{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BDF2UYUFHVRTDMDVIZHAESCZY7","short_pith_number":"pith:BDF2UYUF","schema_version":"1.0","canonical_sha256":"08cbaa62853d6331b075464e024859c7ebb199a19a22e7d8056dcd8714a56cff","source":{"kind":"arxiv","id":"2404.06173","version":1},"attestation_state":"computed","paper":{"title":"Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong-Wah Ngo, Jiaxin Wu, Wing-Kwong Chan","submitted_at":"2024-04-09T09:54:21Z","abstract_excerpt":"Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small sizes of available video-text datasets and the low quality of concept banks, which results in the failures of unseen queries and the out-of-vocabulary problem. This paper addresses these two problems by constructing a new dataset and developing a multi-word concept bank. Specifically, capitalizing on a generative model, we construct a new dataset consisting of"},"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":"2404.06173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T09:54:21Z","cross_cats_sorted":[],"title_canon_sha256":"521194edb6b3e2550d7d13b239c58c108223d338bbd29e69e588ebb05c6acd30","abstract_canon_sha256":"f635391979e92527ec63207e97e5338483d301b69b508607f8350637d1141732"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:05.286549Z","signature_b64":"hv7uz0toiWT3Bz+4KAdlx/tWa63v/8h8kX3dvfmv3cWwAESMu7GcM+Zu3VSRx54YMdwmR7t0Th1oUc0pE4iQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08cbaa62853d6331b075464e024859c7ebb199a19a22e7d8056dcd8714a56cff","last_reissued_at":"2026-07-05T08:06:05.286068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:05.286068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong-Wah Ngo, Jiaxin Wu, Wing-Kwong Chan","submitted_at":"2024-04-09T09:54:21Z","abstract_excerpt":"Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small sizes of available video-text datasets and the low quality of concept banks, which results in the failures of unseen queries and the out-of-vocabulary problem. This paper addresses these two problems by constructing a new dataset and developing a multi-word concept bank. Specifically, capitalizing on a generative model, we construct a new dataset consisting of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06173","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/2404.06173/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":"2404.06173","created_at":"2026-07-05T08:06:05.286131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06173v1","created_at":"2026-07-05T08:06:05.286131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06173","created_at":"2026-07-05T08:06:05.286131+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDF2UYUFHVRT","created_at":"2026-07-05T08:06:05.286131+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDF2UYUFHVRTDMDV","created_at":"2026-07-05T08:06:05.286131+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDF2UYUF","created_at":"2026-07-05T08:06:05.286131+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/BDF2UYUFHVRTDMDVIZHAESCZY7","json":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7.json","graph_json":"https://pith.science/api/pith-number/BDF2UYUFHVRTDMDVIZHAESCZY7/graph.json","events_json":"https://pith.science/api/pith-number/BDF2UYUFHVRTDMDVIZHAESCZY7/events.json","paper":"https://pith.science/paper/BDF2UYUF"},"agent_actions":{"view_html":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7","download_json":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7.json","view_paper":"https://pith.science/paper/BDF2UYUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06173&json=true","fetch_graph":"https://pith.science/api/pith-number/BDF2UYUFHVRTDMDVIZHAESCZY7/graph.json","fetch_events":"https://pith.science/api/pith-number/BDF2UYUFHVRTDMDVIZHAESCZY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7/action/storage_attestation","attest_author":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7/action/author_attestation","sign_citation":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7/action/citation_signature","submit_replication":"https://pith.science/pith/BDF2UYUFHVRTDMDVIZHAESCZY7/action/replication_record"}},"created_at":"2026-07-05T08:06:05.286131+00:00","updated_at":"2026-07-05T08:06:05.286131+00:00"}