{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4B5ZLRVEYNWC6LXX4KTEXG5P64","short_pith_number":"pith:4B5ZLRVE","schema_version":"1.0","canonical_sha256":"e07b95c6a4c36c2f2ef7e2a64b9baff7034418209b6ac23b0c5a7316c6a3af29","source":{"kind":"arxiv","id":"1902.01078","version":2},"attestation_state":"computed","paper":{"title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Christos Chrysoulas, Georgios Kapidis, Grigorios Kalliatakis, Remco Veltkamp, Ronald Poppe","submitted_at":"2019-02-04T08:19:50Z","abstract_excerpt":"Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets. Because of the high level of complexity of these methods, as the convolution operations are also extended to additional dimension in order to extract features from them as well, providing a visualization for the signals that the network interpret as informative, is a challenging task. An effective notion of understanding the network's inner-workings would b"},"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":"1902.01078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-04T08:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"1841b5f0a1b5eaec5d52f22b0f8e05b47235c45d62d68a171a85e565714bb137","abstract_canon_sha256":"dcd6b62d618853243cce0ce30ae1677aa7564c71250f37889510f7144d679ea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:17.225438Z","signature_b64":"APYlJiZ29phTMqAyS3nm4oGsWL6A28we04ZP4JckiPu1WxBjTyn+3Bwi9D7vsELUuylKW5tlbpGuHTvuPzMHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e07b95c6a4c36c2f2ef7e2a64b9baff7034418209b6ac23b0c5a7316c6a3af29","last_reissued_at":"2026-07-05T01:12:17.225035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:17.225035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Christos Chrysoulas, Georgios Kapidis, Grigorios Kalliatakis, Remco Veltkamp, Ronald Poppe","submitted_at":"2019-02-04T08:19:50Z","abstract_excerpt":"Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets. Because of the high level of complexity of these methods, as the convolution operations are also extended to additional dimension in order to extract features from them as well, providing a visualization for the signals that the network interpret as informative, is a challenging task. An effective notion of understanding the network's inner-workings would b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01078","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/1902.01078/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":"1902.01078","created_at":"2026-07-05T01:12:17.225090+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01078v2","created_at":"2026-07-05T01:12:17.225090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01078","created_at":"2026-07-05T01:12:17.225090+00:00"},{"alias_kind":"pith_short_12","alias_value":"4B5ZLRVEYNWC","created_at":"2026-07-05T01:12:17.225090+00:00"},{"alias_kind":"pith_short_16","alias_value":"4B5ZLRVEYNWC6LXX","created_at":"2026-07-05T01:12:17.225090+00:00"},{"alias_kind":"pith_short_8","alias_value":"4B5ZLRVE","created_at":"2026-07-05T01:12:17.225090+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/4B5ZLRVEYNWC6LXX4KTEXG5P64","json":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64.json","graph_json":"https://pith.science/api/pith-number/4B5ZLRVEYNWC6LXX4KTEXG5P64/graph.json","events_json":"https://pith.science/api/pith-number/4B5ZLRVEYNWC6LXX4KTEXG5P64/events.json","paper":"https://pith.science/paper/4B5ZLRVE"},"agent_actions":{"view_html":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64","download_json":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64.json","view_paper":"https://pith.science/paper/4B5ZLRVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01078&json=true","fetch_graph":"https://pith.science/api/pith-number/4B5ZLRVEYNWC6LXX4KTEXG5P64/graph.json","fetch_events":"https://pith.science/api/pith-number/4B5ZLRVEYNWC6LXX4KTEXG5P64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64/action/storage_attestation","attest_author":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64/action/author_attestation","sign_citation":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64/action/citation_signature","submit_replication":"https://pith.science/pith/4B5ZLRVEYNWC6LXX4KTEXG5P64/action/replication_record"}},"created_at":"2026-07-05T01:12:17.225090+00:00","updated_at":"2026-07-05T01:12:17.225090+00:00"}