{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JYVJYH2KNCK46QG42ULZ7YS35G","short_pith_number":"pith:JYVJYH2K","schema_version":"1.0","canonical_sha256":"4e2a9c1f4a6895cf40dcd5179fe25be9ba88b072f4fc8f38366b65394514fb1e","source":{"kind":"arxiv","id":"1712.05080","version":2},"attestation_state":"computed","paper":{"title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Gautam Prasad, Phuc Nguyen, Ting Liu","submitted_at":"2017-12-14T03:34:03Z","abstract_excerpt":"We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no requirement of temporal localization annotations. We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling. Our loss function is comprised of two terms that minimize the video-level action classification error and enforce the sp"},"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":"1712.05080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-14T03:34:03Z","cross_cats_sorted":[],"title_canon_sha256":"97123c111d43ee8793615b959ce9e22ac9e7f690f1957f55ed7c9df1bf2462c8","abstract_canon_sha256":"e31c0b8f6e53a2f18aa46bb70308bc1d0b58f39e0e0dddfff085d5c246316264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:34.898024Z","signature_b64":"g+Am9eZaPx1VtB8cnShwPl5IxyzuFab1D8DKjW/qpfgHeFSVG8jzNeIq0ip7MOWzaBiQE4L+7hMMZtq/fZVmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e2a9c1f4a6895cf40dcd5179fe25be9ba88b072f4fc8f38366b65394514fb1e","last_reissued_at":"2026-05-18T00:19:34.897273Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:34.897273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Gautam Prasad, Phuc Nguyen, Ting Liu","submitted_at":"2017-12-14T03:34:03Z","abstract_excerpt":"We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no requirement of temporal localization annotations. We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling. Our loss function is comprised of two terms that minimize the video-level action classification error and enforce the sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05080","kind":"arxiv","version":2},"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":"1712.05080","created_at":"2026-05-18T00:19:34.897382+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.05080v2","created_at":"2026-05-18T00:19:34.897382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05080","created_at":"2026-05-18T00:19:34.897382+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYVJYH2KNCK4","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYVJYH2KNCK46QG4","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYVJYH2K","created_at":"2026-05-18T12:31:24.725408+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/JYVJYH2KNCK46QG42ULZ7YS35G","json":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G.json","graph_json":"https://pith.science/api/pith-number/JYVJYH2KNCK46QG42ULZ7YS35G/graph.json","events_json":"https://pith.science/api/pith-number/JYVJYH2KNCK46QG42ULZ7YS35G/events.json","paper":"https://pith.science/paper/JYVJYH2K"},"agent_actions":{"view_html":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G","download_json":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G.json","view_paper":"https://pith.science/paper/JYVJYH2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.05080&json=true","fetch_graph":"https://pith.science/api/pith-number/JYVJYH2KNCK46QG42ULZ7YS35G/graph.json","fetch_events":"https://pith.science/api/pith-number/JYVJYH2KNCK46QG42ULZ7YS35G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G/action/storage_attestation","attest_author":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G/action/author_attestation","sign_citation":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G/action/citation_signature","submit_replication":"https://pith.science/pith/JYVJYH2KNCK46QG42ULZ7YS35G/action/replication_record"}},"created_at":"2026-05-18T00:19:34.897382+00:00","updated_at":"2026-05-18T00:19:34.897382+00:00"}