{"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/positive-augmented-constrastive-learning-for","title":"Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation","arxiv_id":"2303.12112","date":"2023-03-21","proceeding":"CVPR 2023 1","authors":["Sara Sarto","Manuele Barraco","Marcella Cornia","Lorenzo Baraldi","Rita Cucchiara"],"abstract":"The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. Our source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.","url_abs":"https://arxiv.org/abs/2303.12112v3","url_pdf":"https://arxiv.org/pdf/2303.12112v3.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":"positive-augmented-constrastive-learning-for","repo_url":"https://github.com/aimagelab/pacscore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.12112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12112"}},"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":"deterministic:regex_extraction","url":"https://github.com/aimagelab/pacscore","reach":null}],"summary":{"ran":2,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"2ddbbaf587daf674","entry":"CapDataset","repo":"aimagelab/pacscore","repo_kind":"official","path":"evaluation/pac_score/pac_score.py","file_url":"https://github.com/aimagelab/pacscore/blob/HEAD/evaluation/pac_score/pac_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ddbbaf587daf674"}},{"code_sha256_prefix":"436fc058cf71f80e","entry":"ImageDataset","repo":"aimagelab/pacscore","repo_kind":"official","path":"evaluation/pac_score/pac_score.py","file_url":"https://github.com/aimagelab/pacscore/blob/HEAD/evaluation/pac_score/pac_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"436fc058cf71f80e"}},{"code_sha256_prefix":"35ecbfe542de2a52","entry":"extract_all_images","repo":"aimagelab/pacscore","repo_kind":"official","path":"evaluation/pac_score/pac_score.py","file_url":"https://github.com/aimagelab/pacscore/blob/HEAD/evaluation/pac_score/pac_score.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35ecbfe542de2a52"}},{"code_sha256_prefix":"3c1569ce004845d7","entry":"PACScore","repo":"aimagelab/pacscore","repo_kind":"official","path":"evaluation/pac_score/pac_score.py","file_url":"https://github.com/aimagelab/pacscore/blob/HEAD/evaluation/pac_score/pac_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c1569ce004845d7"}},{"code_sha256_prefix":"d539740783cb3aac","entry":"extract_all_captions","repo":"aimagelab/pacscore","repo_kind":"official","path":"evaluation/pac_score/pac_score.py","file_url":"https://github.com/aimagelab/pacscore/blob/HEAD/evaluation/pac_score/pac_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d539740783cb3aac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}