{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DQV4JRILVK6FPBMLYWV3TZ6WYR","short_pith_number":"pith:DQV4JRIL","schema_version":"1.0","canonical_sha256":"1c2bc4c50baabc57858bc5abb9e7d6c451d0a39923e2f1de819a4f6ab48e5998","source":{"kind":"arxiv","id":"1805.08162","version":1},"attestation_state":"computed","paper":{"title":"VideoCapsuleNet: A Simplified Network for Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Duarte, Mubarak Shah, Yogesh S Rawat","submitted_at":"2018-05-21T16:28:47Z","abstract_excerpt":"The recent advances in Deep Convolutional Neural Networks (DCNNs) have shown extremely good results for video human action classification, however, action detection is still a challenging problem. The current action detection approaches follow a complex pipeline which involves multiple tasks such as tube proposals, optical flow, and tube classification. In this work, we present a more elegant solution for action detection based on the recently developed capsule network. We propose a 3D capsule network for videos, called VideoCapsuleNet: a unified network for action detection which can jointly "},"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":"1805.08162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T16:28:47Z","cross_cats_sorted":[],"title_canon_sha256":"19d2d79a8e731d2b63c426dda2ba74bf66ec6a971c01dfb61c1100a8a383b449","abstract_canon_sha256":"be536736b9aa80dfde7e8c1afe0cf44f97d2e60e1d74d659268363ef8211f62e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:31.500048Z","signature_b64":"Bxk7PTBUBSlFj09j+UcWNTYozyWi7+W9Hzhh5dJTg/3URQLjR8Dd8eTKqxyiysA+hfidQfblZYhcRXG77UJ7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2bc4c50baabc57858bc5abb9e7d6c451d0a39923e2f1de819a4f6ab48e5998","last_reissued_at":"2026-05-18T00:15:31.499492Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:31.499492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoCapsuleNet: A Simplified Network for Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Duarte, Mubarak Shah, Yogesh S Rawat","submitted_at":"2018-05-21T16:28:47Z","abstract_excerpt":"The recent advances in Deep Convolutional Neural Networks (DCNNs) have shown extremely good results for video human action classification, however, action detection is still a challenging problem. The current action detection approaches follow a complex pipeline which involves multiple tasks such as tube proposals, optical flow, and tube classification. In this work, we present a more elegant solution for action detection based on the recently developed capsule network. We propose a 3D capsule network for videos, called VideoCapsuleNet: a unified network for action detection which can jointly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08162","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":""},"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":"1805.08162","created_at":"2026-05-18T00:15:31.499577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08162v1","created_at":"2026-05-18T00:15:31.499577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08162","created_at":"2026-05-18T00:15:31.499577+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQV4JRILVK6F","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQV4JRILVK6FPBML","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQV4JRIL","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01847","citing_title":"Deformable Tube Network for Action Detection in Videos","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR","json":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR.json","graph_json":"https://pith.science/api/pith-number/DQV4JRILVK6FPBMLYWV3TZ6WYR/graph.json","events_json":"https://pith.science/api/pith-number/DQV4JRILVK6FPBMLYWV3TZ6WYR/events.json","paper":"https://pith.science/paper/DQV4JRIL"},"agent_actions":{"view_html":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR","download_json":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR.json","view_paper":"https://pith.science/paper/DQV4JRIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08162&json=true","fetch_graph":"https://pith.science/api/pith-number/DQV4JRILVK6FPBMLYWV3TZ6WYR/graph.json","fetch_events":"https://pith.science/api/pith-number/DQV4JRILVK6FPBMLYWV3TZ6WYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR/action/storage_attestation","attest_author":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR/action/author_attestation","sign_citation":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR/action/citation_signature","submit_replication":"https://pith.science/pith/DQV4JRILVK6FPBMLYWV3TZ6WYR/action/replication_record"}},"created_at":"2026-05-18T00:15:31.499577+00:00","updated_at":"2026-05-18T00:15:31.499577+00:00"}