{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DTRKLXN3MTAMULYVKB54OQLV6X","short_pith_number":"pith:DTRKLXN3","schema_version":"1.0","canonical_sha256":"1ce2a5ddbb64c0ca2f15507bc74175f5d86bf4736cd10f9b0a7440776ca1661a","source":{"kind":"arxiv","id":"2105.04213","version":2},"attestation_state":"computed","paper":{"title":"Temporal-Spatial Feature Pyramid for Video Saliency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qinyao Chang, Shiping Zhu","submitted_at":"2021-05-10T09:14:14Z","abstract_excerpt":"Multi-level features are important for saliency detection. Better combination and use of multi-level features with time information can greatly improve the accuracy of the video saliency model. In order to fully combine multi-level features and make it serve the video saliency model, we propose a 3D fully convolutional encoder-decoder architecture for video saliency detection, which combines scale, space and time information for video saliency modeling. The encoder extracts multi-scale temporal-spatial features from the input continuous video frames, and then constructs temporal-spatial featur"},"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":"2105.04213","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T09:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"b92d3a9c21792a9b9bec6843d9809fd886bc951aa1e8c491f7d2b61e2a1ab0c4","abstract_canon_sha256":"20abdf264a77641fa4e929feb01ad279f3a1f0d36388a244aec60534a85a7c89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:49.725128Z","signature_b64":"1Ucm9uWnl6XtRHYk9O/49NIULxBuE8vWVzTjNN8Z4pJgufBga1BDG1o7St0rgevHBuXXilPE1rriSBb66u78Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce2a5ddbb64c0ca2f15507bc74175f5d86bf4736cd10f9b0a7440776ca1661a","last_reissued_at":"2026-07-05T03:13:49.724596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:49.724596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal-Spatial Feature Pyramid for Video Saliency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qinyao Chang, Shiping Zhu","submitted_at":"2021-05-10T09:14:14Z","abstract_excerpt":"Multi-level features are important for saliency detection. Better combination and use of multi-level features with time information can greatly improve the accuracy of the video saliency model. In order to fully combine multi-level features and make it serve the video saliency model, we propose a 3D fully convolutional encoder-decoder architecture for video saliency detection, which combines scale, space and time information for video saliency modeling. The encoder extracts multi-scale temporal-spatial features from the input continuous video frames, and then constructs temporal-spatial featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04213","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/2105.04213/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":"2105.04213","created_at":"2026-07-05T03:13:49.724664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04213v2","created_at":"2026-07-05T03:13:49.724664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04213","created_at":"2026-07-05T03:13:49.724664+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTRKLXN3MTAM","created_at":"2026-07-05T03:13:49.724664+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTRKLXN3MTAMULYV","created_at":"2026-07-05T03:13:49.724664+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTRKLXN3","created_at":"2026-07-05T03:13:49.724664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03540","citing_title":"Attend to Anything: Foundation Model for Unified Human Attention Modeling","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29302","citing_title":"ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23790","citing_title":"Exploring deep learning for Event-Based Saliency Prediction with a Transformer-based model","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08858","citing_title":"BIAS: A Biologically Inspired Algorithm for Video Saliency Detection","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X","json":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X.json","graph_json":"https://pith.science/api/pith-number/DTRKLXN3MTAMULYVKB54OQLV6X/graph.json","events_json":"https://pith.science/api/pith-number/DTRKLXN3MTAMULYVKB54OQLV6X/events.json","paper":"https://pith.science/paper/DTRKLXN3"},"agent_actions":{"view_html":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X","download_json":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X.json","view_paper":"https://pith.science/paper/DTRKLXN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04213&json=true","fetch_graph":"https://pith.science/api/pith-number/DTRKLXN3MTAMULYVKB54OQLV6X/graph.json","fetch_events":"https://pith.science/api/pith-number/DTRKLXN3MTAMULYVKB54OQLV6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X/action/storage_attestation","attest_author":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X/action/author_attestation","sign_citation":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X/action/citation_signature","submit_replication":"https://pith.science/pith/DTRKLXN3MTAMULYVKB54OQLV6X/action/replication_record"}},"created_at":"2026-07-05T03:13:49.724664+00:00","updated_at":"2026-07-05T03:13:49.724664+00:00"}