{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L22DD7FERQIQ7ABPZPJN7R5POV","short_pith_number":"pith:L22DD7FE","schema_version":"1.0","canonical_sha256":"5eb431fca48c110f802fcbd2dfc7af756dfee9cfc938c3f204690641904f3901","source":{"kind":"arxiv","id":"2401.02138","version":1},"attestation_state":"computed","paper":{"title":"Explore Human Parsing Modality for Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyang Meng, Jinfu Liu, Mengyuan Liu, Nan Dai, Runwei Ding, Shen Zhao, Yuhang Wen","submitted_at":"2024-01-04T08:43:41Z","abstract_excerpt":"Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality limitations. To address this, we introduce human parsing feature map as a novel modality, since it can selectively retain effective semantic features of the body parts, while filtering out most irrelevant noise. We propose a new dual-branch framework called Ensemble Human Parsing and Pose Network (EPP-Net), which is the first to leverage both skeletons and human parsing modalities for ac"},"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":"2401.02138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:43:41Z","cross_cats_sorted":[],"title_canon_sha256":"34f944e7d8cfdc5982ad39cc721180963f6ca23a261747044d70b02aadefced7","abstract_canon_sha256":"a4a29c3cf112b948e60eebf5033ddf175c9e4908033a8360a1b84303d3dd3c84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:11.892077Z","signature_b64":"0PKR+WQ+1+wHRvMiW8caxnn4xvv1tDs7mQm1LLgDmRYGsWKItMy45JCJV1R0FG3sSU20mb8e1eigfZ8PWF+EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb431fca48c110f802fcbd2dfc7af756dfee9cfc938c3f204690641904f3901","last_reissued_at":"2026-07-05T07:30:11.891618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:11.891618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore Human Parsing Modality for Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyang Meng, Jinfu Liu, Mengyuan Liu, Nan Dai, Runwei Ding, Shen Zhao, Yuhang Wen","submitted_at":"2024-01-04T08:43:41Z","abstract_excerpt":"Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality limitations. To address this, we introduce human parsing feature map as a novel modality, since it can selectively retain effective semantic features of the body parts, while filtering out most irrelevant noise. We propose a new dual-branch framework called Ensemble Human Parsing and Pose Network (EPP-Net), which is the first to leverage both skeletons and human parsing modalities for ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02138","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/2401.02138/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":"2401.02138","created_at":"2026-07-05T07:30:11.891680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02138v1","created_at":"2026-07-05T07:30:11.891680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02138","created_at":"2026-07-05T07:30:11.891680+00:00"},{"alias_kind":"pith_short_12","alias_value":"L22DD7FERQIQ","created_at":"2026-07-05T07:30:11.891680+00:00"},{"alias_kind":"pith_short_16","alias_value":"L22DD7FERQIQ7ABP","created_at":"2026-07-05T07:30:11.891680+00:00"},{"alias_kind":"pith_short_8","alias_value":"L22DD7FE","created_at":"2026-07-05T07:30:11.891680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02094","citing_title":"SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV","json":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV.json","graph_json":"https://pith.science/api/pith-number/L22DD7FERQIQ7ABPZPJN7R5POV/graph.json","events_json":"https://pith.science/api/pith-number/L22DD7FERQIQ7ABPZPJN7R5POV/events.json","paper":"https://pith.science/paper/L22DD7FE"},"agent_actions":{"view_html":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV","download_json":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV.json","view_paper":"https://pith.science/paper/L22DD7FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02138&json=true","fetch_graph":"https://pith.science/api/pith-number/L22DD7FERQIQ7ABPZPJN7R5POV/graph.json","fetch_events":"https://pith.science/api/pith-number/L22DD7FERQIQ7ABPZPJN7R5POV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV/action/storage_attestation","attest_author":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV/action/author_attestation","sign_citation":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV/action/citation_signature","submit_replication":"https://pith.science/pith/L22DD7FERQIQ7ABPZPJN7R5POV/action/replication_record"}},"created_at":"2026-07-05T07:30:11.891680+00:00","updated_at":"2026-07-05T07:30:11.891680+00:00"}