{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PG4YAIKUVAQUUEYGRK6AE5SWVS","short_pith_number":"pith:PG4YAIKU","schema_version":"1.0","canonical_sha256":"79b9802154a8214a13068abc027656ac88ca12fa8b0953559bdbb39407961876","source":{"kind":"arxiv","id":"2104.09496","version":1},"attestation_state":"computed","paper":{"title":"Temporal Query Networks for Fine-grained Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Ankush Gupta, Chuhan Zhang","submitted_at":"2021-04-19T17:58:48Z","abstract_excerpt":"Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each query addresses a particular question, and has its own response label set. We make the following four contributions: (I) We propose a new model - a Temporal Query Network - which enables the query-response functionality, and a structural understanding of fine-grained actions. It attends to relevant segments for each query with a temporal attention mechanism, and"},"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":"2104.09496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-19T17:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"e7c6752bc5b4e2827b3ba50c5d4c0b0e2f65ab8b454d4fe4f5190b8ba24dbf86","abstract_canon_sha256":"1f17515ca5127f78175aa5586fa3f43c2bf2326558c51168352264bc67792210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:13.827229Z","signature_b64":"jbfCzvUXsrhCcqY6hSxVxwgEzN5MBvKTZUO0a1eF4bHtri7PAlD/mTD1tWOneknqUACtJjRao2hlp9wNUSzoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79b9802154a8214a13068abc027656ac88ca12fa8b0953559bdbb39407961876","last_reissued_at":"2026-07-05T02:33:13.826763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:13.826763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Query Networks for Fine-grained Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Ankush Gupta, Chuhan Zhang","submitted_at":"2021-04-19T17:58:48Z","abstract_excerpt":"Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each query addresses a particular question, and has its own response label set. We make the following four contributions: (I) We propose a new model - a Temporal Query Network - which enables the query-response functionality, and a structural understanding of fine-grained actions. It attends to relevant segments for each query with a temporal attention mechanism, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09496","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/2104.09496/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":"2104.09496","created_at":"2026-07-05T02:33:13.826827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09496v1","created_at":"2026-07-05T02:33:13.826827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09496","created_at":"2026-07-05T02:33:13.826827+00:00"},{"alias_kind":"pith_short_12","alias_value":"PG4YAIKUVAQU","created_at":"2026-07-05T02:33:13.826827+00:00"},{"alias_kind":"pith_short_16","alias_value":"PG4YAIKUVAQUUEYG","created_at":"2026-07-05T02:33:13.826827+00:00"},{"alias_kind":"pith_short_8","alias_value":"PG4YAIKU","created_at":"2026-07-05T02:33:13.826827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00692","citing_title":"CascadeFormer: A Family of Two-stage Cascading Transformers for Skeleton-based Human Action Recognition","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS","json":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS.json","graph_json":"https://pith.science/api/pith-number/PG4YAIKUVAQUUEYGRK6AE5SWVS/graph.json","events_json":"https://pith.science/api/pith-number/PG4YAIKUVAQUUEYGRK6AE5SWVS/events.json","paper":"https://pith.science/paper/PG4YAIKU"},"agent_actions":{"view_html":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS","download_json":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS.json","view_paper":"https://pith.science/paper/PG4YAIKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09496&json=true","fetch_graph":"https://pith.science/api/pith-number/PG4YAIKUVAQUUEYGRK6AE5SWVS/graph.json","fetch_events":"https://pith.science/api/pith-number/PG4YAIKUVAQUUEYGRK6AE5SWVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS/action/storage_attestation","attest_author":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS/action/author_attestation","sign_citation":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS/action/citation_signature","submit_replication":"https://pith.science/pith/PG4YAIKUVAQUUEYGRK6AE5SWVS/action/replication_record"}},"created_at":"2026-07-05T02:33:13.826827+00:00","updated_at":"2026-07-05T02:33:13.826827+00:00"}