{"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/multi-dataset-training-of-transformers-for","title":"Multi-dataset Training of Transformers for Robust Action Recognition","arxiv_id":"2209.12362","date":"2022-09-26","proceeding":null,"authors":["Junwei Liang","Enwei Zhang","Jun Zhang","Chunhua Shen"],"abstract":"We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action recognition in the past decade, it remains challenging yet valuable how to train a single model that can perform well across multiple datasets. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss, aiming to learn robust representations for action recognition. In particular, the informative loss maximizes the expressiveness of the feature embedding while the projection loss for each dataset mines the intrinsic relations between classes across datasets. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2 datasets. Extensive experimental results show that our method can consistently improve state-of-the-art performance. Code and models are released.","url_abs":"https://arxiv.org/abs/2209.12362v4","url_pdf":"https://arxiv.org/pdf/2209.12362v4.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":"multi-dataset-training-of-transformers-for","repo_url":"https://github.com/junweiliang/multitrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.12362","atlas_url":"https://app.syntology.ai/?focus=2209.12362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12362"}},"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":"deterministic:regex_extraction","url":"https://github.com/JunweiLiang/MultiTrain","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junweiliang/multitrain","reach":null}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"ec4d0c57187accb7","entry":"LSEPLoss","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec4d0c57187accb7"}},{"code_sha256_prefix":"0dac89749d6d9308","entry":"MeanAbsoluteError","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.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":"0dac89749d6d9308"}},{"code_sha256_prefix":"038b53347cdfe89b","entry":"NCEandRCE","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"038b53347cdfe89b"}},{"code_sha256_prefix":"5007808e58a0cf6a","entry":"NormalizedSoftTargetCrossEntropy","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5007808e58a0cf6a"}},{"code_sha256_prefix":"95fb2d4c767dc202","entry":"ReverseSoftTargetCrossEntropy","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95fb2d4c767dc202"}},{"code_sha256_prefix":"666787bd3939df7c","entry":"SoftTargetCrossEntropy","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"666787bd3939df7c"}},{"code_sha256_prefix":"39a9b846b179205b","entry":"read_val_data","repo":"JunweiLiang/MultiTrain","repo_kind":"official","path":"tools/train_net.py","file_url":"https://github.com/JunweiLiang/MultiTrain/blob/HEAD/tools/train_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39a9b846b179205b"}},{"code_sha256_prefix":"40418acd5604e86d","entry":"MultiHeadLoss","repo":"junweiliang/multitrain","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/junweiliang/multitrain/blob/HEAD/slowfast/models/losses.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":"40418acd5604e86d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}