","first-page":"3642","article-title":"Auto-aligned multi-modal fusion for 3D object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"}],"event":{"name":"2026 18th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)","location":"Bucharest, Romania","start":{"date-parts":[[2026,7,2]]},"end":{"date-parts":[[2026,7,3]]}},"container-title":["2026 18th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11613560\/11613162\/11613601.pdf?arnumber=11613601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T04:29:57Z","timestamp":1784953797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11613601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ecai69016.2026.11613601","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}