{"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/grounded-entity-landmark-adaptive-pre","title":"Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation","arxiv_id":"2308.12587","date":"2023-08-24","proceeding":"ICCV 2023 1","authors":["Yibo Cui","Liang Xie","Yakun Zhang","Meishan Zhang","Ye Yan","Erwei Yin"],"abstract":"Cross-modal alignment is one key challenge for Vision-and-Language Navigation (VLN). Most existing studies concentrate on mapping the global instruction or single sub-instruction to the corresponding trajectory. However, another critical problem of achieving fine-grained alignment at the entity level is seldom considered. To address this problem, we propose a novel Grounded Entity-Landmark Adaptive (GELA) pre-training paradigm for VLN tasks. To achieve the adaptive pre-training paradigm, we first introduce grounded entity-landmark human annotations into the Room-to-Room (R2R) dataset, named GEL-R2R. Additionally, we adopt three grounded entity-landmark adaptive pre-training objectives: 1) entity phrase prediction, 2) landmark bounding box prediction, and 3) entity-landmark semantic alignment, which explicitly supervise the learning of fine-grained cross-modal alignment between entity phrases and environment landmarks. Finally, we validate our model on two downstream benchmarks: VLN with descriptive instructions (R2R) and dialogue instructions (CVDN). The comprehensive experiments show that our GELA model achieves state-of-the-art results on both tasks, demonstrating its effectiveness and generalizability.","url_abs":"https://arxiv.org/abs/2308.12587v1","url_pdf":"https://arxiv.org/pdf/2308.12587v1.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":"grounded-entity-landmark-adaptive-pre","repo_url":"https://github.com/csir1996/vln-gela","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.12587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12587"}},"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/csir1996/vln-gela","reach":null}],"summary":{"ran":20,"ran_draft_wrong":3,"unverified":7},"by_repo_kind":{"official":{"samples":30,"ran":23,"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":30,"samples":[{"code_sha256_prefix":"3372a10f9d714c01","entry":"BboxPrediction","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"3372a10f9d714c01"}},{"code_sha256_prefix":"f11fe3d331f06585","entry":"BertAttention","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"f11fe3d331f06585"}},{"code_sha256_prefix":"e11f492583515dc1","entry":"BertEmbeddings","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"e11f492583515dc1"}},{"code_sha256_prefix":"80fb8132656f0023","entry":"BertIntermediate","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"80fb8132656f0023"}},{"code_sha256_prefix":"6ef8a8f38e5061ea","entry":"BertLMPredictionHead","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"6ef8a8f38e5061ea"}},{"code_sha256_prefix":"cae60f381a5d3991","entry":"BertLayer","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"cae60f381a5d3991"}},{"code_sha256_prefix":"2076765f9269ebfb","entry":"BertOnlyMLMHead","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"2076765f9269ebfb"}},{"code_sha256_prefix":"c6b2b7a8ef4effa8","entry":"BertOutAttention","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"c6b2b7a8ef4effa8"}},{"code_sha256_prefix":"6b2df70e78c4e5e8","entry":"BertOutput","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"6b2df70e78c4e5e8"}},{"code_sha256_prefix":"a1405b4b0349031c","entry":"BertPredictionHeadTransform","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"a1405b4b0349031c"}},{"code_sha256_prefix":"d50e815eff85ec2b","entry":"BertSelfOutput","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"d50e815eff85ec2b"}},{"code_sha256_prefix":"e438c17327d8794a","entry":"BertXAttention","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"e438c17327d8794a"}},{"code_sha256_prefix":"f1ea5386ce472284","entry":"GIoU_Loss","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1ea5386ce472284"}},{"code_sha256_prefix":"910bb71e7ef2b112","entry":"ImageEmbeddings","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"910bb71e7ef2b112"}},{"code_sha256_prefix":"698a681ee3009703","entry":"ItmPrediction","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"698a681ee3009703"}},{"code_sha256_prefix":"2c41dd19d952d068","entry":"NextActionPrediction","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"2c41dd19d952d068"}},{"code_sha256_prefix":"e35313209150244f","entry":"NextActionRegression","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"e35313209150244f"}},{"code_sha256_prefix":"33a4a4477537ad1c","entry":"Reg_Loss","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33a4a4477537ad1c"}},{"code_sha256_prefix":"db3b410d57d99c4c","entry":"RegionClassification","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"db3b410d57d99c4c"}},{"code_sha256_prefix":"37cdafb5cc664e9a","entry":"SoftDotAttention","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"37cdafb5cc664e9a"}},{"code_sha256_prefix":"eda2157dc8f3fd1d","entry":"SpanPrediction","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"eda2157dc8f3fd1d"}},{"code_sha256_prefix":"b3f29a55ce1e133c","entry":"SpatialRelRegression","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"b3f29a55ce1e133c"}},{"code_sha256_prefix":"3d629255e4cf4ea2","entry":"xyxy2xywh","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d629255e4cf4ea2"}},{"code_sha256_prefix":"8654eadc64d1d6d9","entry":"BertEncoder","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"8654eadc64d1d6d9"}},{"code_sha256_prefix":"181a8da7e0d87dd3","entry":"BertSelfAttention","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"181a8da7e0d87dd3"}},{"code_sha256_prefix":"ed5264df2e315411","entry":"HistoryEmbeddings","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"ed5264df2e315411"}},{"code_sha256_prefix":"3f87e422545347a0","entry":"LXRTXLayer","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"3f87e422545347a0"}},{"code_sha256_prefix":"d236f85a9fdbe5cd","entry":"LxmertEncoder","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"d236f85a9fdbe5cd"}},{"code_sha256_prefix":"b473bd940f0c9a55","entry":"MultiStepNavCMTPreTraining","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"b473bd940f0c9a55"}},{"code_sha256_prefix":"dda880a7d9edaf1b","entry":"NavPreTrainedModel","repo":"csir1996/vln-gela","repo_kind":"official","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.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":"dda880a7d9edaf1b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}