{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FWJ3RRHEZ2IZQYKDOSYEABKJM5","short_pith_number":"pith:FWJ3RRHE","schema_version":"1.0","canonical_sha256":"2d93b8c4e4ce9198614374b0400549677e95441f0542c479b5405b6a472984c8","source":{"kind":"arxiv","id":"2404.01297","version":1},"attestation_state":"computed","paper":{"title":"Streaming Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Arsha Nagrani, Austin Myers, Cordelia Schmid, Shen Yan, Shyamal Buch, Xingyi Zhou, Xuehan Xiong","submitted_at":"2024-04-01T17:59:15Z","abstract_excerpt":"An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrar"},"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":"2404.01297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:59:15Z","cross_cats_sorted":[],"title_canon_sha256":"b1d84ec33eb6f694625ff24c71e7bf393005cb5ab42dc004d16a0285c5386dcc","abstract_canon_sha256":"8ba33b4a28139138d15ae8cb09638d39d14441ce410959cbcd924a857ed6f819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:04.248371Z","signature_b64":"ktXS+eI6FEj8l7E/NDAqhrleFjntZPnHpcGi6m1YqkZFxV4DFUuPQCNWBcSIApDMbaAxQf2rIOePaSwPAMtwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d93b8c4e4ce9198614374b0400549677e95441f0542c479b5405b6a472984c8","last_reissued_at":"2026-07-05T08:03:04.247888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:04.247888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Arsha Nagrani, Austin Myers, Cordelia Schmid, Shen Yan, Shyamal Buch, Xingyi Zhou, Xuehan Xiong","submitted_at":"2024-04-01T17:59:15Z","abstract_excerpt":"An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01297","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/2404.01297/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":"2404.01297","created_at":"2026-07-05T08:03:04.247939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01297v1","created_at":"2026-07-05T08:03:04.247939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01297","created_at":"2026-07-05T08:03:04.247939+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWJ3RRHEZ2IZ","created_at":"2026-07-05T08:03:04.247939+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWJ3RRHEZ2IZQYKD","created_at":"2026-07-05T08:03:04.247939+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWJ3RRHE","created_at":"2026-07-05T08:03:04.247939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02591","citing_title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","ref_index":120,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5","json":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5.json","graph_json":"https://pith.science/api/pith-number/FWJ3RRHEZ2IZQYKDOSYEABKJM5/graph.json","events_json":"https://pith.science/api/pith-number/FWJ3RRHEZ2IZQYKDOSYEABKJM5/events.json","paper":"https://pith.science/paper/FWJ3RRHE"},"agent_actions":{"view_html":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5","download_json":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5.json","view_paper":"https://pith.science/paper/FWJ3RRHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01297&json=true","fetch_graph":"https://pith.science/api/pith-number/FWJ3RRHEZ2IZQYKDOSYEABKJM5/graph.json","fetch_events":"https://pith.science/api/pith-number/FWJ3RRHEZ2IZQYKDOSYEABKJM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5/action/storage_attestation","attest_author":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5/action/author_attestation","sign_citation":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5/action/citation_signature","submit_replication":"https://pith.science/pith/FWJ3RRHEZ2IZQYKDOSYEABKJM5/action/replication_record"}},"created_at":"2026-07-05T08:03:04.247939+00:00","updated_at":"2026-07-05T08:03:04.247939+00:00"}