{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MXPYUCAYMF77HX5YR5WYEPYKDD","short_pith_number":"pith:MXPYUCAY","schema_version":"1.0","canonical_sha256":"65df8a0818617ff3dfb88f6d823f0a18d2823dfcc55a2964fd189c6cd0ff2884","source":{"kind":"arxiv","id":"1907.01869","version":4},"attestation_state":"computed","paper":{"title":"Simple vs complex temporal recurrences for video saliency prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eva Mohedano, Juan Jose Nieto, Kevin McGuinness, Noel E. O'Connor, Panagiotis Linardos, Xavier Giro-i-Nieto","submitted_at":"2019-07-03T12:02:05Z","abstract_excerpt":"This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within the architecture, while the second is a conceptually simple exponential moving average of an internal convolutional state. We use weights pre-trained on the SALICON dataset and fine-tune our model on DHF1K. Our results show that both modifications achieve state-of-the-art results and produce similar saliency maps. Source code is available at https:/"},"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":"1907.01869","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-03T12:02:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4fdb0534e2793cfd5e5b1e5a6e7cdb33aaf66be72c80329c6d28b226bd20fc97","abstract_canon_sha256":"8d4cc824b57ee155292660c0e772785f2706618c6e515a82af9fa1ceab50b716"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:29.833921Z","signature_b64":"kqLprgSOzt6Ws9HcSwXlH5vfLXDboL832G3XqwtPlXH+FUiH16M+Vu4kXc2cq1+usu1reED95cpIhr33a9yLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65df8a0818617ff3dfb88f6d823f0a18d2823dfcc55a2964fd189c6cd0ff2884","last_reissued_at":"2026-05-17T23:40:29.833209Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:29.833209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple vs complex temporal recurrences for video saliency prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Eva Mohedano, Juan Jose Nieto, Kevin McGuinness, Noel E. O'Connor, Panagiotis Linardos, Xavier Giro-i-Nieto","submitted_at":"2019-07-03T12:02:05Z","abstract_excerpt":"This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within the architecture, while the second is a conceptually simple exponential moving average of an internal convolutional state. We use weights pre-trained on the SALICON dataset and fine-tune our model on DHF1K. Our results show that both modifications achieve state-of-the-art results and produce similar saliency maps. Source code is available at https:/"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01869","kind":"arxiv","version":4},"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":"1907.01869","created_at":"2026-05-17T23:40:29.833349+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01869v4","created_at":"2026-05-17T23:40:29.833349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01869","created_at":"2026-05-17T23:40:29.833349+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXPYUCAYMF77","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXPYUCAYMF77HX5Y","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXPYUCAY","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.28251","citing_title":"DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08858","citing_title":"BIAS: A Biologically Inspired Algorithm for Video Saliency Detection","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD","json":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD.json","graph_json":"https://pith.science/api/pith-number/MXPYUCAYMF77HX5YR5WYEPYKDD/graph.json","events_json":"https://pith.science/api/pith-number/MXPYUCAYMF77HX5YR5WYEPYKDD/events.json","paper":"https://pith.science/paper/MXPYUCAY"},"agent_actions":{"view_html":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD","download_json":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD.json","view_paper":"https://pith.science/paper/MXPYUCAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01869&json=true","fetch_graph":"https://pith.science/api/pith-number/MXPYUCAYMF77HX5YR5WYEPYKDD/graph.json","fetch_events":"https://pith.science/api/pith-number/MXPYUCAYMF77HX5YR5WYEPYKDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD/action/storage_attestation","attest_author":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD/action/author_attestation","sign_citation":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD/action/citation_signature","submit_replication":"https://pith.science/pith/MXPYUCAYMF77HX5YR5WYEPYKDD/action/replication_record"}},"created_at":"2026-05-17T23:40:29.833349+00:00","updated_at":"2026-05-17T23:40:29.833349+00:00"}