{"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/learning-to-describe-differences-between","title":"Learning to Describe Differences Between Pairs of Similar Images","arxiv_id":"1808.10584","date":"2018-08-31","proceeding":"EMNLP 2018 10","authors":["Harsh Jhamtani","Taylor Berg-Kirkpatrick"],"abstract":"In this paper, we introduce the task of automatically generating text to\ndescribe the differences between two similar images. We collect a new dataset\nby crowd-sourcing difference descriptions for pairs of image frames extracted\nfrom video-surveillance footage. Annotators were asked to succinctly describe\nall the differences in a short paragraph. As a result, our novel dataset\nprovides an opportunity to explore models that align language and vision, and\ncapture visual salience. The dataset may also be a useful benchmark for\ncoherent multi-sentence generation. We perform a firstpass visual analysis that\nexposes clusters of differing pixels as a proxy for object-level differences.\nWe propose a model that captures visual salience by using a latent variable to\nalign clusters of differing pixels with output sentences. We find that, for\nboth single-sentence generation and as well as multi-sentence generation, the\nproposed model outperforms the models that use attention alone.","url_abs":"http://arxiv.org/abs/1808.10584v1","url_pdf":"http://arxiv.org/pdf/1808.10584v1.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":"learning-to-describe-differences-between","repo_url":"https://github.com/harsh19/spot-the-diff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"spot-the-diff","name":"Spot-the-diff","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.10584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10584"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/harsh19/spot-the-diff","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"4cf9d6b0e8185d87","entry":"PIL2array","repo":"harsh19/spot-the-diff","repo_kind":"official","path":"code/clustering/utilities.py","file_url":"https://github.com/harsh19/spot-the-diff/blob/HEAD/code/clustering/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cf9d6b0e8185d87"}},{"code_sha256_prefix":"30d7e616f7567ada","entry":"changeToBinary","repo":"harsh19/spot-the-diff","repo_kind":"official","path":"code/clustering/utilities.py","file_url":"https://github.com/harsh19/spot-the-diff/blob/HEAD/code/clustering/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30d7e616f7567ada"}},{"code_sha256_prefix":"5f8c4e41595a647a","entry":"findBoxPoints","repo":"harsh19/spot-the-diff","repo_kind":"official","path":"code/clustering/box.py","file_url":"https://github.com/harsh19/spot-the-diff/blob/HEAD/code/clustering/box.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f8c4e41595a647a"}},{"code_sha256_prefix":"6ad4b197533dceaf","entry":"findRectangleCoordinates","repo":"harsh19/spot-the-diff","repo_kind":"official","path":"code/clustering/box.py","file_url":"https://github.com/harsh19/spot-the-diff/blob/HEAD/code/clustering/box.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ad4b197533dceaf"}},{"code_sha256_prefix":"71c404b24fb633ff","entry":"getMatrixFromIM","repo":"harsh19/spot-the-diff","repo_kind":"official","path":"code/clustering/utilities.py","file_url":"https://github.com/harsh19/spot-the-diff/blob/HEAD/code/clustering/utilities.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71c404b24fb633ff"}},{"code_sha256_prefix":"682f15261bbaf957","entry":"loadClusters","repo":"harsh19/spot-the-diff","repo_kind":"official","path":"code/clustering/box.py","file_url":"https://github.com/harsh19/spot-the-diff/blob/HEAD/code/clustering/box.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"682f15261bbaf957"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}