{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3WTFJYPOBPWCISREPJRM57NX47","short_pith_number":"pith:3WTFJYPO","canonical_record":{"source":{"id":"2104.10054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T15:26:24Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"1a5cf705c3c85491677d1f98df7ee6c28ad27a0a9dbc3785a1e207504d8aa923","abstract_canon_sha256":"1065200f32c8e5833f543281a6e06a564cd11c9d51ad034f1692bbd6df571573"},"schema_version":"1.0"},"canonical_sha256":"dda654e1ee0bec244a247a62cefdb7e7caa1b5057e46ae34b076c48aad36f648","source":{"kind":"arxiv","id":"2104.10054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10054","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10054v1","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10054","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"3WTFJYPOBPWC","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"3WTFJYPOBPWCISRE","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"3WTFJYPO","created_at":"2026-07-05T02:33:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3WTFJYPOBPWCISREPJRM57NX47","target":"record","payload":{"canonical_record":{"source":{"id":"2104.10054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T15:26:24Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"1a5cf705c3c85491677d1f98df7ee6c28ad27a0a9dbc3785a1e207504d8aa923","abstract_canon_sha256":"1065200f32c8e5833f543281a6e06a564cd11c9d51ad034f1692bbd6df571573"},"schema_version":"1.0"},"canonical_sha256":"dda654e1ee0bec244a247a62cefdb7e7caa1b5057e46ae34b076c48aad36f648","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:39.548897Z","signature_b64":"lXNu51iCjCW1McG5XNpFC0pV4ub4aqJr/U8LFhi0x5r8ZiP6rpmOgk0Lfg0qwIMUvM5/M7mshC9WtwosJagZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dda654e1ee0bec244a247a62cefdb7e7caa1b5057e46ae34b076c48aad36f648","last_reissued_at":"2026-07-05T02:33:39.548504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:39.548504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.10054","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IPGI8QorTLiMtKfF7Sm+xcQynp7+gmDAt/642HVWJQwdbAYI5e05HuVG/ObGEuSwIHYegor8K6UdiPztg6dbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T11:28:04.425916Z"},"content_sha256":"8e2a3dd65856cced61e5577b8ffe927360ade40312ea500acdbd3aebcf502cfd","schema_version":"1.0","event_id":"sha256:8e2a3dd65856cced61e5577b8ffe927360ade40312ea500acdbd3aebcf502cfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3WTFJYPOBPWCISREPJRM57NX47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Xiaohan Wang, Yi Yang","submitted_at":"2021-04-20T15:26:24Z","abstract_excerpt":"Text-video retrieval is a challenging task that aims to search relevant video contents based on natural language descriptions. The key to this problem is to measure text-video similarities in a joint embedding space. However, most existing methods only consider the global cross-modal similarity and overlook the local details. Some works incorporate the local comparisons through cross-modal local matching and reasoning. These complex operations introduce tremendous computation. In this paper, we design an efficient global-local alignment method. The multi-modal video sequences and text features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10054","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/2104.10054/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":"2026-07-05T02:33:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmKricktdMx2hDC+c7tUr/+2J8cLqoS3eKSFNemnTaGztLtIuz5hsWRznMeq5Mpe6OVN4lt3s3stx6lz16vMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T11:28:04.426290Z"},"content_sha256":"fef3f8b000a43ffe20e42bf7022ef80d487fc3ad9cca1cfed3f3c86c1ab0ad35","schema_version":"1.0","event_id":"sha256:fef3f8b000a43ffe20e42bf7022ef80d487fc3ad9cca1cfed3f3c86c1ab0ad35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WTFJYPOBPWCISREPJRM57NX47/bundle.json","state_url":"https://pith.science/pith/3WTFJYPOBPWCISREPJRM57NX47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WTFJYPOBPWCISREPJRM57NX47/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":"2026-07-10T11:28:04Z","links":{"resolver":"https://pith.science/pith/3WTFJYPOBPWCISREPJRM57NX47","bundle":"https://pith.science/pith/3WTFJYPOBPWCISREPJRM57NX47/bundle.json","state":"https://pith.science/pith/3WTFJYPOBPWCISREPJRM57NX47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WTFJYPOBPWCISREPJRM57NX47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3WTFJYPOBPWCISREPJRM57NX47","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":"1065200f32c8e5833f543281a6e06a564cd11c9d51ad034f1692bbd6df571573","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T15:26:24Z","title_canon_sha256":"1a5cf705c3c85491677d1f98df7ee6c28ad27a0a9dbc3785a1e207504d8aa923"},"schema_version":"1.0","source":{"id":"2104.10054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10054","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10054v1","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10054","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"pith_short_12","alias_value":"3WTFJYPOBPWC","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"pith_short_16","alias_value":"3WTFJYPOBPWCISRE","created_at":"2026-07-05T02:33:39Z"},{"alias_kind":"pith_short_8","alias_value":"3WTFJYPO","created_at":"2026-07-05T02:33:39Z"}],"graph_snapshots":[{"event_id":"sha256:fef3f8b000a43ffe20e42bf7022ef80d487fc3ad9cca1cfed3f3c86c1ab0ad35","target":"graph","created_at":"2026-07-05T02:33:39Z","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/2104.10054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-video retrieval is a challenging task that aims to search relevant video contents based on natural language descriptions. The key to this problem is to measure text-video similarities in a joint embedding space. However, most existing methods only consider the global cross-modal similarity and overlook the local details. Some works incorporate the local comparisons through cross-modal local matching and reasoning. These complex operations introduce tremendous computation. In this paper, we design an efficient global-local alignment method. The multi-modal video sequences and text features","authors_text":"Linchao Zhu, Xiaohan Wang, Yi Yang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T15:26:24Z","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10054","kind":"arxiv","version":1},"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":"sha256:8e2a3dd65856cced61e5577b8ffe927360ade40312ea500acdbd3aebcf502cfd","target":"record","created_at":"2026-07-05T02:33:39Z","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":"1065200f32c8e5833f543281a6e06a564cd11c9d51ad034f1692bbd6df571573","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-20T15:26:24Z","title_canon_sha256":"1a5cf705c3c85491677d1f98df7ee6c28ad27a0a9dbc3785a1e207504d8aa923"},"schema_version":"1.0","source":{"id":"2104.10054","kind":"arxiv","version":1}},"canonical_sha256":"dda654e1ee0bec244a247a62cefdb7e7caa1b5057e46ae34b076c48aad36f648","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dda654e1ee0bec244a247a62cefdb7e7caa1b5057e46ae34b076c48aad36f648","first_computed_at":"2026-07-05T02:33:39.548504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:39.548504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lXNu51iCjCW1McG5XNpFC0pV4ub4aqJr/U8LFhi0x5r8ZiP6rpmOgk0Lfg0qwIMUvM5/M7mshC9WtwosJagZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:39.548897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.10054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e2a3dd65856cced61e5577b8ffe927360ade40312ea500acdbd3aebcf502cfd","sha256:fef3f8b000a43ffe20e42bf7022ef80d487fc3ad9cca1cfed3f3c86c1ab0ad35"],"state_sha256":"806d716e748c1a7771e5495a58c11f83e989d77ca41eaba9216fb3d2e6b8e20b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uk4WTkspema2g2Nhl8TbEca/bzSrno8Dsa59xme9ae9E3noOsugmUGrtjht5n+kGPMe4Yhe3qp4zVaYw0CdhDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T11:28:04.428201Z","bundle_sha256":"c9aad915aa73ba39438d900471001a31948670839f7635539a91bef5a134046c"}}