{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ANDH54TZEVMCXUJFFMR3LGBX5R","short_pith_number":"pith:ANDH54TZ","schema_version":"1.0","canonical_sha256":"03467ef27925582bd1252b23b59837ec7083a620f4ed4af9d4521ddbb97b88ea","source":{"kind":"arxiv","id":"2209.12362","version":4},"attestation_state":"computed","paper":{"title":"Multi-dataset Training of Transformers for Robust Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Enwei Zhang, Junwei Liang, Jun Zhang","submitted_at":"2022-09-26T01:30:43Z","abstract_excerpt":"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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.12362","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-26T01:30:43Z","cross_cats_sorted":[],"title_canon_sha256":"55a16eb0e4e85de3717374b6d860a787cf1fb2467b28cbe494ab387f1f6d8899","abstract_canon_sha256":"c784a3e2cfcf16ff27d3292651f1ff94a01ebf0a039edccbeb8c7f5b3e6c7dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:19.163344Z","signature_b64":"7XNKP1oOL09dfUVXBYjrzPuUP5gNsbJufs02GxIzOmwqRdzbnfD5UsQQnPSVt/AfPKizTsGlEoKyHY3B8hCtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03467ef27925582bd1252b23b59837ec7083a620f4ed4af9d4521ddbb97b88ea","last_reissued_at":"2026-07-05T05:19:19.162918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:19.162918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-dataset Training of Transformers for Robust Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Enwei Zhang, Junwei Liang, Jun Zhang","submitted_at":"2022-09-26T01:30:43Z","abstract_excerpt":"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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12362","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.12362/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.12362","created_at":"2026-07-05T05:19:19.162973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12362v4","created_at":"2026-07-05T05:19:19.162973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12362","created_at":"2026-07-05T05:19:19.162973+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANDH54TZEVMC","created_at":"2026-07-05T05:19:19.162973+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANDH54TZEVMCXUJF","created_at":"2026-07-05T05:19:19.162973+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANDH54TZ","created_at":"2026-07-05T05:19:19.162973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R","json":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R.json","graph_json":"https://pith.science/api/pith-number/ANDH54TZEVMCXUJFFMR3LGBX5R/graph.json","events_json":"https://pith.science/api/pith-number/ANDH54TZEVMCXUJFFMR3LGBX5R/events.json","paper":"https://pith.science/paper/ANDH54TZ"},"agent_actions":{"view_html":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R","download_json":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R.json","view_paper":"https://pith.science/paper/ANDH54TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12362&json=true","fetch_graph":"https://pith.science/api/pith-number/ANDH54TZEVMCXUJFFMR3LGBX5R/graph.json","fetch_events":"https://pith.science/api/pith-number/ANDH54TZEVMCXUJFFMR3LGBX5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R/action/storage_attestation","attest_author":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R/action/author_attestation","sign_citation":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R/action/citation_signature","submit_replication":"https://pith.science/pith/ANDH54TZEVMCXUJFFMR3LGBX5R/action/replication_record"}},"created_at":"2026-07-05T05:19:19.162973+00:00","updated_at":"2026-07-05T05:19:19.162973+00:00"}