{"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/seq2tens-an-efficient-representation-of","title":"Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections","arxiv_id":"2006.07027","date":"2020-06-12","proceeding":"ICLR 2021 1","authors":["Csaba Toth","Patric Bonnier","Harald Oberhauser"],"abstract":"Sequential data such as time series, video, or text can be challenging to analyse as the ordered structure gives rise to complex dependencies. At the heart of this is non-commutativity, in the sense that reordering the elements of a sequence can completely change its meaning. We use a classical mathematical object -- the tensor algebra -- to capture such dependencies. To address the innate computational complexity of high degree tensors, we use compositions of low-rank tensor projections. This yields modular and scalable building blocks for neural networks that give state-of-the-art performance on standard benchmarks such as multivariate time series classification and generative models for video.","url_abs":"https://arxiv.org/abs/2006.07027v2","url_pdf":"https://arxiv.org/pdf/2006.07027v2.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":"seq2tens-an-efficient-representation-of","repo_url":"https://github.com/tgcsaba/seq2tens","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"},{"task_slug":"tensor-algebra","task_name":"tensor algebra"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"gaussian-process","method_name":"Gaussian Process"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/imputation-on-hmnist","task":"Imputation","dataset":"HMNIST","model":"GP-VAE (B-NLST)","rank_in_archive_order":1,"of":1,"metrics":{"AUROC":"0.962","MSE":"0.092","NLL":"0.251"},"uses_additional_data":false},{"leaderboard":"/sota/imputation-on-physionet-challenge-2012","task":"Imputation","dataset":"PhysioNet Challenge 2012","model":"GP-VAE (B-NLST)","rank_in_archive_order":1,"of":1,"metrics":{"AUROC":"0.743"},"uses_additional_data":false},{"leaderboard":"/sota/imputation-on-sprites","task":"Imputation","dataset":"Sprites","model":"GP-VAE (B-NLST)","rank_in_archive_order":1,"of":1,"metrics":{"MSE":"0.002"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-auslan","task":"Time Series Classification","dataset":"AUSLAN","model":"FCN-SNLST","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"0.993"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-auslan","task":"Time Series Classification","dataset":"AUSLAN","model":"SNLST","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"0.969"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-arabicdigits","task":"Time Series Classification","dataset":"ArabicDigits","model":"FCN-SNLST","rank_in_archive_order":3,"of":10,"metrics":{"Accuracy":"0.993"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-arabicdigits","task":"Time Series Classification","dataset":"ArabicDigits","model":"SNLST","rank_in_archive_order":10,"of":10,"metrics":{"Accuracy":"0.968"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-cmusubject16","task":"Time Series Classification","dataset":"CMUsubject16","model":"SNLST","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-cmusubject16","task":"Time Series Classification","dataset":"CMUsubject16","model":"FCN-SNLST","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on","task":"Time Series Classification","dataset":"CharacterTrajectories","model":"FCN-SNLST","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"0.994"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on","task":"Time Series Classification","dataset":"CharacterTrajectories","model":"SNLST","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"0.957"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-digitshapes","task":"Time Series Classification","dataset":"DigitShapes","model":"SNLST","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-digitshapes","task":"Time Series Classification","dataset":"DigitShapes","model":"FCN-SNLST","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-ecg","task":"Time Series Classification","dataset":"ECG","model":"FCN-SNLST","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"0.860"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-ecg","task":"Time Series Classification","dataset":"ECG","model":"SNLST","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"0.842"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-japanesevowels","task":"Time Series Classification","dataset":"JapaneseVowels","model":"FCN-SNLST","rank_in_archive_order":9,"of":10,"metrics":{"Accuracy":"0.980"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-japanesevowels","task":"Time Series Classification","dataset":"JapaneseVowels","model":"SNLST","rank_in_archive_order":10,"of":10,"metrics":{"Accuracy":"0.979"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-kickvspunch","task":"Time Series Classification","dataset":"KickvsPunch","model":"SNLST","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-kickvspunch","task":"Time Series Classification","dataset":"KickvsPunch","model":"FCN-SNLST","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-libras","task":"Time Series Classification","dataset":"Libras","model":"FCN-SNLST","rank_in_archive_order":2,"of":10,"metrics":{"Accuracy":"0.957"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-libras","task":"Time Series Classification","dataset":"Libras","model":"SNLST","rank_in_archive_order":7,"of":10,"metrics":{"Accuracy":"0.773"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-netflow","task":"Time Series Classification","dataset":"NetFlow","model":"FCN-SNLST","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"0.960"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-netflow","task":"Time Series Classification","dataset":"NetFlow","model":"SNLST","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"0.793"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-pems","task":"Time Series Classification","dataset":"PEMS","model":"FCN-SNLST","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"0.857"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-pems","task":"Time Series Classification","dataset":"PEMS","model":"SNLST","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"0.747"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-pendigits","task":"Time Series Classification","dataset":"PenDigits","model":"SNLST","rank_in_archive_order":2,"of":8,"metrics":{"Accuracy":"0.954"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-pendigits","task":"Time Series Classification","dataset":"PenDigits","model":"FCN-SNLST","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"0.953"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-shapes","task":"Time Series Classification","dataset":"SHAPES","model":"SNLST","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-shapes","task":"Time Series Classification","dataset":"SHAPES","model":"FCN-SNLST","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-uwave","task":"Time Series Classification","dataset":"UWave","model":"FCN-SNLST","rank_in_archive_order":3,"of":10,"metrics":{"Accuracy":"0.969"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-uwave","task":"Time Series Classification","dataset":"UWave","model":"SNLST","rank_in_archive_order":7,"of":10,"metrics":{"Accuracy":"0.938"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-wafer","task":"Time Series Classification","dataset":"Wafer","model":"FCN-SNLST","rank_in_archive_order":4,"of":10,"metrics":{"Accuracy":"0.989"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-wafer","task":"Time Series Classification","dataset":"Wafer","model":"SNLST","rank_in_archive_order":7,"of":10,"metrics":{"Accuracy":"0.981"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-walkvsrun","task":"Time Series Classification","dataset":"WalkvsRun","model":"FCN-SNLST","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-walkvsrun","task":"Time Series Classification","dataset":"WalkvsRun","model":"SNLST","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"tgcsaba/seq2tens","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":"cfcfa009cb04c043658440376605061659a45b12bfd96e1e2bcc2390b6a31b37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}