{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SOR2HCPQMIU44WBX5KWIWP67MY","short_pith_number":"pith:SOR2HCPQ","schema_version":"1.0","canonical_sha256":"93a3a389f06229ce5837eaac8b3fdf662fdf2efbf4fe35e8f0c86b06613b23a0","source":{"kind":"arxiv","id":"2105.12085","version":3},"attestation_state":"computed","paper":{"title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongliang He, Jin Ye, Mingde Yao, Wenhao Wu, Xiao Tan, Yanwu Xu, Yifeng Shi, Yingying Li, Yuxiang Zhao, Zhikang Zou, Zichao Dong","submitted_at":"2021-05-25T17:09:57Z","abstract_excerpt":"Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolu"},"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":"2105.12085","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-25T17:09:57Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"439567f4107074a5d6ed0467c2d3e2423d101d01aa3b3dd4a22f928fae15ba92","abstract_canon_sha256":"b6b780930838f674b4e870e3ff3ef5f109b5db197af312ecf09616be3684a77c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:27.606801Z","signature_b64":"QUbjtxXnWHn261VvU0IG1ok8emyVvAZYcrIfvfxWTY3n9rkGC+9gFj6itR+yhhCqJJ5e7xEBRRYOmwWOVVvTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93a3a389f06229ce5837eaac8b3fdf662fdf2efbf4fe35e8f0c86b06613b23a0","last_reissued_at":"2026-07-05T03:06:27.606278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:27.606278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongliang He, Jin Ye, Mingde Yao, Wenhao Wu, Xiao Tan, Yanwu Xu, Yifeng Shi, Yingying Li, Yuxiang Zhao, Zhikang Zou, Zichao Dong","submitted_at":"2021-05-25T17:09:57Z","abstract_excerpt":"Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12085","kind":"arxiv","version":3},"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/2105.12085/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":"2105.12085","created_at":"2026-07-05T03:06:27.606338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.12085v3","created_at":"2026-07-05T03:06:27.606338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12085","created_at":"2026-07-05T03:06:27.606338+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOR2HCPQMIU4","created_at":"2026-07-05T03:06:27.606338+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOR2HCPQMIU44WBX","created_at":"2026-07-05T03:06:27.606338+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOR2HCPQ","created_at":"2026-07-05T03:06:27.606338+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/SOR2HCPQMIU44WBX5KWIWP67MY","json":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY.json","graph_json":"https://pith.science/api/pith-number/SOR2HCPQMIU44WBX5KWIWP67MY/graph.json","events_json":"https://pith.science/api/pith-number/SOR2HCPQMIU44WBX5KWIWP67MY/events.json","paper":"https://pith.science/paper/SOR2HCPQ"},"agent_actions":{"view_html":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY","download_json":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY.json","view_paper":"https://pith.science/paper/SOR2HCPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.12085&json=true","fetch_graph":"https://pith.science/api/pith-number/SOR2HCPQMIU44WBX5KWIWP67MY/graph.json","fetch_events":"https://pith.science/api/pith-number/SOR2HCPQMIU44WBX5KWIWP67MY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY/action/storage_attestation","attest_author":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY/action/author_attestation","sign_citation":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY/action/citation_signature","submit_replication":"https://pith.science/pith/SOR2HCPQMIU44WBX5KWIWP67MY/action/replication_record"}},"created_at":"2026-07-05T03:06:27.606338+00:00","updated_at":"2026-07-05T03:06:27.606338+00:00"}