{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BWPD2CT7A2BINFF6DVPQQYPL6N","short_pith_number":"pith:BWPD2CT7","schema_version":"1.0","canonical_sha256":"0d9e3d0a7f06828694be1d5f0861ebf371604e29961265b5907c4bfe28ff342b","source":{"kind":"arxiv","id":"2106.15787","version":1},"attestation_state":"computed","paper":{"title":"Long-Short Temporal Modeling for Efficient Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Liyu Wu, Yuexian Zou","submitted_at":"2021-06-30T02:54:13Z","abstract_excerpt":"Efficient long-short temporal modeling is key for enhancing the performance of action recognition task. In this paper, we propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module and a Video-level Aggregation (VLA) module to achieve long-short temporal modeling. Specifically, motion representations have been proved effective in capturing short-term and high-frequency action. However, current motion representations are calculated from adjacent frames, which may have poor interpretation and bring useless information (noisy or blank). Th"},"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":"2106.15787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-30T02:54:13Z","cross_cats_sorted":[],"title_canon_sha256":"8ea4e61d9dbd7090e497a92976aa5c1d00bea30a7e41a48cb5f4e8ea513ba6d0","abstract_canon_sha256":"92fb1650b706678750f202b83a51d9338e26a0b09fc200f4545e4bb52222a3a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:00.321051Z","signature_b64":"Pt8sZMBKPO93rk7jB3kBiBNJp6lqOaaKe4PNBs/h4RBA6YfNRfEbA1CER/K3EdOMLfkNG1Ry4lplHAWu6mijCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d9e3d0a7f06828694be1d5f0861ebf371604e29961265b5907c4bfe28ff342b","last_reissued_at":"2026-07-05T02:54:00.320647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:00.320647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Short Temporal Modeling for Efficient Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Liyu Wu, Yuexian Zou","submitted_at":"2021-06-30T02:54:13Z","abstract_excerpt":"Efficient long-short temporal modeling is key for enhancing the performance of action recognition task. In this paper, we propose a new two-stream action recognition network, termed as MENet, consisting of a Motion Enhancement (ME) module and a Video-level Aggregation (VLA) module to achieve long-short temporal modeling. Specifically, motion representations have been proved effective in capturing short-term and high-frequency action. However, current motion representations are calculated from adjacent frames, which may have poor interpretation and bring useless information (noisy or blank). Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15787","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/2106.15787/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":"2106.15787","created_at":"2026-07-05T02:54:00.320702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15787v1","created_at":"2026-07-05T02:54:00.320702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15787","created_at":"2026-07-05T02:54:00.320702+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWPD2CT7A2BI","created_at":"2026-07-05T02:54:00.320702+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWPD2CT7A2BINFF6","created_at":"2026-07-05T02:54:00.320702+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWPD2CT7","created_at":"2026-07-05T02:54:00.320702+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/BWPD2CT7A2BINFF6DVPQQYPL6N","json":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N.json","graph_json":"https://pith.science/api/pith-number/BWPD2CT7A2BINFF6DVPQQYPL6N/graph.json","events_json":"https://pith.science/api/pith-number/BWPD2CT7A2BINFF6DVPQQYPL6N/events.json","paper":"https://pith.science/paper/BWPD2CT7"},"agent_actions":{"view_html":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N","download_json":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N.json","view_paper":"https://pith.science/paper/BWPD2CT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15787&json=true","fetch_graph":"https://pith.science/api/pith-number/BWPD2CT7A2BINFF6DVPQQYPL6N/graph.json","fetch_events":"https://pith.science/api/pith-number/BWPD2CT7A2BINFF6DVPQQYPL6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N/action/storage_attestation","attest_author":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N/action/author_attestation","sign_citation":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N/action/citation_signature","submit_replication":"https://pith.science/pith/BWPD2CT7A2BINFF6DVPQQYPL6N/action/replication_record"}},"created_at":"2026-07-05T02:54:00.320702+00:00","updated_at":"2026-07-05T02:54:00.320702+00:00"}