{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OXEX2RUFAYMTKF6RTC77MSBPPR","short_pith_number":"pith:OXEX2RUF","schema_version":"1.0","canonical_sha256":"75c97d468506193517d198bff6482f7c43f025d4b9156a62f6ec43abf8f09114","source":{"kind":"arxiv","id":"2504.07785","version":1},"attestation_state":"computed","paper":{"title":"Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lechao Cheng, Meng Wang, Yan Zhang, Yaxiong Wang, Zhun Zhong","submitted_at":"2025-04-10T14:22:15Z","abstract_excerpt":"Micro-Action Recognition (MAR) aims to classify subtle human actions in video. However, annotating MAR datasets is particularly challenging due to the subtlety of actions. To this end, we introduce the setting of Semi-Supervised MAR (SSMAR), where only a part of samples are labeled. We first evaluate traditional Semi-Supervised Learning (SSL) methods to SSMAR and find that these methods tend to overfit on inaccurate pseudo-labels, leading to error accumulation and degraded performance. This issue primarily arises from the common practice of directly using the predictions of classifier as pseud"},"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":"2504.07785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T14:22:15Z","cross_cats_sorted":[],"title_canon_sha256":"0781a3d334d309d4b3306e5da2c77bbc595b9712f8afc0d152547646479130d2","abstract_canon_sha256":"4b18918f211a0251ae2dbb64d5c5d5b8a8372f7211038a4679409681f5d0f193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:14.837902Z","signature_b64":"mgAD1eNosHL24djtx7ixbhSpupKwIpDcaw+QTctIlqMukraMQRcfJ74AWNdKUjnLbj0kBRiZGHOnzoLb0UKHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c97d468506193517d198bff6482f7c43f025d4b9156a62f6ec43abf8f09114","last_reissued_at":"2026-07-05T10:47:14.837438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:14.837438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lechao Cheng, Meng Wang, Yan Zhang, Yaxiong Wang, Zhun Zhong","submitted_at":"2025-04-10T14:22:15Z","abstract_excerpt":"Micro-Action Recognition (MAR) aims to classify subtle human actions in video. However, annotating MAR datasets is particularly challenging due to the subtlety of actions. To this end, we introduce the setting of Semi-Supervised MAR (SSMAR), where only a part of samples are labeled. We first evaluate traditional Semi-Supervised Learning (SSL) methods to SSMAR and find that these methods tend to overfit on inaccurate pseudo-labels, leading to error accumulation and degraded performance. This issue primarily arises from the common practice of directly using the predictions of classifier as pseud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07785","kind":"arxiv","version":1},"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/2504.07785/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":"2504.07785","created_at":"2026-07-05T10:47:14.837489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07785v1","created_at":"2026-07-05T10:47:14.837489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07785","created_at":"2026-07-05T10:47:14.837489+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXEX2RUFAYMT","created_at":"2026-07-05T10:47:14.837489+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXEX2RUFAYMTKF6R","created_at":"2026-07-05T10:47:14.837489+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXEX2RUF","created_at":"2026-07-05T10:47:14.837489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12848","citing_title":"Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR","json":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR.json","graph_json":"https://pith.science/api/pith-number/OXEX2RUFAYMTKF6RTC77MSBPPR/graph.json","events_json":"https://pith.science/api/pith-number/OXEX2RUFAYMTKF6RTC77MSBPPR/events.json","paper":"https://pith.science/paper/OXEX2RUF"},"agent_actions":{"view_html":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR","download_json":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR.json","view_paper":"https://pith.science/paper/OXEX2RUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07785&json=true","fetch_graph":"https://pith.science/api/pith-number/OXEX2RUFAYMTKF6RTC77MSBPPR/graph.json","fetch_events":"https://pith.science/api/pith-number/OXEX2RUFAYMTKF6RTC77MSBPPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR/action/storage_attestation","attest_author":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR/action/author_attestation","sign_citation":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR/action/citation_signature","submit_replication":"https://pith.science/pith/OXEX2RUFAYMTKF6RTC77MSBPPR/action/replication_record"}},"created_at":"2026-07-05T10:47:14.837489+00:00","updated_at":"2026-07-05T10:47:14.837489+00:00"}