{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TWW6AUWTV6F7FG5WONYSD4MZ5F","short_pith_number":"pith:TWW6AUWT","schema_version":"1.0","canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","source":{"kind":"arxiv","id":"2312.11897","version":3},"attestation_state":"computed","paper":{"title":"Text-Conditioned Resampler For Long Form Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Tonioni, Andrew Zisserman, Bruno Korbar, Federico Tombari, Yongqin Xian","submitted_at":"2023-12-19T06:42:47Z","abstract_excerpt":"In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can pr"},"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":"2312.11897","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T06:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"95e3382a7c6d27832666f28cb855e22c4900e18b4abed5721c9729c10664d69d","abstract_canon_sha256":"02ea099064fde002a4e11b80e61e9beb0e74a4e32fac7bf3fb6739a81a62025e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:16.043329Z","signature_b64":"E2Wk4FKzVwOLBGrYneBfga+UEGGTz1dXcl8SxEyrPWRaP9SHbksiQ1j9qjIITQbpQtf/BuuMS3tkgIeSx7yqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","last_reissued_at":"2026-07-05T08:56:16.042977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:16.042977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Conditioned Resampler For Long Form Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Tonioni, Andrew Zisserman, Bruno Korbar, Federico Tombari, Yongqin Xian","submitted_at":"2023-12-19T06:42:47Z","abstract_excerpt":"In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11897","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/2312.11897/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":"2312.11897","created_at":"2026-07-05T08:56:16.043032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11897v3","created_at":"2026-07-05T08:56:16.043032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11897","created_at":"2026-07-05T08:56:16.043032+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWW6AUWTV6F7","created_at":"2026-07-05T08:56:16.043032+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWW6AUWTV6F7FG5W","created_at":"2026-07-05T08:56:16.043032+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWW6AUWT","created_at":"2026-07-05T08:56:16.043032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15953","citing_title":"Understanding Long Videos via LLM-Powered Entity Relation Graphs","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F","json":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F.json","graph_json":"https://pith.science/api/pith-number/TWW6AUWTV6F7FG5WONYSD4MZ5F/graph.json","events_json":"https://pith.science/api/pith-number/TWW6AUWTV6F7FG5WONYSD4MZ5F/events.json","paper":"https://pith.science/paper/TWW6AUWT"},"agent_actions":{"view_html":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F","download_json":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F.json","view_paper":"https://pith.science/paper/TWW6AUWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11897&json=true","fetch_graph":"https://pith.science/api/pith-number/TWW6AUWTV6F7FG5WONYSD4MZ5F/graph.json","fetch_events":"https://pith.science/api/pith-number/TWW6AUWTV6F7FG5WONYSD4MZ5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/action/storage_attestation","attest_author":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/action/author_attestation","sign_citation":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/action/citation_signature","submit_replication":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/action/replication_record"}},"created_at":"2026-07-05T08:56:16.043032+00:00","updated_at":"2026-07-05T08:56:16.043032+00:00"}