{"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/mikasa-multi-key-anchor-scene-aware","title":"MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding","arxiv_id":"2403.03077","date":"2024-03-05","proceeding":"CVPR 2024 1","authors":["Chun-Peng Chang","Shaoxiang Wang","Alain Pagani","Didier Stricker"],"abstract":"3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.","url_abs":"https://arxiv.org/abs/2403.03077v4","url_pdf":"https://arxiv.org/pdf/2403.03077v4.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":"mikasa-multi-key-anchor-scene-aware","repo_url":"https://github.com/dfki-av/mikasa-3dvg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-visual-grounding","task_name":"3D visual grounding"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.03077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03077"}},"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/dfki-av/mikasa-3dvg","reach":null}],"summary":{"ran":11,"unverified":5},"by_repo_kind":{"official":{"samples":16,"ran":11,"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":16,"samples":[{"code_sha256_prefix":"c9ea4b32ab8ee01d","entry":"BatchNorm2d","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"c9ea4b32ab8ee01d"}},{"code_sha256_prefix":"43954295982678e1","entry":"Conv2d","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43954295982678e1"}},{"code_sha256_prefix":"a2c9643fb81b1320","entry":"CrossFFN","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"a2c9643fb81b1320"}},{"code_sha256_prefix":"7eb05f38c1da0278","entry":"FeedForwardLayer","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"7eb05f38c1da0278"}},{"code_sha256_prefix":"fbfaf9b85641a7d4","entry":"FusionNet","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"fbfaf9b85641a7d4"}},{"code_sha256_prefix":"d0c66f6eec198b93","entry":"GroupAll","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0c66f6eec198b93"}},{"code_sha256_prefix":"c6818d25fb38e40e","entry":"MultiHeadSpatialNet","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"c6818d25fb38e40e"}},{"code_sha256_prefix":"79ba2e730dfd23fc","entry":"QueryAndGroup","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"79ba2e730dfd23fc"}},{"code_sha256_prefix":"ce88d757651269ea","entry":"SharedMLP","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","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":"ce88d757651269ea"}},{"code_sha256_prefix":"f3c2a0236652d30c","entry":"_BNBase","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3c2a0236652d30c"}},{"code_sha256_prefix":"29953e9c8508d4e0","entry":"_ConvBase","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29953e9c8508d4e0"}},{"code_sha256_prefix":"234728b3b9078cf1","entry":"MiKASA_transformer","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.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":"234728b3b9078cf1"}},{"code_sha256_prefix":"7225d8c84c7f69c2","entry":"PointNetPP","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.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":"7225d8c84c7f69c2"}},{"code_sha256_prefix":"644b83bc52ec1cc1","entry":"PointnetSAModuleMSG","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.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":"644b83bc52ec1cc1"}},{"code_sha256_prefix":"a7de4c208ca1025c","entry":"_PointnetSAModuleBase","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.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":"a7de4c208ca1025c"}},{"code_sha256_prefix":"775337099d9f9b3c","entry":"break_up_pc","repo":"dfki-av/mikasa-3dvg","repo_kind":"official","path":"models/MiKASA_transformer.py","file_url":"https://github.com/dfki-av/mikasa-3dvg/blob/HEAD/models/MiKASA_transformer.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":"775337099d9f9b3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}