{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JNDGCVVOIIMGWWV2WNTIJRI35R","short_pith_number":"pith:JNDGCVVO","schema_version":"1.0","canonical_sha256":"4b466156ae42186b5abab36684c51bec7a84772b85861407f1de00ed5df0f53b","source":{"kind":"arxiv","id":"2404.01174","version":2},"attestation_state":"computed","paper":{"title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ruiqin Xiong, Wenrui Li, Xiaopeng Fan, Xiaopeng Hong","submitted_at":"2024-04-01T15:26:44Z","abstract_excerpt":"Temporal video grounding (TVG) is a critical task in video content understanding, requiring precise alignment between video content and natural language instructions. Despite significant advancements, existing methods face challenges in managing confidence bias towards salient objects and capturing long-term dependencies in video sequences. To address these issues, we introduce SpikeMba: a multi-modal spiking saliency mamba for temporal video grounding. Our approach integrates Spiking Neural Networks (SNNs) with state space models (SSMs) to leverage their unique advantages in handling differen"},"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":"2404.01174","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T15:26:44Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"897c0b02a9c70407830a24541db92b232ac11e53d0778621625448cb992a7108","abstract_canon_sha256":"7520f77bb8ad2373e8a3192ffedbac10cefdd14ca9f1870f0dffeb9540a77861"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:52.214909Z","signature_b64":"WJBhOrGJkShL0Y2oyyuWXoqFlCF/ZohdpvHkcKD0KcC58IJTReBCW8p8uI6XQqqeJg3WMcCC5eeneyNK0hAoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b466156ae42186b5abab36684c51bec7a84772b85861407f1de00ed5df0f53b","last_reissued_at":"2026-07-05T08:21:52.214439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:52.214439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Ruiqin Xiong, Wenrui Li, Xiaopeng Fan, Xiaopeng Hong","submitted_at":"2024-04-01T15:26:44Z","abstract_excerpt":"Temporal video grounding (TVG) is a critical task in video content understanding, requiring precise alignment between video content and natural language instructions. Despite significant advancements, existing methods face challenges in managing confidence bias towards salient objects and capturing long-term dependencies in video sequences. To address these issues, we introduce SpikeMba: a multi-modal spiking saliency mamba for temporal video grounding. Our approach integrates Spiking Neural Networks (SNNs) with state space models (SSMs) to leverage their unique advantages in handling differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01174","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/2404.01174/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":"2404.01174","created_at":"2026-07-05T08:21:52.214497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01174v2","created_at":"2026-07-05T08:21:52.214497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01174","created_at":"2026-07-05T08:21:52.214497+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNDGCVVOIIMG","created_at":"2026-07-05T08:21:52.214497+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNDGCVVOIIMGWWV2","created_at":"2026-07-05T08:21:52.214497+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNDGCVVO","created_at":"2026-07-05T08:21:52.214497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18328","citing_title":"EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04595","citing_title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25570","citing_title":"Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R","json":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R.json","graph_json":"https://pith.science/api/pith-number/JNDGCVVOIIMGWWV2WNTIJRI35R/graph.json","events_json":"https://pith.science/api/pith-number/JNDGCVVOIIMGWWV2WNTIJRI35R/events.json","paper":"https://pith.science/paper/JNDGCVVO"},"agent_actions":{"view_html":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R","download_json":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R.json","view_paper":"https://pith.science/paper/JNDGCVVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01174&json=true","fetch_graph":"https://pith.science/api/pith-number/JNDGCVVOIIMGWWV2WNTIJRI35R/graph.json","fetch_events":"https://pith.science/api/pith-number/JNDGCVVOIIMGWWV2WNTIJRI35R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R/action/storage_attestation","attest_author":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R/action/author_attestation","sign_citation":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R/action/citation_signature","submit_replication":"https://pith.science/pith/JNDGCVVOIIMGWWV2WNTIJRI35R/action/replication_record"}},"created_at":"2026-07-05T08:21:52.214497+00:00","updated_at":"2026-07-05T08:21:52.214497+00:00"}