{"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/caption-anything-interactive-image","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","arxiv_id":"2305.02677","date":"2023-05-04","proceeding":null,"authors":["Teng Wang","Jinrui Zhang","Junjie Fei","Hao Zheng","Yunlong Tang","Zhe Li","Mingqi Gao","Shanshan Zhao"],"abstract":"Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this paper, we present Caption AnyThing (CAT), a foundation model augmented image captioning framework supporting a wide range of multimodel controls: 1) visual controls, including points, boxes, and trajectories; 2) language controls, such as sentiment, length, language, and factuality. Powered by Segment Anything Model (SAM) and ChatGPT, we unify the visual and language prompts into a modularized framework, enabling the flexible combination between different controls. Extensive case studies demonstrate the user intention alignment capabilities of our framework, shedding light on effective user interaction modeling in vision-language applications. Our code is publicly available at https://github.com/ttengwang/Caption-Anything.","url_abs":"https://arxiv.org/abs/2305.02677v3","url_pdf":"https://arxiv.org/pdf/2305.02677v3.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":"caption-anything-interactive-image","repo_url":"https://github.com/ttengwang/caption-anything","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":null,"task_name":"Image Description"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"controllable-image-captioning","task_name":"controllable image captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.02677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02677"}},"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/ttengwang/caption-anything","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":10,"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":0,"samples":[{"code_sha256_prefix":"4675779aec92d6c0","entry":"contrastive_loss","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/captioner/modeling_blip.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/captioner/modeling_blip.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"code_sha256_prefix":"0f0179451c7c8909","entry":"cut_dialogue_history","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/utils/chatbot.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/utils/chatbot.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0f0179451c7c8909"}},{"code_sha256_prefix":"e8bafcb096991087","entry":"prompts","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/utils/chatbot.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/utils/chatbot.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e8bafcb096991087"}},{"code_sha256_prefix":"a5e8522096c36f22","entry":"blip_loss","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/captioner/modeling_blip.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/captioner/modeling_blip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a5e8522096c36f22"}},{"code_sha256_prefix":"ce21ed86e2cfbd5d","entry":"boundary","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/captioner/base_captioner.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/captioner/base_captioner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ce21ed86e2cfbd5d"}},{"code_sha256_prefix":"5ae4d76bf88ad349","entry":"get_new_image_name","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/utils/chatbot.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/utils/chatbot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5ae4d76bf88ad349"}},{"code_sha256_prefix":"91c053efaa6c0477","entry":"gt_bbox","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/utils/densecap_painter.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/utils/densecap_painter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"91c053efaa6c0477"}},{"code_sha256_prefix":"46167d2d7c39ffb7","entry":"new_seg_to_box","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/captioner/base_captioner.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/captioner/base_captioner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"46167d2d7c39ffb7"}},{"code_sha256_prefix":"68ef60bd886a1090","entry":"parse_bbox","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/utils/densecap_painter.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/utils/densecap_painter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"68ef60bd886a1090"}},{"code_sha256_prefix":"ce858c1a6ea89f7c","entry":"seg_to_box","repo":"ttengwang/caption-anything","repo_kind":"official","path":"caption_anything/captioner/base_captioner.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/captioner/base_captioner.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ce858c1a6ea89f7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}