{"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/advancing-semantic-future-prediction-through","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","arxiv_id":"2501.08303","date":"2025-01-14","proceeding":"CVPR 2025 1","authors":["Efstathios Karypidis","Ioannis Kakogeorgiou","Spyros Gidaris","Nikos Komodakis"],"abstract":"Semantic future prediction is important for autonomous systems navigating dynamic environments. This paper introduces FUTURIST, a method for multimodal future semantic prediction that uses a unified and efficient visual sequence transformer architecture. Our approach incorporates a multimodal masked visual modeling objective and a novel masking mechanism designed for multimodal training. This allows the model to effectively integrate visible information from various modalities, improving prediction accuracy. Additionally, we propose a VAE-free hierarchical tokenization process, which reduces computational complexity, streamlines the training pipeline, and enables end-to-end training with high-resolution, multimodal inputs. We validate FUTURIST on the Cityscapes dataset, demonstrating state-of-the-art performance in future semantic segmentation for both short- and mid-term forecasting. We provide the implementation code at https://github.com/Sta8is/FUTURIST .","url_abs":"https://arxiv.org/abs/2501.08303v1","url_pdf":"https://arxiv.org/pdf/2501.08303v1.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":"advancing-semantic-future-prediction-through","repo_url":"https://github.com/sta8is/futurist","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"future-prediction","task_name":"Future prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.08303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08303"}},"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/sta8is/futurist","reach":null}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"8a974cbe1001d2e3","entry":"AddBroadcastPosEmbed","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a974cbe1001d2e3"}},{"code_sha256_prefix":"f7968fce35e007d8","entry":"Attention","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7968fce35e007d8"}},{"code_sha256_prefix":"73f0b6932d0b0069","entry":"FeedForward","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73f0b6932d0b0069"}},{"code_sha256_prefix":"2cd986aaeac6b22b","entry":"PreNorm","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cd986aaeac6b22b"}},{"code_sha256_prefix":"974919609ba7f2ff","entry":"TransformerEncoder","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"974919609ba7f2ff"}},{"code_sha256_prefix":"36d663d1929fba10","entry":"TransformerEncoderSeperableAttention","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36d663d1929fba10"}},{"code_sha256_prefix":"da9bf75a3bed9d36","entry":"Futurist","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.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":"da9bf75a3bed9d36"}},{"code_sha256_prefix":"ad84686f18317ddd","entry":"MaskTransformer","repo":"sta8is/futurist","repo_kind":"official","path":"src/futurist.py","file_url":"https://github.com/sta8is/futurist/blob/HEAD/src/futurist.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":"ad84686f18317ddd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}