{"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/lets-transfer-transformations-of-shared","title":"Let's Transfer Transformations of Shared Semantic Representations","arxiv_id":"1903.00793","date":"2019-03-02","proceeding":null,"authors":["Nam Vo","Lu Jiang","James Hays"],"abstract":"With a good image understanding capability, can we manipulate the images high\nlevel semantic representation? Such transformation operation can be used to\ngenerate or retrieve similar images but with a desired modification (for\nexample changing beach background to street background); similar ability has\nbeen demonstrated in zero shot learning, attribute composition and attribute\nmanipulation image search. In this work we show how one can learn\ntransformations with no training examples by learning them on another domain\nand then transfer to the target domain. This is feasible if: first,\ntransformation training data is more accessible in the other domain and second,\nboth domains share similar semantics such that one can learn transformations in\na shared embedding space. We demonstrate this on an image retrieval task where\nsearch query is an image, plus an additional transformation specification (for\nexample: search for images similar to this one but background is a street\ninstead of a beach). In one experiment, we transfer transformation from\nsynthesized 2D blobs image to 3D rendered image, and in the other, we transfer\nfrom text domain to natural image domain.","url_abs":"http://arxiv.org/abs/1903.00793v1","url_pdf":"http://arxiv.org/pdf/1903.00793v1.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":"lets-transfer-transformations-of-shared","repo_url":"https://github.com/gchb2012/VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"lets-transfer-transformations-of-shared","repo_url":"https://github.com/lugiavn/transformation-transferring","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-3d","task_name":"Image to 3D"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"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":"gchb2012/VQA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lugiavn/transformation-transferring","kind":"listed","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":"c67c1def180ec2819c884dbf5a1208a7b3d7dcc7dbbd3b4ddea614eca663381c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}