{"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/cova-context-aware-visual-attention-for","title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","arxiv_id":"2110.12320","date":"2021-10-24","proceeding":"ECNLP (ACL) 2022 5","authors":["Anurendra Kumar","Keval Morabia","Jingjin Wang","Kevin Chen-Chuan Chang","Alexander Schwing"],"abstract":"Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as context and appearance are encoded in an abstract manner. To address this challenge we propose to reformulate WIE as a context-aware Webpage Object Detection task. Specifically, we develop a Context-aware Visual Attention-based (CoVA) detection pipeline which combines appearance features with syntactical structure from the DOM tree. To study the approach we collect a new large-scale dataset of e-commerce websites for which we manually annotate every web element with four labels: product price, product title, product image and background. On this dataset we show that the proposed CoVA approach is a new challenging baseline which improves upon prior state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2110.12320v1","url_pdf":"https://arxiv.org/pdf/2110.12320v1.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":"cova-context-aware-visual-attention-for","repo_url":"https://github.com/kevalmorabia97/cova-web-object-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"webpage-object-detection","task_name":"Webpage Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"cova","method_name":"CoVA"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fast-r-cnn","method_name":"Fast R-CNN"},{"method_slug":"gat","method_name":"GAT"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"cova","name":"CoVA","full_name":"CoVA dataset for Webpage Object Detection / Information Extraction"}],"methods_introduced":[{"slug":"cova","name":"CoVA","full_name":"Context-aware Visual Attention-based (CoVA) webpage object detection pipeline"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.12320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12320"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kevalmorabia97/cova-web-object-detection","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c76c5875dc8c9963","entry":"count_parameters","repo":"kevalmorabia97/cova-web-object-detection","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kevalmorabia97/cova-web-object-detection/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c76c5875dc8c9963"}},{"code_sha256_prefix":"d000088734926f4b","entry":"custom_collate_fn","repo":"kevalmorabia97/cova-web-object-detection","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/kevalmorabia97/cova-web-object-detection/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d000088734926f4b"}},{"code_sha256_prefix":"6c7efc956a22d5af","entry":"load_data","repo":"kevalmorabia97/cova-web-object-detection","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/kevalmorabia97/cova-web-object-detection/blob/HEAD/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c7efc956a22d5af"}},{"code_sha256_prefix":"7d27c8ec904b9dfc","entry":"pkl_load","repo":"kevalmorabia97/cova-web-object-detection","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kevalmorabia97/cova-web-object-detection/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d27c8ec904b9dfc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}