{"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/beyond-embeddings-the-promise-of-visual-table","title":"Beyond Embeddings: The Promise of Visual Table in Visual Reasoning","arxiv_id":"2403.18252","date":"2024-03-27","proceeding":null,"authors":["Yiwu Zhong","Zi-Yuan Hu","Michael R. Lyu","LiWei Wang"],"abstract":"Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often lack access to world knowledge critical for visual reasoning. In this work, we propose Visual Table, a novel form of visual representation tailored for visual reasoning. Visual tables are constructed as hierarchical descriptions of visual scenes, featuring a scene description and multiple object-centric descriptions covering categories, attributes, and knowledge. Thanks to the structural and textual formats, visual tables offer unique advantages over mere visual embeddings, such as interpretability and controllable editing. Furthermore, they deliver instance-level world knowledge and detailed attributes that are essential for visual reasoning. To create visual tables, we develop a generator trained on the dataset with collected, small-scale annotations. Extensive results on 11 visual reasoning benchmarks demonstrate that the generated visual tables significantly outperform previous structural and text-based representations. Moreover, they consistently enhance state-of-the-art multimodal large language models across diverse benchmarks, showcasing their potential for advancing visual reasoning tasks. Our code is available at https://github.com/LaVi-Lab/Visual-Table.","url_abs":"https://arxiv.org/abs/2403.18252v2","url_pdf":"https://arxiv.org/pdf/2403.18252v2.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":"beyond-embeddings-the-promise-of-visual-table","repo_url":"https://github.com/lavi-lab/visual-table","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LLaVA-VT (Vicuna-13B)","rank_in_archive_order":114,"of":231,"metrics":{"GPT-4 score":"39.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LLaVA-VT (Vicuna-7B)","rank_in_archive_order":189,"of":231,"metrics":{"GPT-4 score":"31.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.18252","atlas_url":"https://app.syntology.ai/?focus=2403.18252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18252"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/lavi-lab/visual-table","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":3,"ran_violates":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":8,"ran":8,"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":"42a46570620cd9fa","entry":"get_chunk","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"fb48214e8ea84c17","entry":"get_eval","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/eval_gpt_review_visual.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/eval_gpt_review_visual.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb48214e8ea84c17"}},{"code_sha256_prefix":"bae18947b56f2be1","entry":"is_none","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/model_vqa_mmbench.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/model_vqa_mmbench.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae18947b56f2be1"}},{"code_sha256_prefix":"9b3c1cb391672ccb","entry":"load_image","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/model_vqa_qbench.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/model_vqa_qbench.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b3c1cb391672ccb"}},{"code_sha256_prefix":"763f6fe20bd52fbb","entry":"parse_score","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/eval_gpt_review_visual.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/eval_gpt_review_visual.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"763f6fe20bd52fbb"}},{"code_sha256_prefix":"7beeb01acc36919e","entry":"read_jsonl","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/generate_webpage_data_from_table.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/generate_webpage_data_from_table.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7beeb01acc36919e"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/model_vqa.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"1d45bc90fd0cd90c","entry":"trim_hanging_lines","repo":"lavi-lab/visual-table","repo_kind":"official","path":"llava/eval/generate_webpage_data_from_table.py","file_url":"https://github.com/lavi-lab/visual-table/blob/HEAD/llava/eval/generate_webpage_data_from_table.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d45bc90fd0cd90c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}