{"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-dataset-and-architecture-for-visual","title":"A Dataset and Architecture for Visual Reasoning with a Working Memory","arxiv_id":"1803.06092","date":"2018-03-16","proceeding":"ECCV 2018 9","authors":["Guangyu Robert Yang","Igor Ganichev","Xiao-Jing Wang","Jonathon Shlens","David Sussillo"],"abstract":"A vexing problem in artificial intelligence is reasoning about events that\noccur in complex, changing visual stimuli such as in video analysis or game\nplay. Inspired by a rich tradition of visual reasoning and memory in cognitive\npsychology and neuroscience, we developed an artificial, configurable visual\nquestion and answer dataset (COG) to parallel experiments in humans and\nanimals. COG is much simpler than the general problem of video analysis, yet it\naddresses many of the problems relating to visual and logical reasoning and\nmemory -- problems that remain challenging for modern deep learning\narchitectures. We additionally propose a deep learning architecture that\nperforms competitively on other diagnostic VQA datasets (i.e. CLEVR) as well as\neasy settings of the COG dataset. However, several settings of COG result in\ndatasets that are progressively more challenging to learn. After training, the\nnetwork can zero-shot generalize to many new tasks. Preliminary analyses of the\nnetwork architectures trained on COG demonstrate that the network accomplishes\nthe task in a manner interpretable to humans.","url_abs":"http://arxiv.org/abs/1803.06092v2","url_pdf":"http://arxiv.org/pdf/1803.06092v2.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":"a-dataset-and-architecture-for-visual","repo_url":"https://github.com/google/cog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-dataset-and-architecture-for-visual","repo_url":"https://github.com/bashivanlab/iwisdm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-dataset-and-architecture-for-visual","repo_url":"https://github.com/ibm/gcog","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"cog","name":"COG","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.06092","atlas_url":"https://app.syntology.ai/?focus=1803.06092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06092"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ibm/gcog","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bashivanlab/iwisdm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/cog","reach":null}],"summary":{"ran_draft_wrong":5},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":3,"ran":3,"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":"51e7b042a9982d7d","entry":"create_task","repo":"bashivanlab/iwisdm","repo_kind":"listed","path":"benchmarking/create_bench.py","file_url":"https://github.com/bashivanlab/iwisdm/blob/HEAD/benchmarking/create_bench.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51e7b042a9982d7d"}},{"code_sha256_prefix":"628d9212033b209a","entry":"duplicate_check","repo":"bashivanlab/iwisdm","repo_kind":"listed","path":"benchmarking/create_bench.py","file_url":"https://github.com/bashivanlab/iwisdm/blob/HEAD/benchmarking/create_bench.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"628d9212033b209a"}},{"code_sha256_prefix":"ac137256a6442b8e","entry":"generate_trial","repo":"bashivanlab/iwisdm","repo_kind":"listed","path":"benchmarking/create_bench.py","file_url":"https://github.com/bashivanlab/iwisdm/blob/HEAD/benchmarking/create_bench.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac137256a6442b8e"}},{"code_sha256_prefix":"9cdd1174742166f2","entry":"get_target_value","repo":"google/cog","repo_kind":"official","path":"cognitive/generate_dataset.py","file_url":"https://github.com/google/cog/blob/HEAD/cognitive/generate_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9cdd1174742166f2"}},{"code_sha256_prefix":"278fb3b11efe0d35","entry":"log_exceptions","repo":"google/cog","repo_kind":"official","path":"cognitive/generate_dataset.py","file_url":"https://github.com/google/cog/blob/HEAD/cognitive/generate_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"278fb3b11efe0d35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}