{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/multi-target-embodied-question-answering","title":"Multi-Target Embodied Question Answering","arxiv_id":"1904.04686","date":"2019-04-09","proceeding":"CVPR 2019 6","authors":["Licheng Yu","Xinlei Chen","Georgia Gkioxari","Mohit Bansal","Tamara L. Berg","Dhruv Batra"],"abstract":"Embodied Question Answering (EQA) is a relatively new task where an agent is\nasked to answer questions about its environment from egocentric perception. EQA\nmakes the fundamental assumption that every question, e.g., \"what color is the\ncar?\", has exactly one target (\"car\") being inquired about. This assumption\nputs a direct limitation on the abilities of the agent. We present a\ngeneralization of EQA - Multi-Target EQA (MT-EQA). Specifically, we study\nquestions that have multiple targets in them, such as \"Is the dresser in the\nbedroom bigger than the oven in the kitchen?\", where the agent has to navigate\nto multiple locations (\"dresser in bedroom\", \"oven in kitchen\") and perform\ncomparative reasoning (\"dresser\" bigger than \"oven\") before it can answer a\nquestion. Such questions require the development of entirely new modules or\ncomponents in the agent. To address this, we propose a modular architecture\ncomposed of a program generator, a controller, a navigator, and a VQA module.\nThe program generator converts the given question into sequential executable\nsub-programs; the navigator guides the agent to multiple locations pertinent to\nthe navigation-related sub-programs; and the controller learns to select\nrelevant observations along its path. These observations are then fed to the\nVQA module to predict the answer. We perform detailed analysis for each of the\nmodel components and show that our joint model can outperform previous methods\nand strong baselines by a significant margin.","url_abs":"http://arxiv.org/abs/1904.04686v1","url_pdf":"http://arxiv.org/pdf/1904.04686v1.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":"multi-target-embodied-question-answering","repo_url":"https://github.com/facebookresearch/EmbodiedQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"embodied-question-answering","task_name":"Embodied Question Answering"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.04686","atlas_url":"https://app.syntology.ai/?focus=1904.04686","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1904.04686"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.04686\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.04686"},"call":"get_concepts_for_paper(arxiv_id=\"1904.04686\")"}],"by_repo":[{"repo":"facebookresearch/EmbodiedQA","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b9cd7dd1d061f78aa5f37e5d5f94cd12015edc582c0e6ed638b71d056ad5b5ef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}