{"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":"/method/soho","slug":"soho","name":"SOHO","full_name":"SOHO","full_name_withheld":false,"description_markdown":"SOHO (“See Out of tHe bOx”) that takes a whole image as input, and learns vision-language representation in an end-to-end manner. SOHO does not require bounding box annotations which enables inference 10 times faster than region-based approaches. Text embeddings are used to extract textual embedding features. A trainable CNN is used to extract visual representations. SOHO learns to extract comprehensive yet compact image features through a visual dictionary (VD) that facilitates cross-modal understanding. VD is designed to represent consistent visual abstractions of similar semantics. It is updated on-the-fly and utilized in the proposed pre-training task Masked Visual Modeling (MVM).","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2104.03135v2","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision and Language Pre-Trained Models","url":"/methods/category/vision-and-language-pre-trained-models","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"thermoonet-a-deep-learning-based-small-body","title":"ThermoONet -- a deep learning-based small body thermophysical network: applications to modelling water activity of comets","date":"2025-05-20","arxiv_id":"2505.14016","n_code_links":0,"syntology":null},{"paper":null,"slug":"prediction-of-geoeffective-cmes-using-soho","title":"Prediction of Geoeffective CMEs Using SOHO Images and Deep Learning","date":"2025-01-02","arxiv_id":"2501.01011","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-ontology-for-the-social-determinants-of","title":"An Ontology for the Social Determinants of Health Domain","date":"2022-11-15","arxiv_id":"2211.07837","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-machine-learning-ready-dataset-prepared","title":"A Machine-Learning-Ready Dataset Prepared from the Solar and Heliospheric Observatory Mission","date":"2021-08-04","arxiv_id":"2108.06394","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-out-of-the-box-end-to-end-pre-training","slug":"seeing-out-of-the-box-end-to-end-pre-training","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","date":"2021-04-07","arxiv_id":"2104.03135","n_code_links":3,"syntology":null}],"papers_shown":5,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":5,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/text-retrieval","name":"Text Retrieval","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/visual-entailment","name":"Visual Entailment","papers":1},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":1},{"task":"/task/global-optimization","name":"global-optimization","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":1},{"year":"2025","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/soho"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=SOHO","read_at":"2026-10-05T01:02:15+00:00","query":"SOHO","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"SOHO","origin_arxiv_id":"2104.03135"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":3,"in_graph":3,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2104.03135","citations":317},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'SOHO'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2104.03135","page":"/paper/seeing-out-of-the-box-end-to-end-pre-training","syntology_url":"https://syntology.ai/paper/2104.03135","in_graph_layer":false,"samples":0},"line":"repository known, no verified implementation (declared_code; repositories: 3 listed of 3 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2104.03135) is about this method is not checked.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"250c7381ba8d607ca8b04e87b81b050de029df218083ea2d2f27dd559cc0250d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}