{"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/object-based-attention-for-spatio-temporal","title":"Attention over learned object embeddings enables complex visual reasoning","arxiv_id":"2012.08508","date":"2020-12-15","proceeding":"NeurIPS 2021 12","authors":["David Ding","Felix Hill","Adam Santoro","Malcolm Reynolds","Matt Botvinick"],"abstract":"Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic components, independent dynamics models or semantic parsers) targeted towards that specific type of task have typically performed better. The downside to these targeted approaches, however, is that they can be more brittle than general-purpose neural networks, requiring significant modification or even redesign according to the particular task at hand. Here, we propose a more general neural-network-based approach to dynamic visual reasoning problems that obtains state-of-the-art performance on three different domains, in each case outperforming bespoke modular approaches tailored specifically to the task. Our method relies on learned object-centric representations, self-attention and self-supervised dynamics learning, and all three elements together are required for strong performance to emerge. The success of this combination suggests that there may be no need to trade off flexibility for performance on problems involving spatio-temporal or causal-style reasoning. With the right soft biases and learning objectives in a neural network we may be able to attain the best of both worlds.","url_abs":"https://arxiv.org/abs/2012.08508v3","url_pdf":"https://arxiv.org/pdf/2012.08508v3.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":"object-based-attention-for-spatio-temporal","repo_url":"https://github.com/deepmind/deepmind-research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-cater","task":"Video Object Tracking","dataset":"CATER","model":"Aloe","rank_in_archive_order":4,"of":7,"metrics":{"L1":"0.44","Top 1 Accuracy":"74.0","Top 5 Accuracy":"94.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.08508","atlas_url":"https://app.syntology.ai/?focus=2012.08508","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":"2012.08508"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.08508\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.08508"},"call":"get_concepts_for_paper(arxiv_id=\"2012.08508\")"}],"by_repo":[{"repo":"deepmind/deepmind-research","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2006.12982","2101.08692","2103.03206","2105.14039"],"harvested_for_calls":[{"arxiv_id":"2006.12982","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.12982"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.12982\")"},{"arxiv_id":"2101.08692","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.08692"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.08692\")"},{"arxiv_id":"2103.03206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.03206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.03206\")"},{"arxiv_id":"2105.14039","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14039"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14039\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"a4107579ec1f88599bab013a45386f3ab26c37cbc02a228418becb8b1a7a648a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}