{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZMLNXC2CBG5HZBJ5Z66FCOH2KN","short_pith_number":"pith:ZMLNXC2C","schema_version":"1.0","canonical_sha256":"cb16db8b4209ba7c853dcfbc5138fa5375333d19ff752058aa55fc674bd19488","source":{"kind":"arxiv","id":"1710.10330","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Aggregation for Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Xiaowei Zhao, Yang Liu","submitted_at":"2017-10-27T20:56:35Z","abstract_excerpt":"In this paper, we present a solution to Large-Scale Video Classification Challenge (LSVC2017) [1] that ranked the 1st place. We focused on a variety of modalities that cover visual, motion and audio. Also, we visualized the aggregation process to better understand how each modality takes effect. Among the extracted modalities, we found Temporal-Spatial features calculated by 3D convolution quite promising that greatly improved the performance. We attained the official metric mAP 0.8741 on the testing set with the ensemble model."},"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":"1710.10330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-27T20:56:35Z","cross_cats_sorted":[],"title_canon_sha256":"2eb0e0fa0b42dd407c2e6a93724efad094b28902adbef4538519ee1b57dad483","abstract_canon_sha256":"c6474a12adb291c7b969a68e47adb5d9fbc6582a93b98a8c0b1bfee5692301ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:49.858642Z","signature_b64":"RjjZNWiSVCsk1/xJLPDuZFfUIATYbyBZ2TJcMqFfDpt4tODYxcgULq7hxFC2zuCkTdAkZbr+VEwiZrFYtkzMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb16db8b4209ba7c853dcfbc5138fa5375333d19ff752058aa55fc674bd19488","last_reissued_at":"2026-05-18T00:31:49.858045Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:49.858045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Aggregation for Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Xiaowei Zhao, Yang Liu","submitted_at":"2017-10-27T20:56:35Z","abstract_excerpt":"In this paper, we present a solution to Large-Scale Video Classification Challenge (LSVC2017) [1] that ranked the 1st place. We focused on a variety of modalities that cover visual, motion and audio. Also, we visualized the aggregation process to better understand how each modality takes effect. Among the extracted modalities, we found Temporal-Spatial features calculated by 3D convolution quite promising that greatly improved the performance. We attained the official metric mAP 0.8741 on the testing set with the ensemble model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10330","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":"1710.10330","created_at":"2026-05-18T00:31:49.858124+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10330v1","created_at":"2026-05-18T00:31:49.858124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10330","created_at":"2026-05-18T00:31:49.858124+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMLNXC2CBG5H","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMLNXC2CBG5HZBJ5","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMLNXC2C","created_at":"2026-05-18T12:31:59.375834+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/ZMLNXC2CBG5HZBJ5Z66FCOH2KN","json":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN.json","graph_json":"https://pith.science/api/pith-number/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/graph.json","events_json":"https://pith.science/api/pith-number/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/events.json","paper":"https://pith.science/paper/ZMLNXC2C"},"agent_actions":{"view_html":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN","download_json":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN.json","view_paper":"https://pith.science/paper/ZMLNXC2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10330&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/action/storage_attestation","attest_author":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/action/author_attestation","sign_citation":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/action/citation_signature","submit_replication":"https://pith.science/pith/ZMLNXC2CBG5HZBJ5Z66FCOH2KN/action/replication_record"}},"created_at":"2026-05-18T00:31:49.858124+00:00","updated_at":"2026-05-18T00:31:49.858124+00:00"}