{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M22TGXB5O2T53LJXJLLJQNTIDE","short_pith_number":"pith:M22TGXB5","schema_version":"1.0","canonical_sha256":"66b5335c3d76a7ddad374ad698366819183a5eb4ea7bd34a3ada4838b4b66539","source":{"kind":"arxiv","id":"2106.14447","version":1},"attestation_state":"computed","paper":{"title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo He, Jingyu Xin, Le Kang, Xin Zhou, Zhiyu Cheng","submitted_at":"2021-06-28T08:00:21Z","abstract_excerpt":"With rapidly evolving internet technologies and emerging tools, sports related videos generated online are increasing at an unprecedentedly fast pace. To automate sports video editing/highlight generation process, a key task is to precisely recognize and locate the events in the long untrimmed videos. In this tech report, we present a two-stage paradigm to detect what and when events happen in soccer broadcast videos. Specifically, we fine-tune multiple action recognition models on soccer data to extract high-level semantic features, and design a transformer based temporal detection module to "},"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":"2106.14447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-28T08:00:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf9b5f63a9b1a950ec075bd6cff19116c6e36a35cecccceee18d09f7120dbc0d","abstract_canon_sha256":"5daecb9a9c015f262b60fadf52ef6c12aa10ea2b4be857df148b8f71a508bc2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:50.986509Z","signature_b64":"jqvUaWWoUoFFo6dhGSBnZA4SRMzonglPdVVMF/uofy3FEFa5fg5hH4HOFDzGHDPY55YwdsEXZT97XabWGYqRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b5335c3d76a7ddad374ad698366819183a5eb4ea7bd34a3ada4838b4b66539","last_reissued_at":"2026-07-05T02:52:50.985988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:50.985988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo He, Jingyu Xin, Le Kang, Xin Zhou, Zhiyu Cheng","submitted_at":"2021-06-28T08:00:21Z","abstract_excerpt":"With rapidly evolving internet technologies and emerging tools, sports related videos generated online are increasing at an unprecedentedly fast pace. To automate sports video editing/highlight generation process, a key task is to precisely recognize and locate the events in the long untrimmed videos. In this tech report, we present a two-stage paradigm to detect what and when events happen in soccer broadcast videos. Specifically, we fine-tune multiple action recognition models on soccer data to extract high-level semantic features, and design a transformer based temporal detection module to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14447","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/2106.14447/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":"2106.14447","created_at":"2026-07-05T02:52:50.986058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14447v1","created_at":"2026-07-05T02:52:50.986058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14447","created_at":"2026-07-05T02:52:50.986058+00:00"},{"alias_kind":"pith_short_12","alias_value":"M22TGXB5O2T5","created_at":"2026-07-05T02:52:50.986058+00:00"},{"alias_kind":"pith_short_16","alias_value":"M22TGXB5O2T53LJX","created_at":"2026-07-05T02:52:50.986058+00:00"},{"alias_kind":"pith_short_8","alias_value":"M22TGXB5","created_at":"2026-07-05T02:52:50.986058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01820","citing_title":"Towards Universal Soccer Video Understanding","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE","json":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE.json","graph_json":"https://pith.science/api/pith-number/M22TGXB5O2T53LJXJLLJQNTIDE/graph.json","events_json":"https://pith.science/api/pith-number/M22TGXB5O2T53LJXJLLJQNTIDE/events.json","paper":"https://pith.science/paper/M22TGXB5"},"agent_actions":{"view_html":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE","download_json":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE.json","view_paper":"https://pith.science/paper/M22TGXB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14447&json=true","fetch_graph":"https://pith.science/api/pith-number/M22TGXB5O2T53LJXJLLJQNTIDE/graph.json","fetch_events":"https://pith.science/api/pith-number/M22TGXB5O2T53LJXJLLJQNTIDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE/action/storage_attestation","attest_author":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE/action/author_attestation","sign_citation":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE/action/citation_signature","submit_replication":"https://pith.science/pith/M22TGXB5O2T53LJXJLLJQNTIDE/action/replication_record"}},"created_at":"2026-07-05T02:52:50.986058+00:00","updated_at":"2026-07-05T02:52:50.986058+00:00"}