{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMR74LR2CM3WCGOXBAO4TU4MRJ","short_pith_number":"pith:TMR74LR2","schema_version":"1.0","canonical_sha256":"9b23fe2e3a13376119d7081dc9d38c8a52f42d734ec07d275ec17525b6b5904b","source":{"kind":"arxiv","id":"2409.19252","version":1},"attestation_state":"computed","paper":{"title":"Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haosheng Chen, Jiaxu Leng, Ji Gan, Mingpi Tan, Xinbo Gao, Yiran Liu, Zhanjie Wu","submitted_at":"2024-09-28T05:54:20Z","abstract_excerpt":"While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\\emph{i.e.}, ambiguous violence). In contrast, hyperbolic representation learning, renowned for its ability to model hierarchical and complex relationships between events, has the potential to amplify the discrimination between visually similar events. Inspired by these, we develop a novel Dual-Space Representation Learning (DS"},"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":"2409.19252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T05:54:20Z","cross_cats_sorted":[],"title_canon_sha256":"092f70265d5debae8ecf9fd8c88826a35638e5bc93d2ab74543403113ac7cd80","abstract_canon_sha256":"5831c96a8ef26de11d14d83092b99287045547c69df87c201e06c4186997a41c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:12.745700Z","signature_b64":"3P/AtkEs9qO8awP0u3lD5y8ns+FbOYKN/kHwrEQ8AXwW5AlpLiBPeCE1iBFNm8xMe71HSjXmlnd8a8zA/GTcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b23fe2e3a13376119d7081dc9d38c8a52f42d734ec07d275ec17525b6b5904b","last_reissued_at":"2026-07-05T09:13:12.745192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:12.745192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haosheng Chen, Jiaxu Leng, Ji Gan, Mingpi Tan, Xinbo Gao, Yiran Liu, Zhanjie Wu","submitted_at":"2024-09-28T05:54:20Z","abstract_excerpt":"While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\\emph{i.e.}, ambiguous violence). In contrast, hyperbolic representation learning, renowned for its ability to model hierarchical and complex relationships between events, has the potential to amplify the discrimination between visually similar events. Inspired by these, we develop a novel Dual-Space Representation Learning (DS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19252","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/2409.19252/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":"2409.19252","created_at":"2026-07-05T09:13:12.745257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19252v1","created_at":"2026-07-05T09:13:12.745257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19252","created_at":"2026-07-05T09:13:12.745257+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMR74LR2CM3W","created_at":"2026-07-05T09:13:12.745257+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMR74LR2CM3WCGOX","created_at":"2026-07-05T09:13:12.745257+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMR74LR2","created_at":"2026-07-05T09:13:12.745257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00473","citing_title":"HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detection","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ","json":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ.json","graph_json":"https://pith.science/api/pith-number/TMR74LR2CM3WCGOXBAO4TU4MRJ/graph.json","events_json":"https://pith.science/api/pith-number/TMR74LR2CM3WCGOXBAO4TU4MRJ/events.json","paper":"https://pith.science/paper/TMR74LR2"},"agent_actions":{"view_html":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ","download_json":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ.json","view_paper":"https://pith.science/paper/TMR74LR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19252&json=true","fetch_graph":"https://pith.science/api/pith-number/TMR74LR2CM3WCGOXBAO4TU4MRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TMR74LR2CM3WCGOXBAO4TU4MRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ/action/storage_attestation","attest_author":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ/action/author_attestation","sign_citation":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ/action/citation_signature","submit_replication":"https://pith.science/pith/TMR74LR2CM3WCGOXBAO4TU4MRJ/action/replication_record"}},"created_at":"2026-07-05T09:13:12.745257+00:00","updated_at":"2026-07-05T09:13:12.745257+00:00"}