{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S3NQW7BN3LSYDYNN3C6QMMBYLA","short_pith_number":"pith:S3NQW7BN","schema_version":"1.0","canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","source":{"kind":"arxiv","id":"2306.09947","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"\\\"Ozkan \\c{C}ayl{\\i}, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xubo Liu","submitted_at":"2023-06-16T16:28:03Z","abstract_excerpt":"Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering state-of-the-art performance. However, these methods are often undeployable in low-power devices like smartphones due to the large size of the model parameters. In this paper, we propose to exploit simple pooling front-end and down-sampling algorithms with knowledge distillation for audio and visual attributes using a reduced number of audio-visual frames. With the h"},"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":"2306.09947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T16:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"dc741328c19f94fd4eca3c298e777347f87aa932004af38a0c05623fcee39721","abstract_canon_sha256":"e86eed6788fb238320a9839a353fd34725da4d80af482c0dda42c417ec9d0ec1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:25.805117Z","signature_b64":"+NPhKCtaxbOyJpMIRCmFf2USQmTXhw1oc7MmZ1bvivNFEFAlCcLVSHwFc5dU9+IB5JTzK77/ugmFuVLECxZpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","last_reissued_at":"2026-07-05T06:21:25.804555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:25.804555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"\\\"Ozkan \\c{C}ayl{\\i}, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xubo Liu","submitted_at":"2023-06-16T16:28:03Z","abstract_excerpt":"Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering state-of-the-art performance. However, these methods are often undeployable in low-power devices like smartphones due to the large size of the model parameters. In this paper, we propose to exploit simple pooling front-end and down-sampling algorithms with knowledge distillation for audio and visual attributes using a reduced number of audio-visual frames. With the h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09947","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/2306.09947/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":"2306.09947","created_at":"2026-07-05T06:21:25.804614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09947v1","created_at":"2026-07-05T06:21:25.804614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09947","created_at":"2026-07-05T06:21:25.804614+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3NQW7BN3LSY","created_at":"2026-07-05T06:21:25.804614+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3NQW7BN3LSYDYNN","created_at":"2026-07-05T06:21:25.804614+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3NQW7BN","created_at":"2026-07-05T06:21:25.804614+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/S3NQW7BN3LSYDYNN3C6QMMBYLA","json":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA.json","graph_json":"https://pith.science/api/pith-number/S3NQW7BN3LSYDYNN3C6QMMBYLA/graph.json","events_json":"https://pith.science/api/pith-number/S3NQW7BN3LSYDYNN3C6QMMBYLA/events.json","paper":"https://pith.science/paper/S3NQW7BN"},"agent_actions":{"view_html":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA","download_json":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA.json","view_paper":"https://pith.science/paper/S3NQW7BN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09947&json=true","fetch_graph":"https://pith.science/api/pith-number/S3NQW7BN3LSYDYNN3C6QMMBYLA/graph.json","fetch_events":"https://pith.science/api/pith-number/S3NQW7BN3LSYDYNN3C6QMMBYLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/action/storage_attestation","attest_author":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/action/author_attestation","sign_citation":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/action/citation_signature","submit_replication":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/action/replication_record"}},"created_at":"2026-07-05T06:21:25.804614+00:00","updated_at":"2026-07-05T06:21:25.804614+00:00"}