{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PNKREUSUJR225WZCCISDN24ZWC","short_pith_number":"pith:PNKREUSU","schema_version":"1.0","canonical_sha256":"7b551252544c75aedb22122436eb99b098b91d5e5b38b350d78691a0e8f27a0d","source":{"kind":"arxiv","id":"2106.13014","version":1},"attestation_state":"computed","paper":{"title":"Exploring Stronger Feature for Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Jianwen Jiang, Mingqian Tang, Nong Sang, Shiwei Zhang, Xiang Wang, Yutong Feng, Zhiwu Qing, Ziyuan Huang","submitted_at":"2021-06-24T13:46:30Z","abstract_excerpt":"Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upper bound of detection performance. In this technical report, we explored classic convolution-based backbones and the recent surge of transformer-based backbones. We found that the transformer-based methods can achieve better classification performance than convolution-based, but they cannot generate accuracy action proposals. In addition, extracting features with larger frame reso"},"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":"2106.13014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T13:46:30Z","cross_cats_sorted":[],"title_canon_sha256":"c615b8848e3a338e73ff16c1e98044dc6a9db731e180043ed99ac9d3d52a75c6","abstract_canon_sha256":"cdd7d7131725d0184b735dbb8f592d61da53148168adfa8f4b4f721f5608a49b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:08.840766Z","signature_b64":"Vly7pF198QJ5+wrqQzCj3VBiqIUTVfmT3NNlkEGuYLSI51+kejnCVPmo1VJ9XNg5AGwzTe3Gd+pHor06bNIAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b551252544c75aedb22122436eb99b098b91d5e5b38b350d78691a0e8f27a0d","last_reissued_at":"2026-07-05T02:52:08.840370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:08.840370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Stronger Feature for Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxin Gao, Jianwen Jiang, Mingqian Tang, Nong Sang, Shiwei Zhang, Xiang Wang, Yutong Feng, Zhiwu Qing, Ziyuan Huang","submitted_at":"2021-06-24T13:46:30Z","abstract_excerpt":"Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upper bound of detection performance. In this technical report, we explored classic convolution-based backbones and the recent surge of transformer-based backbones. We found that the transformer-based methods can achieve better classification performance than convolution-based, but they cannot generate accuracy action proposals. In addition, extracting features with larger frame reso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13014","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/2106.13014/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":"2106.13014","created_at":"2026-07-05T02:52:08.840429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13014v1","created_at":"2026-07-05T02:52:08.840429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13014","created_at":"2026-07-05T02:52:08.840429+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNKREUSUJR22","created_at":"2026-07-05T02:52:08.840429+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNKREUSUJR225WZC","created_at":"2026-07-05T02:52:08.840429+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNKREUSU","created_at":"2026-07-05T02:52:08.840429+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/PNKREUSUJR225WZCCISDN24ZWC","json":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC.json","graph_json":"https://pith.science/api/pith-number/PNKREUSUJR225WZCCISDN24ZWC/graph.json","events_json":"https://pith.science/api/pith-number/PNKREUSUJR225WZCCISDN24ZWC/events.json","paper":"https://pith.science/paper/PNKREUSU"},"agent_actions":{"view_html":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC","download_json":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC.json","view_paper":"https://pith.science/paper/PNKREUSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13014&json=true","fetch_graph":"https://pith.science/api/pith-number/PNKREUSUJR225WZCCISDN24ZWC/graph.json","fetch_events":"https://pith.science/api/pith-number/PNKREUSUJR225WZCCISDN24ZWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC/action/storage_attestation","attest_author":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC/action/author_attestation","sign_citation":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC/action/citation_signature","submit_replication":"https://pith.science/pith/PNKREUSUJR225WZCCISDN24ZWC/action/replication_record"}},"created_at":"2026-07-05T02:52:08.840429+00:00","updated_at":"2026-07-05T02:52:08.840429+00:00"}