{"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/multiscale-vision-transformers","title":"Multiscale Vision Transformers","arxiv_id":"2104.11227","date":"2021-04-22","proceeding":"ICCV 2021 10","authors":["Haoqi Fan","Bo Xiong","Karttikeya Mangalam","Yanghao Li","Zhicheng Yan","Jitendra Malik","Christoph Feichtenhofer"],"abstract":"We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https://github.com/facebookresearch/SlowFast","url_abs":"https://arxiv.org/abs/2104.11227v1","url_pdf":"https://arxiv.org/pdf/2104.11227v1.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":"multiscale-vision-transformers","repo_url":"https://github.com/facebookresearch/SlowFast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/facebookresearch/hiera","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/facebookresearch/pytorchvideo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/junweiliang/multitrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/rohanshad/cmr_transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/wangjk666/stts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/facebookresearch/mvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multiscale-vision-transformers","repo_url":"https://github.com/towhee-io/towhee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"mvit","method_name":"MViT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"mvit","name":"MViT","full_name":"Multiscale Vision Transformer"}],"results":[{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"MViT-B-24, 32x3 (Kinetics-600 pretraining)","rank_in_archive_order":14,"of":49,"metrics":{"MAP":"47.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"MViT-B, 32x3 (Kinetics-600 pretraining)","rank_in_archive_order":16,"of":49,"metrics":{"MAP":"47.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"MViT-B-24, 32x3 (Kinetics-400 pretraining)","rank_in_archive_order":17,"of":49,"metrics":{"MAP":"46.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"MViT-B, 32x3 (Kinetics-400 pretraining)","rank_in_archive_order":19,"of":49,"metrics":{"MAP":"44.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"MViT-B, 16x4 (Kinetics-600 pretraining)","rank_in_archive_order":21,"of":49,"metrics":{"MAP":"43.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"MViT-B, 16x4 (Kinetics-400 pretraining)","rank_in_archive_order":33,"of":49,"metrics":{"MAP":"40"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"MViT-B, 64x3","rank_in_archive_order":87,"of":207,"metrics":{"Acc@1":"81.2","Acc@5":"95.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"MViT-B, 32x3","rank_in_archive_order":103,"of":207,"metrics":{"Acc@1":"80.2","Acc@5":"94.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"MViT-B, 16x4","rank_in_archive_order":126,"of":207,"metrics":{"Acc@1":"78.4","Acc@5":"93.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"MViT-S","rank_in_archive_order":151,"of":207,"metrics":{"Acc@1":"76","Acc@5":"92.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"MViT-B-24, 32x3","rank_in_archive_order":36,"of":65,"metrics":{"Top-1 Accuracy":"83.8","Top-5 Accuracy":"96.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"MViT-B, 32x3","rank_in_archive_order":39,"of":65,"metrics":{"Top-1 Accuracy":"83.4","Top-5 Accuracy":"96.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"MViT-B, 16x4","rank_in_archive_order":44,"of":65,"metrics":{"Top-1 Accuracy":"82.1","Top-5 Accuracy":"95.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"MViT-B-24, 32x3 (Kinetics-600 pretraining)","rank_in_archive_order":27,"of":38,"metrics":{"mAP":"28.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"MViT-B, 32x3 (Kinetics-500 pretraining)","rank_in_archive_order":28,"of":38,"metrics":{"mAP":"27.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"MViT-B, 64x3 (Kinetics-400 pretraining)","rank_in_archive_order":30,"of":38,"metrics":{"mAP":"27.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"MViT-B, 32x3 (Kinetics-400 pretraining)","rank_in_archive_order":32,"of":38,"metrics":{"mAP":"26.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"MViT-B, 16x4 (Kinetics-600 pretraining)","rank_in_archive_order":35,"of":38,"metrics":{"mAP":"26.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"MViT-B, 16x4 (Kinetics-400 pretraining)","rank_in_archive_order":36,"of":38,"metrics":{"mAP":"24.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"MViT-B-24, 32x3","rank_in_archive_order":49,"of":123,"metrics":{"GFLOPs":"236x3","Parameters":"53.2M","Top-1 Accuracy":"68.7","Top-5 Accuracy":"91.5"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"MViT-B, 32x3(Kinetics600 pretrain)","rank_in_archive_order":57,"of":123,"metrics":{"GFLOPs":"170x3","Parameters":"36.6","Top-1 Accuracy":"67.8","Top-5 Accuracy":"91.3"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"MViT-B, 16x4","rank_in_archive_order":82,"of":123,"metrics":{"Top-1 Accuracy":"66.2","Top-5 Accuracy":"90.2"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MViT-B-24","rank_in_archive_order":287,"of":1060,"metrics":{"GFLOPs":"32.7","Number of params":"72.9M","Top 1 Accuracy":"84.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MViT-B-16","rank_in_archive_order":479,"of":1060,"metrics":{"GFLOPs":"7.8","Number of params":"37M","Top 1 Accuracy":"83.0%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}},"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/facebookresearch/hiera","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junweiliang/multitrain","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/SlowFast","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/pytorchvideo","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wangjk666/stts","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rohanshad/cmr_transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/towhee-io/towhee","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/mvit","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"ran_fixture":2,"ran_honours":1,"unverified":13},"by_repo_kind":{"listed":{"samples":26,"ran":13,"repositories":2}},"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":5,"samples":[{"code_sha256_prefix":"aabc00fba35e5b60","entry":"AttentionPool","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"aabc00fba35e5b60"}},{"code_sha256_prefix":"8eadaa524165fa27","entry":"DropPath","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","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":"8eadaa524165fa27"}},{"code_sha256_prefix":"137b894a55248107","entry":"LayerNorm","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"137b894a55248107"}},{"code_sha256_prefix":"11bb9021dd0d5f1d","entry":"MaxPool3d","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"11bb9021dd0d5f1d"}},{"code_sha256_prefix":"9220e80dfcec043a","entry":"Mlp","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"9220e80dfcec043a"}},{"code_sha256_prefix":"73d46d814f26bc08","entry":"MultiscaleVisionTransformers","repo":"rohanshad/cmr_transformer","repo_kind":"listed","path":"arch/mvit.py","file_url":"https://github.com/rohanshad/cmr_transformer/blob/HEAD/arch/mvit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"73d46d814f26bc08"}},{"code_sha256_prefix":"56cfb3a853df70e9","entry":"PatchEmbed","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"56cfb3a853df70e9"}},{"code_sha256_prefix":"ca6f8c79a4ba5eea","entry":"Sigmoid","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"ca6f8c79a4ba5eea"}},{"code_sha256_prefix":"8e8401b5c2cbe9af","entry":"SpatioTemporalClsPositionalEncoding","repo":"rohanshad/cmr_transformer","repo_kind":"listed","path":"arch/mvit.py","file_url":"https://github.com/rohanshad/cmr_transformer/blob/HEAD/arch/mvit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8e8401b5c2cbe9af"}},{"code_sha256_prefix":"a84009ea4b4e7411","entry":"TransformerBasicHead","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.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":"a84009ea4b4e7411"}},{"code_sha256_prefix":"63080b2b0157a638","entry":"drop_path_func","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63080b2b0157a638"}},{"code_sha256_prefix":"fa1b9bbe882fd839","entry":"find_most_h_w","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fa1b9bbe882fd839"}},{"code_sha256_prefix":"c828b94ed536888e","entry":"round_width","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c828b94ed536888e"}},{"code_sha256_prefix":"e085e89664c8c8f1","entry":"Add","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e085e89664c8c8f1"}},{"code_sha256_prefix":"c8f04d0354d412d8","entry":"Clone","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c8f04d0354d412d8"}},{"code_sha256_prefix":"f51d56342db748dc","entry":"Conv3d","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f51d56342db748dc"}},{"code_sha256_prefix":"c6b33d8045bad24a","entry":"IndexSelect","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6b33d8045bad24a"}},{"code_sha256_prefix":"b3cb3600d1ec619e","entry":"MViT","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b3cb3600d1ec619e"}},{"code_sha256_prefix":"d0c301eed0a9217c","entry":"MultiScaleAttention","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0c301eed0a9217c"}},{"code_sha256_prefix":"2e7ddef56b034315","entry":"MultiScaleBlock","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2e7ddef56b034315"}},{"code_sha256_prefix":"31c2f4da4c4a0948","entry":"_init_vit_weights","repo":"rohanshad/cmr_transformer","repo_kind":"listed","path":"arch/mvit.py","file_url":"https://github.com/rohanshad/cmr_transformer/blob/HEAD/arch/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"31c2f4da4c4a0948"}},{"code_sha256_prefix":"4038555957e35d15","entry":"align_scale","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4038555957e35d15"}},{"code_sha256_prefix":"59e53e1981813f80","entry":"compute_rollout_attention","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59e53e1981813f80"}},{"code_sha256_prefix":"081229a28d5f0e17","entry":"init_net_weights","repo":"rohanshad/cmr_transformer","repo_kind":"listed","path":"arch/mvit.py","file_url":"https://github.com/rohanshad/cmr_transformer/blob/HEAD/arch/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"081229a28d5f0e17"}},{"code_sha256_prefix":"a6b157934033010d","entry":"resize_last_dim_to_most","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/multiscale_vision_transformers/mvit.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/multiscale_vision_transformers/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6b157934033010d"}},{"code_sha256_prefix":"f69f7538b6980470","entry":"set_attributes","repo":"rohanshad/cmr_transformer","repo_kind":"listed","path":"arch/mvit.py","file_url":"https://github.com/rohanshad/cmr_transformer/blob/HEAD/arch/mvit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f69f7538b6980470"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}