{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:31:58Z","timestamp":1768293118099,"version":"3.49.0"},"reference-count":20,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGKDD Explor. Newsl."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:p>Cattle-brand identification poses unique challenges due to the sparse, high-contrast nature of symbolic marks and the large stylistic gap between clean reference templates and hand-drawn queries. Since a prediction layer cannot be applied reliably in this setting, weperform identification through feature extraction and similarity search using a VGG-16 encoder and a FAISS-based retrieval system. weinvestigate how the encoder represents these binary symbols by combining channel-level activation statistics, Grad-CAM saliency maps, and Top-10 retrieval results. Our analysis shows that a small group of filters, especially an outer-contour detector, dominates the embedding space, leading to systematic underrepresentation of internal strokes, multi-component patterns, and thin or rotated structures. By comparing the saliency profiles of each query and its reference template, we observe how spatial contribution mismatches propagate into ranking errors. The study provides a concise, reproducible framework for auditing CNN feature extraction in symbolic CBIR tasks and highlights structural vulnerabilities relevant to livestock identification, logo retrieval, and other domains involving sparse binary imagery.<\/jats:p>","DOI":"10.1145\/3787470.3787486","type":"journal-article","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:46:21Z","timestamp":1767228381000},"page":"149-155","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explaining Embedding-Based Matching of Hand-DrawnBinary Symbols with Grad-CAM: A Case Study on CattleBrands"],"prefix":"10.1145","volume":"27","author":[{"given":"Leandra Alves","family":"Soares","sequence":"first","affiliation":[{"name":"Institute of Physics, UFG, Goi\u00e2nia, Goi\u00e1s, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos Vin\u00edcius S.","family":"Medeiros","sequence":"additional","affiliation":[{"name":"Institute of Informatics, UFG, Goi\u00e2nia, Goi\u00e1s, Brazil, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aldo A.","family":"D\u00edaz-Salazar","sequence":"additional","affiliation":[{"name":"Institute of Informatics, UFG, Goi\u00e2nia, Goi\u00e1s, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"O. C. Association. Oklahoma brand registration. https: \/\/www.okcattlemen.org\/brands. Accessed: 2025-05- 30."},{"key":"e_1_2_1_2_1","volume-title":"Sampling Techniques","author":"Cochran W. G.","year":"1977","unstructured":"W. G. Cochran. Sampling Techniques. John Wiley & Sons, 3rd edition, 1977.","edition":"3"},{"issue":"1","key":"e_1_2_1_3_1","first-page":"235","article-title":"Interpretability in healthcare: A comparative study of local machine learning interpretability techniques","volume":"36","author":"ElShawi R.","year":"2020","unstructured":"R. ElShawi, Y. Sherif, M. Al-Mallah, and S. Sakr. Interpretability in healthcare: A comparative study of local machine learning interpretability techniques. Computational Intelligence, 36(1):235--249, 2020.","journal-title":"Computational Intelligence"},{"key":"e_1_2_1_4_1","unstructured":"O. I. Inc. British columbia livestock brand database (brandbook). https:\/\/www.ownershipid.ca\/ brandbook. Accessed: 2025-05--30."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_2_1_6_1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NeurIPS), pages 1097--1105, 2012."},{"key":"e_1_2_1_7_1","volume-title":"Transactions on Machine Learning Research","author":"Li X.","year":"2024","unstructured":"X. Li et al. Hierarchical prototype-based explanations. Transactions on Machine Learning Research, 2024."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.906290"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI67909.2025.11223494"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01469"},{"key":"e_1_2_1_12_1","unstructured":"T. D. of Agriculture. Tennessee agricultural brand database. https:\/\/agriculture.tn.gov\/ListBrand. asp. Accessed: 2025-05--30."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"issue":"2","key":"e_1_2_1_15_1","first-page":"45","article-title":"Segmentation and detection of cattle branding images using cnn and svm","volume":"8","author":"Silva J.","year":"2017","unstructured":"J. Silva, B. Pereira, and L. Santos. Segmentation and detection of cattle branding images using cnn and svm. Journal of Agricultural Informatics, 8(2):45--53, 2017.","journal-title":"Journal of Agricultural Informatics"},{"key":"e_1_2_1_16_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan K.","year":"2013","unstructured":"K. Simonyan, A. Vedaldi, and A. Zisserman. Deep inside convolutional networks: Visualising image classification models and saliency maps. 2013."},{"key":"e_1_2_1_17_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Simonyan K.","year":"2015","unstructured":"K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations (ICLR), 2015."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["ACM SIGKDD Explorations Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787470.3787486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:43:36Z","timestamp":1768265016000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787470.3787486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":20,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12,30]]}},"alternative-id":["10.1145\/3787470.3787486"],"URL":"https:\/\/doi.org\/10.1145\/3787470.3787486","relation":{},"ISSN":["1931-0145","1931-0153"],"issn-type":[{"value":"1931-0145","type":"print"},{"value":"1931-0153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]},"assertion":[{"value":"2025-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}