{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QB4VDNCJQQMH4EXYAL2UODAYYU","short_pith_number":"pith:QB4VDNCJ","canonical_record":{"source":{"id":"2005.08271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-17T15:00:05Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"bd2ae0ad2ea3f2d8fc1056a42a7133ad525e63f7b2235bc13f84d35f298eb39e","abstract_canon_sha256":"fdf4f234e9fdb500b3e258c577fb84afdb8d8ac850eb2d6670577dcb30dc350f"},"schema_version":"1.0"},"canonical_sha256":"807951b44984187e12f802f5470c18c5259f197e0903f58dc1be53dedb5a0d4b","source":{"kind":"arxiv","id":"2005.08271","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08271","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08271v2","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08271","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"QB4VDNCJQQMH","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"QB4VDNCJQQMH4EXY","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"QB4VDNCJ","created_at":"2026-07-05T01:26:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QB4VDNCJQQMH4EXYAL2UODAYYU","target":"record","payload":{"canonical_record":{"source":{"id":"2005.08271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-17T15:00:05Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"bd2ae0ad2ea3f2d8fc1056a42a7133ad525e63f7b2235bc13f84d35f298eb39e","abstract_canon_sha256":"fdf4f234e9fdb500b3e258c577fb84afdb8d8ac850eb2d6670577dcb30dc350f"},"schema_version":"1.0"},"canonical_sha256":"807951b44984187e12f802f5470c18c5259f197e0903f58dc1be53dedb5a0d4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:15.417985Z","signature_b64":"Hd9X0+6lAAD9kv0D9tfcLUo5yEJU1a1pYUgOWt5gUKhJF+hd/ig+yXYWsFpOBLn67WycB5Ppg94JowyPOueOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"807951b44984187e12f802f5470c18c5259f197e0903f58dc1be53dedb5a0d4b","last_reissued_at":"2026-07-05T01:26:15.417530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:15.417530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.08271","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhgJEna9FhQy2H3cTdGCYtTZhEP0cKQmPfybcvLwOA06AtmGcl8uJkwVV12b60r5VZmO5/O7NIF++7zhNzQXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T15:40:19.230947Z"},"content_sha256":"f9a4aab4844e2932c9bb6080e8aaf802dccab4792e4ab22450b7fb2b6143b4c5","schema_version":"1.0","event_id":"sha256:f9a4aab4844e2932c9bb6080e8aaf802dccab4792e4ab22450b7fb2b6143b4c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QB4VDNCJQQMH4EXYAL2UODAYYU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Esa Rahtu, Vladimir Iashin","submitted_at":"2020-05-17T15:00:05Z","abstract_excerpt":"Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a few prior works have utilized both modalities, yet they show poor results or demonstrate the importance on a dataset with a specific domain. In this paper, we introduce Bi-modal Transformer which generalizes the Transformer architecture for a bi-modal input. We show the effectiveness of the proposed model with audio and visual modalities on the dense video captioning task, yet "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08271","kind":"arxiv","version":2},"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/2005.08271/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:26:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fjkacFqRaDjnUOedz5XBpSDA71cJxuRaeabwXpv3w79mNP73LlB87Ssa5fZhOcFUyFL18WtVPH3aRrCiPf5vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T15:40:19.231332Z"},"content_sha256":"c49e9b3cedbafe8c5c2f6680ca69b6f64a97c7cbe3d9d41823c3853766e39898","schema_version":"1.0","event_id":"sha256:c49e9b3cedbafe8c5c2f6680ca69b6f64a97c7cbe3d9d41823c3853766e39898"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QB4VDNCJQQMH4EXYAL2UODAYYU/bundle.json","state_url":"https://pith.science/pith/QB4VDNCJQQMH4EXYAL2UODAYYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QB4VDNCJQQMH4EXYAL2UODAYYU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T15:40:19Z","links":{"resolver":"https://pith.science/pith/QB4VDNCJQQMH4EXYAL2UODAYYU","bundle":"https://pith.science/pith/QB4VDNCJQQMH4EXYAL2UODAYYU/bundle.json","state":"https://pith.science/pith/QB4VDNCJQQMH4EXYAL2UODAYYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QB4VDNCJQQMH4EXYAL2UODAYYU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QB4VDNCJQQMH4EXYAL2UODAYYU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fdf4f234e9fdb500b3e258c577fb84afdb8d8ac850eb2d6670577dcb30dc350f","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-17T15:00:05Z","title_canon_sha256":"bd2ae0ad2ea3f2d8fc1056a42a7133ad525e63f7b2235bc13f84d35f298eb39e"},"schema_version":"1.0","source":{"id":"2005.08271","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08271","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08271v2","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08271","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"pith_short_12","alias_value":"QB4VDNCJQQMH","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"QB4VDNCJQQMH4EXY","created_at":"2026-07-05T01:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"QB4VDNCJ","created_at":"2026-07-05T01:26:15Z"}],"graph_snapshots":[{"event_id":"sha256:c49e9b3cedbafe8c5c2f6680ca69b6f64a97c7cbe3d9d41823c3853766e39898","target":"graph","created_at":"2026-07-05T01:26:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.08271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a few prior works have utilized both modalities, yet they show poor results or demonstrate the importance on a dataset with a specific domain. In this paper, we introduce Bi-modal Transformer which generalizes the Transformer architecture for a bi-modal input. We show the effectiveness of the proposed model with audio and visual modalities on the dense video captioning task, yet ","authors_text":"Esa Rahtu, Vladimir Iashin","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-17T15:00:05Z","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08271","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f9a4aab4844e2932c9bb6080e8aaf802dccab4792e4ab22450b7fb2b6143b4c5","target":"record","created_at":"2026-07-05T01:26:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fdf4f234e9fdb500b3e258c577fb84afdb8d8ac850eb2d6670577dcb30dc350f","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-17T15:00:05Z","title_canon_sha256":"bd2ae0ad2ea3f2d8fc1056a42a7133ad525e63f7b2235bc13f84d35f298eb39e"},"schema_version":"1.0","source":{"id":"2005.08271","kind":"arxiv","version":2}},"canonical_sha256":"807951b44984187e12f802f5470c18c5259f197e0903f58dc1be53dedb5a0d4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"807951b44984187e12f802f5470c18c5259f197e0903f58dc1be53dedb5a0d4b","first_computed_at":"2026-07-05T01:26:15.417530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:15.417530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hd9X0+6lAAD9kv0D9tfcLUo5yEJU1a1pYUgOWt5gUKhJF+hd/ig+yXYWsFpOBLn67WycB5Ppg94JowyPOueOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:15.417985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.08271","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9a4aab4844e2932c9bb6080e8aaf802dccab4792e4ab22450b7fb2b6143b4c5","sha256:c49e9b3cedbafe8c5c2f6680ca69b6f64a97c7cbe3d9d41823c3853766e39898"],"state_sha256":"50e85b70b92ab6ea93df435b560482837705a0a6d202eeb086d5ba59f19a6637"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HABj7Bzdog+qNGuovSIcNnRIi026QaC07L0mec+pIbmVc//diFnr6a2LxbM0WGNpk+otemZ/gHCBRUdHknoVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T15:40:19.233726Z","bundle_sha256":"daab3e85e6a51621ef523652ccd22e4679758d1fd5cf53f19c39fdaf3c46a148"}}