{"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/multimodal-explanations-justifying-decisions","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","arxiv_id":"1802.08129","date":"2018-02-15","proceeding":"CVPR 2018 6","authors":["Dong Huk Park","Lisa Anne Hendricks","Zeynep Akata","Anna Rohrbach","Bernt Schiele","Trevor Darrell","Marcus Rohrbach"],"abstract":"Deep models that are both effective and explainable are desirable in many\nsettings; prior explainable models have been unimodal, offering either\nimage-based visualization of attention weights or text-based generation of\npost-hoc justifications. We propose a multimodal approach to explanation, and\nargue that the two modalities provide complementary explanatory strengths. We\ncollect two new datasets to define and evaluate this task, and propose a novel\nmodel which can provide joint textual rationale generation and attention\nvisualization. Our datasets define visual and textual justifications of a\nclassification decision for activity recognition tasks (ACT-X) and for visual\nquestion answering tasks (VQA-X). We quantitatively show that training with the\ntextual explanations not only yields better textual justification models, but\nalso better localizes the evidence that supports the decision. We also\nqualitatively show cases where visual explanation is more insightful than\ntextual explanation, and vice versa, supporting our thesis that multimodal\nexplanation models offer significant benefits over unimodal approaches.","url_abs":"http://arxiv.org/abs/1802.08129v1","url_pdf":"http://arxiv.org/pdf/1802.08129v1.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":"multimodal-explanations-justifying-decisions","repo_url":"https://github.com/Seth-Park/MultimodalExplanations","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"explainable-models","task_name":"Explainable Models"},{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.08129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08129"}},"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/Seth-Park/MultimodalExplanations","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"b3d40d8fb19d0215","entry":"verify_folder","repo":"Seth-Park/MultimodalExplanations","repo_kind":"official","path":"PJ-X-ACT/generate_act_exp/generate_explanation.py","file_url":"https://github.com/Seth-Park/MultimodalExplanations/blob/HEAD/PJ-X-ACT/generate_act_exp/generate_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b3d40d8fb19d0215"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}