{"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/compact-trilinear-interaction-for-visual","title":"Compact Trilinear Interaction for Visual Question Answering","arxiv_id":"1909.11874","date":"2019-09-26","proceeding":"ICCV 2019 10","authors":["Tuong Do","Thanh-Toan Do","Huy Tran","Erman Tjiputra","Quang D. Tran"],"abstract":"In Visual Question Answering (VQA), answers have a great correlation with question meaning and visual contents. Thus, to selectively utilize image, question and answer information, we propose a novel trilinear interaction model which simultaneously learns high level associations between these three inputs. In addition, to overcome the interaction complexity, we introduce a multimodal tensor-based PARALIND decomposition which efficiently parameterizes trilinear interaction between the three inputs. Moreover, knowledge distillation is first time applied in Free-form Opened-ended VQA. It is not only for reducing the computational cost and required memory but also for transferring knowledge from trilinear interaction model to bilinear interaction model. The extensive experiments on benchmarking datasets TDIUC, VQA-2.0, and Visual7W show that the proposed compact trilinear interaction model achieves state-of-the-art results when using a single model on all three datasets.","url_abs":"https://arxiv.org/abs/1909.11874v1","url_pdf":"https://arxiv.org/pdf/1909.11874v1.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":"compact-trilinear-interaction-for-visual","repo_url":"https://github.com/aioz-ai/ICCV19_VQA-CTI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"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":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-tdiuc","task":"Visual Question Answering (VQA)","dataset":"TDIUC","model":"BAN2-CTI","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"87"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BAN2-CTI","rank_in_archive_order":40,"of":56,"metrics":{"Accuracy":"67.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-visual7w","task":"Visual Question Answering (VQA)","dataset":"Visual7W","model":"CTI (with Boxes)","rank_in_archive_order":2,"of":4,"metrics":{"Percentage correct":"72.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.11874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11874"}},"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/aioz-ai/ICCV19_VQA-CTI","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"cf2efa825f4afaf0","entry":"answer_filter","repo":"aioz-ai/ICCV19_VQA-CTI","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/aioz-ai/ICCV19_VQA-CTI/blob/HEAD/src/dataset.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2efa825f4afaf0"}},{"code_sha256_prefix":"dae936b303032b0f","entry":"ModeProduct","repo":"aioz-ai/ICCV19_VQA-CTI","repo_kind":"official","path":"src/Tensor.py","file_url":"https://github.com/aioz-ai/ICCV19_VQA-CTI/blob/HEAD/src/Tensor.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":"dae936b303032b0f"}},{"code_sha256_prefix":"71aa385eadeb1226","entry":"create_glove_embedding_init","repo":"aioz-ai/ICCV19_VQA-CTI","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/aioz-ai/ICCV19_VQA-CTI/blob/HEAD/src/dataset.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":"71aa385eadeb1226"}},{"code_sha256_prefix":"6652b5d834042107","entry":"load_json","repo":"aioz-ai/ICCV19_VQA-CTI","repo_kind":"official","path":"src/evaluate_TDIUC.py","file_url":"https://github.com/aioz-ai/ICCV19_VQA-CTI/blob/HEAD/src/evaluate_TDIUC.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":"6652b5d834042107"}},{"code_sha256_prefix":"fccda75b0263c740","entry":"tfidf_from_questions","repo":"aioz-ai/ICCV19_VQA-CTI","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/aioz-ai/ICCV19_VQA-CTI/blob/HEAD/src/dataset.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":"fccda75b0263c740"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}