{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/describing-textures-in-the-wild","title":"Describing Textures in the Wild","arxiv_id":"1311.3618","date":"2013-11-14","proceeding":"CVPR 2014 6","authors":["Mircea Cimpoi","Subhransu Maji","Iasonas Kokkinos","Sammy Mohamed","Andrea Vedaldi"],"abstract":"Patterns and textures are defining characteristics of many natural objects: a\nshirt can be striped, the wings of a butterfly can be veined, and the skin of\nan animal can be scaly. Aiming at supporting this analytical dimension in image\nunderstanding, we address the challenging problem of describing textures with\nsemantic attributes. We identify a rich vocabulary of forty-seven texture terms\nand use them to describe a large dataset of patterns collected in the wild.The\nresulting Describable Textures Dataset (DTD) is the basis to seek for the best\ntexture representation for recognizing describable texture attributes in\nimages. We port from object recognition to texture recognition the Improved\nFisher Vector (IFV) and show that, surprisingly, it outperforms specialized\ntexture descriptors not only on our problem, but also in established material\nrecognition datasets. We also show that the describable attributes are\nexcellent texture descriptors, transferring between datasets and tasks; in\nparticular, combined with IFV, they significantly outperform the\nstate-of-the-art by more than 8 percent on both FMD and KTHTIPS-2b benchmarks.\nWe also demonstrate that they produce intuitive descriptions of materials and\nInternet images.","url_abs":"http://arxiv.org/abs/1311.3618v2","url_pdf":"http://arxiv.org/pdf/1311.3618v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/Puning97/AUTO-for-OOD-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/cider","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/dice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/gradnorm_ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/knn-ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/large_scale_ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/npos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/react","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/deeplearning-wisc/snn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/jimzai/mode-ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/mapleleaf6/zode","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/tmlr-group/class_prior","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/tmlr-group/neglabel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"describing-textures-in-the-wild","repo_url":"https://github.com/yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"material-recognition","task_name":"Material Recognition"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[{"slug":"dtd","name":"DTD","full_name":"Describable Textures Dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1311.3618","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}