{"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/pro-cap-leveraging-a-frozen-vision-language","title":"Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection","arxiv_id":"2308.08088","date":"2023-08-16","proceeding":null,"authors":["Rui Cao","Ming Shan Hee","Adriel Kuek","Wen-Haw Chong","Roy Ka-Wei Lee","Jing Jiang"],"abstract":"Hateful meme detection is a challenging multimodal task that requires comprehension of both vision and language, as well as cross-modal interactions. Recent studies have tried to fine-tune pre-trained vision-language models (PVLMs) for this task. However, with increasing model sizes, it becomes important to leverage powerful PVLMs more efficiently, rather than simply fine-tuning them. Recently, researchers have attempted to convert meme images into textual captions and prompt language models for predictions. This approach has shown good performance but suffers from non-informative image captions. Considering the two factors mentioned above, we propose a probing-based captioning approach to leverage PVLMs in a zero-shot visual question answering (VQA) manner. Specifically, we prompt a frozen PVLM by asking hateful content-related questions and use the answers as image captions (which we call Pro-Cap), so that the captions contain information critical for hateful content detection. The good performance of models with Pro-Cap on three benchmarks validates the effectiveness and generalization of the proposed method.","url_abs":"https://arxiv.org/abs/2308.08088v1","url_pdf":"https://arxiv.org/pdf/2308.08088v1.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":"pro-cap-leveraging-a-frozen-vision-language","repo_url":"https://github.com/social-ai-studio/pro-cap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pro-cap-leveraging-a-frozen-vision-language","repo_url":"https://github.com/abril4416/kgen_vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"meme-classification","task_name":"Meme Classification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/meme-classification-on-hateful-memes","task":"Meme Classification","dataset":"Hateful Memes","model":"Pro-Cap","rank_in_archive_order":13,"of":17,"metrics":{"Accuracy":"0.723","ROC-AUC":"0.809"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.08088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08088"}},"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/social-ai-studio/pro-cap","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abril4416/kgen_vqa","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"8324318c7428d828","entry":"load_pkl","repo":"social-ai-studio/pro-cap","repo_kind":"official","path":"codes/scr/dataset.py","file_url":"https://github.com/social-ai-studio/pro-cap/blob/HEAD/codes/scr/dataset.py","link_basis":"harvester_set","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":"8324318c7428d828"}},{"code_sha256_prefix":"c7f91c779ebf5d00","entry":"build_baseline","repo":"social-ai-studio/pro-cap","repo_kind":"official","path":"codes/scr/pbm.py","file_url":"https://github.com/social-ai-studio/pro-cap/blob/HEAD/codes/scr/pbm.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":"c7f91c779ebf5d00"}},{"code_sha256_prefix":"6719bd0b479a0f4e","entry":"read_csv","repo":"social-ai-studio/pro-cap","repo_kind":"official","path":"codes/scr/dataset.py","file_url":"https://github.com/social-ai-studio/pro-cap/blob/HEAD/codes/scr/dataset.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":"6719bd0b479a0f4e"}},{"code_sha256_prefix":"4e153db0c2c01df3","entry":"read_hdf5","repo":"social-ai-studio/pro-cap","repo_kind":"official","path":"codes/scr/dataset.py","file_url":"https://github.com/social-ai-studio/pro-cap/blob/HEAD/codes/scr/dataset.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":"4e153db0c2c01df3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}