{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4YM7ODHJD6RBAY23J3MS7SWE2G","short_pith_number":"pith:4YM7ODHJ","schema_version":"1.0","canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","source":{"kind":"arxiv","id":"2501.10787","version":1},"attestation_state":"computed","paper":{"title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Zhou, Fuwei Zhang, Pengcheng Zhao, Shujin Lin, Zhixian He","submitted_at":"2025-01-18T14:54:56Z","abstract_excerpt":"Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract multimodal information, and finally use a Transformer Decoder to decode multimodal information. However, existing methods face several issues: (1) Overlapping semantic information between different samples in the dataset hinders the model's multimodal aligning performance; (2) Existing models are not able to efficiently extract local features of the video; (3) T"},"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":"2501.10787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T14:54:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"586248602d0190536f8c851169434deb21e83c04cc729f5f386874b8f7b33363","abstract_canon_sha256":"81c45d69c47b204831780ec3e6b8870043882489110881b6aa2f31ef5781e52e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:59.362211Z","signature_b64":"aC3AS7St4XI5o3JNqaiRI5NkocBOsn1t+id7HixB52s7oc53RL5Za3i86GIHMlVxZr8mypplRrO02LD5XwlsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","last_reissued_at":"2026-07-05T10:02:59.361688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:59.361688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Zhou, Fuwei Zhang, Pengcheng Zhao, Shujin Lin, Zhixian He","submitted_at":"2025-01-18T14:54:56Z","abstract_excerpt":"Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract multimodal information, and finally use a Transformer Decoder to decode multimodal information. However, existing methods face several issues: (1) Overlapping semantic information between different samples in the dataset hinders the model's multimodal aligning performance; (2) Existing models are not able to efficiently extract local features of the video; (3) T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10787","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/2501.10787/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":"2501.10787","created_at":"2026-07-05T10:02:59.361747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10787v1","created_at":"2026-07-05T10:02:59.361747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10787","created_at":"2026-07-05T10:02:59.361747+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YM7ODHJD6RB","created_at":"2026-07-05T10:02:59.361747+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YM7ODHJD6RBAY23","created_at":"2026-07-05T10:02:59.361747+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YM7ODHJ","created_at":"2026-07-05T10:02:59.361747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09248","citing_title":"Temporal-Aware Reasoning Optimization for Video Temporal Grounding","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03398","citing_title":"MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02623","citing_title":"Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G","json":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G.json","graph_json":"https://pith.science/api/pith-number/4YM7ODHJD6RBAY23J3MS7SWE2G/graph.json","events_json":"https://pith.science/api/pith-number/4YM7ODHJD6RBAY23J3MS7SWE2G/events.json","paper":"https://pith.science/paper/4YM7ODHJ"},"agent_actions":{"view_html":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G","download_json":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G.json","view_paper":"https://pith.science/paper/4YM7ODHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10787&json=true","fetch_graph":"https://pith.science/api/pith-number/4YM7ODHJD6RBAY23J3MS7SWE2G/graph.json","fetch_events":"https://pith.science/api/pith-number/4YM7ODHJD6RBAY23J3MS7SWE2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/action/storage_attestation","attest_author":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/action/author_attestation","sign_citation":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/action/citation_signature","submit_replication":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/action/replication_record"}},"created_at":"2026-07-05T10:02:59.361747+00:00","updated_at":"2026-07-05T10:02:59.361747+00:00"}