{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GUFKM42GESFWLCEYEVUZ2SSSUF","short_pith_number":"pith:GUFKM42G","schema_version":"1.0","canonical_sha256":"350aa67346248b65889825699d4a52a1413bb68f3d5ac572375e5aac662ebfce","source":{"kind":"arxiv","id":"2408.16272","version":1},"attestation_state":"computed","paper":{"title":"Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Ban, Han Fang, Haodong Chen, Haojian Huang, Hao Sun, Jin Chen, Kaijing Ma, Mulin Chen, Pengliang Ji, Xianghao Zang, Xuelong Li","submitted_at":"2024-08-29T05:32:03Z","abstract_excerpt":"Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-world challenges posed by open-vocabulary queries and untrimmed videos. This leads to unreliable predictions for noisy, corrupted, and out-of-distribution data. Adapting VTG models to dynamically estimate uncertainties based on user input can address this issue. To this end, we introduce SRAM, a robust network module that benefits from a two-stage cross-modal alignment task. More importantly, it integrates Deep Evidential Regression (DER) to explicitly and thoroughly quantify uncertainty during training, 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":"2408.16272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T05:32:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a188e94016ee3b434dbcf4f3533cc400f798804eda21f0cd81e5b57fd0213644","abstract_canon_sha256":"2d7d6b4ddb0116049986f05f1bc8bc5b2ab08401b604f75e79948d5738d0ddc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:28.650670Z","signature_b64":"vv1usJDEUPhxNkLgiyS3lhOUZYeoE9wm6QMtqLD0unxq28h/j3WrKNimfTYmAm8sbaOINeg0HC8Nvnc4p+hiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"350aa67346248b65889825699d4a52a1413bb68f3d5ac572375e5aac662ebfce","last_reissued_at":"2026-07-05T09:00:28.650097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:28.650097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Ban, Han Fang, Haodong Chen, Haojian Huang, Hao Sun, Jin Chen, Kaijing Ma, Mulin Chen, Pengliang Ji, Xianghao Zang, Xuelong Li","submitted_at":"2024-08-29T05:32:03Z","abstract_excerpt":"Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-world challenges posed by open-vocabulary queries and untrimmed videos. This leads to unreliable predictions for noisy, corrupted, and out-of-distribution data. Adapting VTG models to dynamically estimate uncertainties based on user input can address this issue. To this end, we introduce SRAM, a robust network module that benefits from a two-stage cross-modal alignment task. More importantly, it integrates Deep Evidential Regression (DER) to explicitly and thoroughly quantify uncertainty during training, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16272","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/2408.16272/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":"2408.16272","created_at":"2026-07-05T09:00:28.650193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16272v1","created_at":"2026-07-05T09:00:28.650193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16272","created_at":"2026-07-05T09:00:28.650193+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUFKM42GESFW","created_at":"2026-07-05T09:00:28.650193+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUFKM42GESFWLCEY","created_at":"2026-07-05T09:00:28.650193+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUFKM42G","created_at":"2026-07-05T09:00:28.650193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.07388","citing_title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","ref_index":285,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF","json":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF.json","graph_json":"https://pith.science/api/pith-number/GUFKM42GESFWLCEYEVUZ2SSSUF/graph.json","events_json":"https://pith.science/api/pith-number/GUFKM42GESFWLCEYEVUZ2SSSUF/events.json","paper":"https://pith.science/paper/GUFKM42G"},"agent_actions":{"view_html":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF","download_json":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF.json","view_paper":"https://pith.science/paper/GUFKM42G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16272&json=true","fetch_graph":"https://pith.science/api/pith-number/GUFKM42GESFWLCEYEVUZ2SSSUF/graph.json","fetch_events":"https://pith.science/api/pith-number/GUFKM42GESFWLCEYEVUZ2SSSUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF/action/storage_attestation","attest_author":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF/action/author_attestation","sign_citation":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF/action/citation_signature","submit_replication":"https://pith.science/pith/GUFKM42GESFWLCEYEVUZ2SSSUF/action/replication_record"}},"created_at":"2026-07-05T09:00:28.650193+00:00","updated_at":"2026-07-05T09:00:28.650193+00:00"}