{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H3WD4SS5SKMLVQF6SMUS2ACJ5T","short_pith_number":"pith:H3WD4SS5","schema_version":"1.0","canonical_sha256":"3eec3e4a5d9298bac0be93292d0049ecc1d56b066f617fa82ea530ffaf847b4f","source":{"kind":"arxiv","id":"2306.07576","version":1},"attestation_state":"computed","paper":{"title":"Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beibei Zhang, Haipeng Chen, Kui Ren, Shuang Wu, Yingda Lyu, Yuheng Yang, Zhenguang Liu, Zhibo Wang","submitted_at":"2023-06-13T06:56:09Z","abstract_excerpt":"Action recognition has long been a fundamental and intriguing problem in artificial intelligence. The task is challenging due to the high dimensionality nature of an action, as well as the subtle motion details to be considered. Current state-of-the-art approaches typically learn from articulated motion sequences in the straightforward 3D Euclidean space. However, the vanilla Euclidean space is not efficient for modeling important motion characteristics such as the joint-wise angular acceleration, which reveals the driving force behind the motion. Moreover, current methods typically attend to "},"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":"2306.07576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T06:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"99f3f17f3642c78174bad1aa75238b1a886f89dff8924728682f5ee1dc18ebc8","abstract_canon_sha256":"cb4c0e71969d0ffc25e355978ef8279dc8d8bd0c608fc46c585c785aa31e54aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:59.857876Z","signature_b64":"G3oXsSgZ1uShWJersKWkmtQESmWrhsMH/smHJdj97E5kWEvmDDtLbizZQEf7jY7geUyW67S0ULiGbDAD/HskCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eec3e4a5d9298bac0be93292d0049ecc1d56b066f617fa82ea530ffaf847b4f","last_reissued_at":"2026-07-05T09:53:59.857397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:59.857397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beibei Zhang, Haipeng Chen, Kui Ren, Shuang Wu, Yingda Lyu, Yuheng Yang, Zhenguang Liu, Zhibo Wang","submitted_at":"2023-06-13T06:56:09Z","abstract_excerpt":"Action recognition has long been a fundamental and intriguing problem in artificial intelligence. The task is challenging due to the high dimensionality nature of an action, as well as the subtle motion details to be considered. Current state-of-the-art approaches typically learn from articulated motion sequences in the straightforward 3D Euclidean space. However, the vanilla Euclidean space is not efficient for modeling important motion characteristics such as the joint-wise angular acceleration, which reveals the driving force behind the motion. Moreover, current methods typically attend to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07576","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/2306.07576/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":"2306.07576","created_at":"2026-07-05T09:53:59.857454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07576v1","created_at":"2026-07-05T09:53:59.857454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07576","created_at":"2026-07-05T09:53:59.857454+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3WD4SS5SKML","created_at":"2026-07-05T09:53:59.857454+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3WD4SS5SKMLVQF6","created_at":"2026-07-05T09:53:59.857454+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3WD4SS5","created_at":"2026-07-05T09:53:59.857454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00915","citing_title":"3D Skeleton-Based Action Recognition: A Review","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T","json":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T.json","graph_json":"https://pith.science/api/pith-number/H3WD4SS5SKMLVQF6SMUS2ACJ5T/graph.json","events_json":"https://pith.science/api/pith-number/H3WD4SS5SKMLVQF6SMUS2ACJ5T/events.json","paper":"https://pith.science/paper/H3WD4SS5"},"agent_actions":{"view_html":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T","download_json":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T.json","view_paper":"https://pith.science/paper/H3WD4SS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07576&json=true","fetch_graph":"https://pith.science/api/pith-number/H3WD4SS5SKMLVQF6SMUS2ACJ5T/graph.json","fetch_events":"https://pith.science/api/pith-number/H3WD4SS5SKMLVQF6SMUS2ACJ5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T/action/storage_attestation","attest_author":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T/action/author_attestation","sign_citation":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T/action/citation_signature","submit_replication":"https://pith.science/pith/H3WD4SS5SKMLVQF6SMUS2ACJ5T/action/replication_record"}},"created_at":"2026-07-05T09:53:59.857454+00:00","updated_at":"2026-07-05T09:53:59.857454+00:00"}