{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CNG2YIOCU3LV2WML6N5HTUVTRD","short_pith_number":"pith:CNG2YIOC","schema_version":"1.0","canonical_sha256":"134dac21c2a6d75d598bf37a79d2b388dc3d6592683d9e0d8506a36fb828dbfb","source":{"kind":"arxiv","id":"2404.04933","version":2},"attestation_state":"computed","paper":{"title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Lin Ma, Yingsen Zeng, Yujie Zhong","submitted_at":"2024-04-07T12:14:42Z","abstract_excerpt":"Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos. Despite that they focus on different events, we observe they have a significant connection. For instance, most descriptions in MR involve multiple actions from TAD. In this paper, we aim to investigate the potential synergy between TAD and MR. Firstly, we propose a unified architecture, termed Unified Moment Detection (UniMD), for both TAD and MR. It transforms the inputs of the two tasks, namely acti"},"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":"2404.04933","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-07T12:14:42Z","cross_cats_sorted":[],"title_canon_sha256":"0d4870bfb6d8d2d0d48bbc4c8d529da5e1fda00e2e8a78d5c987c1d184a13305","abstract_canon_sha256":"72c8e66fe9b04c4670c797dd6b6fe422f91f2492a028ee1c6a6a1775b35cd52b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:34.919533Z","signature_b64":"ljn8LnQDVd36XgWibVsxx9MtBFoB4nEr4B7GdGE5JFlUOqFgaMyBgcn8up3v53+LKS5J7OOb2sOJfo4tfHn2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"134dac21c2a6d75d598bf37a79d2b388dc3d6592683d9e0d8506a36fb828dbfb","last_reissued_at":"2026-07-05T08:42:34.919047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:34.919047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjian Feng, Lin Ma, Yingsen Zeng, Yujie Zhong","submitted_at":"2024-04-07T12:14:42Z","abstract_excerpt":"Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos. Despite that they focus on different events, we observe they have a significant connection. For instance, most descriptions in MR involve multiple actions from TAD. In this paper, we aim to investigate the potential synergy between TAD and MR. Firstly, we propose a unified architecture, termed Unified Moment Detection (UniMD), for both TAD and MR. It transforms the inputs of the two tasks, namely acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04933","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/2404.04933/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":"2404.04933","created_at":"2026-07-05T08:42:34.919105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04933v2","created_at":"2026-07-05T08:42:34.919105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04933","created_at":"2026-07-05T08:42:34.919105+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNG2YIOCU3LV","created_at":"2026-07-05T08:42:34.919105+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNG2YIOCU3LV2WML","created_at":"2026-07-05T08:42:34.919105+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNG2YIOC","created_at":"2026-07-05T08:42:34.919105+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/CNG2YIOCU3LV2WML6N5HTUVTRD","json":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD.json","graph_json":"https://pith.science/api/pith-number/CNG2YIOCU3LV2WML6N5HTUVTRD/graph.json","events_json":"https://pith.science/api/pith-number/CNG2YIOCU3LV2WML6N5HTUVTRD/events.json","paper":"https://pith.science/paper/CNG2YIOC"},"agent_actions":{"view_html":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD","download_json":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD.json","view_paper":"https://pith.science/paper/CNG2YIOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04933&json=true","fetch_graph":"https://pith.science/api/pith-number/CNG2YIOCU3LV2WML6N5HTUVTRD/graph.json","fetch_events":"https://pith.science/api/pith-number/CNG2YIOCU3LV2WML6N5HTUVTRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD/action/storage_attestation","attest_author":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD/action/author_attestation","sign_citation":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD/action/citation_signature","submit_replication":"https://pith.science/pith/CNG2YIOCU3LV2WML6N5HTUVTRD/action/replication_record"}},"created_at":"2026-07-05T08:42:34.919105+00:00","updated_at":"2026-07-05T08:42:34.919105+00:00"}