{"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/a-pooling-approach-to-modelling-spatial","title":"A Pooling Approach to Modelling Spatial Relations for Image Retrieval and Annotation","arxiv_id":"1411.5190","date":"2014-11-19","proceeding":null,"authors":["Mateusz Malinowski","Mario Fritz"],"abstract":"Over the last two decades we have witnessed strong progress on modeling\nvisual object classes, scenes and attributes that have significantly\ncontributed to automated image understanding. On the other hand, surprisingly\nlittle progress has been made on incorporating a spatial representation and\nreasoning in the inference process. In this work, we propose a pooling\ninterpretation of spatial relations and show how it improves image retrieval\nand annotations tasks involving spatial language. Due to the complexity of the\nspatial language, we argue for a learning-based approach that acquires a\nrepresentation of spatial relations by learning parameters of the pooling\noperator. We show improvements on previous work on two datasets and two\ndifferent tasks as well as provide additional insights on a new dataset with an\nexplicit focus on spatial relations.","url_abs":"http://arxiv.org/abs/1411.5190v2","url_pdf":"http://arxiv.org/pdf/1411.5190v2.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":[],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"dataset-of-structured-queries-and-spatial","name":"Dataset of Structured Queries and Spatial Relations","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1411.5190","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}