{"url":"/method/cova","slug":"cova","name":"CoVA","full_name":"Context-aware Visual Attention-based (CoVA) webpage object detection pipeline","full_name_withheld":false,"description_markdown":"Context-Aware Visual Attention-based end-to-end pipeline for Webpage Object Detection (_CoVA_) aims to learn function _f_ to predict labels _y = [$y_1, y_2, ..., y_N$]_ for a webpage containing _N_ elements. The input to CoVA consists of:\r\n1. a screenshot of a webpage,\r\n2. list of bounding boxes _[x, y, w, h]_ of the web elements, and\r\n3. neighborhood information for each element obtained from the DOM tree.\r\n\r\nThis information is processed in four stages:\r\n1. the graph representation extraction for the webpage,\r\n2. the Representation Network (_RN_),\r\n3. the Graph Attention Network (_GAT_), and\r\n4. a fully connected (_FC_) layer.\r\n\r\nThe graph representation extraction computes for every web element _i_ its set of _K_ neighboring web elements _$N_i$_. The _RN_ consists of a Convolutional Neural Net (_CNN_) and a positional encoder aimed to learn a visual representation _$v_i$_ for each web element _i ∈ {1, ..., N}_. The _GAT_ combines the visual representation _$v_i$_ of the web element _i_ to be classified and those of its neighbors, i.e., _$v_k$ ∀k ∈ $N_i$_ to compute the contextual representation _$c_i$_ for web element _i_. Finally, the visual and contextual representations of the web element are concatenated and passed through the _FC_ layer to obtain the classification output.","description_state":"present","introduced_year":null,"introduced_by":{"title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","paper":"/paper/cova-context-aware-visual-attention-for","first_author":"Anurendra Kumar","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/cova-context-aware-visual-attention-for"},"source":{"url":"https://arxiv.org/abs/2110.12320v1","title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/kevalmorabia97/CoVA-Web-Object-Detection/blob/master/models.py","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Webpage Object Detection Pipeline","url":"/methods/category/webpage-object-detection-pipeline","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Object Detection Models","url":"/methods/category/object-detection-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/cova-exploiting-compressed-domain-analysis-to","title":"CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics","date":"2022-07-02","arxiv_id":"2207.00588","n_code_links":1,"syntology":null},{"paper":"/paper/cova-context-aware-visual-attention-for","title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","date":"2021-10-24","arxiv_id":"2110.12320","n_code_links":1,"syntology":{"ran":0,"of":4,"unverified":4,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/webpage-object-detection","name":"Webpage Object Detection","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/cova"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}