{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3C3RWYUAEJGRC2FPG6TKCAEXES","short_pith_number":"pith:3C3RWYUA","schema_version":"1.0","canonical_sha256":"d8b71b6280224d1168af37a6a100972481d3525d323179bab98983fd3592aee9","source":{"kind":"arxiv","id":"1709.06316","version":3},"attestation_state":"computed","paper":{"title":"Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lai Jiang, Mai Xu, Zulin Wang","submitted_at":"2017-09-19T09:45:03Z","abstract_excerpt":"Over the past few years, deep neural networks (DNNs) have exhibited great success in predicting the saliency of images. However, there are few works that apply DNNs to predict the saliency of generic videos. In this paper, we propose a novel DNN-based video saliency prediction method. Specifically, we establish a large-scale eye-tracking database of videos (LEDOV), which provides sufficient data to train the DNN models for predicting video saliency. Through the statistical analysis of our LEDOV database, we find that human attention is normally attracted by objects, particularly moving objects"},"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":"1709.06316","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-19T09:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"062ada9e113ee0a88b18410f554555782df0db886c5fb0d41869b0aee6dd8516","abstract_canon_sha256":"277342f3c0e3ffc8a37aa04e89cfbe993d25c01f8eb10d161a7af26acd62541d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:25.255587Z","signature_b64":"iwOgVQQRVfnZFrYENUqI5VbZO2pHqpNLELXQNWQj1/HxVbGO31h1363P+mieJXlQJWlrZMDz1T0psdJ7BImMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b71b6280224d1168af37a6a100972481d3525d323179bab98983fd3592aee9","last_reissued_at":"2026-05-17T23:56:25.255117Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:25.255117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Video Saliency with Object-to-Motion CNN and Two-layer Convolutional LSTM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lai Jiang, Mai Xu, Zulin Wang","submitted_at":"2017-09-19T09:45:03Z","abstract_excerpt":"Over the past few years, deep neural networks (DNNs) have exhibited great success in predicting the saliency of images. However, there are few works that apply DNNs to predict the saliency of generic videos. In this paper, we propose a novel DNN-based video saliency prediction method. Specifically, we establish a large-scale eye-tracking database of videos (LEDOV), which provides sufficient data to train the DNN models for predicting video saliency. Through the statistical analysis of our LEDOV database, we find that human attention is normally attracted by objects, particularly moving objects"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06316","kind":"arxiv","version":3},"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":"1709.06316","created_at":"2026-05-17T23:56:25.255183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06316v3","created_at":"2026-05-17T23:56:25.255183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06316","created_at":"2026-05-17T23:56:25.255183+00:00"},{"alias_kind":"pith_short_12","alias_value":"3C3RWYUAEJGR","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3C3RWYUAEJGRC2FP","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3C3RWYUA","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.00480","citing_title":"Predicting video saliency using crowdsourced mouse-tracking data","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01869","citing_title":"Simple vs complex temporal recurrences for video saliency prediction","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES","json":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES.json","graph_json":"https://pith.science/api/pith-number/3C3RWYUAEJGRC2FPG6TKCAEXES/graph.json","events_json":"https://pith.science/api/pith-number/3C3RWYUAEJGRC2FPG6TKCAEXES/events.json","paper":"https://pith.science/paper/3C3RWYUA"},"agent_actions":{"view_html":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES","download_json":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES.json","view_paper":"https://pith.science/paper/3C3RWYUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06316&json=true","fetch_graph":"https://pith.science/api/pith-number/3C3RWYUAEJGRC2FPG6TKCAEXES/graph.json","fetch_events":"https://pith.science/api/pith-number/3C3RWYUAEJGRC2FPG6TKCAEXES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES/action/storage_attestation","attest_author":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES/action/author_attestation","sign_citation":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES/action/citation_signature","submit_replication":"https://pith.science/pith/3C3RWYUAEJGRC2FPG6TKCAEXES/action/replication_record"}},"created_at":"2026-05-17T23:56:25.255183+00:00","updated_at":"2026-05-17T23:56:25.255183+00:00"}