{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RP6JLC4PSBPPJ65DIQCCGRQNCH","short_pith_number":"pith:RP6JLC4P","schema_version":"1.0","canonical_sha256":"8bfc958b8f905ef4fba3440423460d11df3c00f11b100402e693e7af52315884","source":{"kind":"arxiv","id":"1801.01415","version":1},"attestation_state":"computed","paper":{"title":"What have we learned from deep representations for action recognition?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Axel Pinz, Christoph Feichtenhofer, Richard P. Wildes","submitted_at":"2018-01-04T15:47:47Z","abstract_excerpt":"As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing what two-stream models have learned in order to recognize actions in video. We show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions. Key observations include the following. First, cross-stream fusion enables the learning of true spatiotemporal "},"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":"1801.01415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-04T15:47:47Z","cross_cats_sorted":[],"title_canon_sha256":"3245a47408ad28bf7740ae6ca3d5b69662077fa2c6680302af535d86ade99fe6","abstract_canon_sha256":"c9cdaee544ae10c8566bfebf28218e184296b5f0df358118f7600fe4ebd05ec8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:42.182894Z","signature_b64":"Z74p6HB67IJVk4pesQuHTzOdxhpJuwrZwYi4U5EqLax4XPdrjvXGhex6+7SRon6yhxYbRqrEEjC2TQR+9yViBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bfc958b8f905ef4fba3440423460d11df3c00f11b100402e693e7af52315884","last_reissued_at":"2026-05-18T00:26:42.182213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:42.182213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What have we learned from deep representations for action recognition?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Axel Pinz, Christoph Feichtenhofer, Richard P. Wildes","submitted_at":"2018-01-04T15:47:47Z","abstract_excerpt":"As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing what two-stream models have learned in order to recognize actions in video. We show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions. Key observations include the following. First, cross-stream fusion enables the learning of true spatiotemporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01415","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":""},"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":"1801.01415","created_at":"2026-05-18T00:26:42.182310+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.01415v1","created_at":"2026-05-18T00:26:42.182310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01415","created_at":"2026-05-18T00:26:42.182310+00:00"},{"alias_kind":"pith_short_12","alias_value":"RP6JLC4PSBPP","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RP6JLC4PSBPPJ65D","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RP6JLC4P","created_at":"2026-05-18T12:32:50.500415+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/RP6JLC4PSBPPJ65DIQCCGRQNCH","json":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH.json","graph_json":"https://pith.science/api/pith-number/RP6JLC4PSBPPJ65DIQCCGRQNCH/graph.json","events_json":"https://pith.science/api/pith-number/RP6JLC4PSBPPJ65DIQCCGRQNCH/events.json","paper":"https://pith.science/paper/RP6JLC4P"},"agent_actions":{"view_html":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH","download_json":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH.json","view_paper":"https://pith.science/paper/RP6JLC4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.01415&json=true","fetch_graph":"https://pith.science/api/pith-number/RP6JLC4PSBPPJ65DIQCCGRQNCH/graph.json","fetch_events":"https://pith.science/api/pith-number/RP6JLC4PSBPPJ65DIQCCGRQNCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH/action/storage_attestation","attest_author":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH/action/author_attestation","sign_citation":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH/action/citation_signature","submit_replication":"https://pith.science/pith/RP6JLC4PSBPPJ65DIQCCGRQNCH/action/replication_record"}},"created_at":"2026-05-18T00:26:42.182310+00:00","updated_at":"2026-05-18T00:26:42.182310+00:00"}