{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U63UAFKMVK7AP5Z2KTOWGT2IPV","short_pith_number":"pith:U63UAFKM","schema_version":"1.0","canonical_sha256":"a7b740154caabe07f73a54dd634f487d5d937b47f6721aca53eb0c58a88b4b47","source":{"kind":"arxiv","id":"2405.16947","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Eldesokey, Adam Kortylewski, Christian Theobalt, Fangneng Zhan, Mohit Mendiratta, Peter Wonka, Qian Wang","submitted_at":"2024-05-27T08:39:38Z","abstract_excerpt":"We introduce the first zero-shot approach for Video Semantic Segmentation (VSS) based on pre-trained diffusion models. A growing research direction attempts to employ diffusion models to perform downstream vision tasks by exploiting their deep understanding of image semantics. Yet, the majority of these approaches have focused on image-related tasks like semantic correspondence and segmentation, with less emphasis on video tasks such as VSS. Ideally, diffusion-based image semantic segmentation approaches can be applied to videos in a frame-by-frame manner. However, we find their performance on"},"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":"2405.16947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:39:38Z","cross_cats_sorted":[],"title_canon_sha256":"7b7268ee7b0bbc65510a840ef0183ce5bfab4220e76cb5a962e53f920ef8ecaf","abstract_canon_sha256":"72b575f02250f2fd345209b84031611dce20419b14f5a5b06a01b70ae6952548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:37.869744Z","signature_b64":"GoBVhsQdiRySTSjqhtaqB7y0MSIKoiMbNoIcNjPjl5jd7HF3KCRmXSdTfaGVGyzDl/iMYs/q2a0Koo9R6CoXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b740154caabe07f73a54dd634f487d5d937b47f6721aca53eb0c58a88b4b47","last_reissued_at":"2026-07-05T08:23:37.869174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:37.869174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Eldesokey, Adam Kortylewski, Christian Theobalt, Fangneng Zhan, Mohit Mendiratta, Peter Wonka, Qian Wang","submitted_at":"2024-05-27T08:39:38Z","abstract_excerpt":"We introduce the first zero-shot approach for Video Semantic Segmentation (VSS) based on pre-trained diffusion models. A growing research direction attempts to employ diffusion models to perform downstream vision tasks by exploiting their deep understanding of image semantics. Yet, the majority of these approaches have focused on image-related tasks like semantic correspondence and segmentation, with less emphasis on video tasks such as VSS. Ideally, diffusion-based image semantic segmentation approaches can be applied to videos in a frame-by-frame manner. However, we find their performance on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16947","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.16947/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":"2405.16947","created_at":"2026-07-05T08:23:37.869246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16947v1","created_at":"2026-07-05T08:23:37.869246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16947","created_at":"2026-07-05T08:23:37.869246+00:00"},{"alias_kind":"pith_short_12","alias_value":"U63UAFKMVK7A","created_at":"2026-07-05T08:23:37.869246+00:00"},{"alias_kind":"pith_short_16","alias_value":"U63UAFKMVK7AP5Z2","created_at":"2026-07-05T08:23:37.869246+00:00"},{"alias_kind":"pith_short_8","alias_value":"U63UAFKM","created_at":"2026-07-05T08:23:37.869246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":228,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV","json":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV.json","graph_json":"https://pith.science/api/pith-number/U63UAFKMVK7AP5Z2KTOWGT2IPV/graph.json","events_json":"https://pith.science/api/pith-number/U63UAFKMVK7AP5Z2KTOWGT2IPV/events.json","paper":"https://pith.science/paper/U63UAFKM"},"agent_actions":{"view_html":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV","download_json":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV.json","view_paper":"https://pith.science/paper/U63UAFKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16947&json=true","fetch_graph":"https://pith.science/api/pith-number/U63UAFKMVK7AP5Z2KTOWGT2IPV/graph.json","fetch_events":"https://pith.science/api/pith-number/U63UAFKMVK7AP5Z2KTOWGT2IPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV/action/storage_attestation","attest_author":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV/action/author_attestation","sign_citation":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV/action/citation_signature","submit_replication":"https://pith.science/pith/U63UAFKMVK7AP5Z2KTOWGT2IPV/action/replication_record"}},"created_at":"2026-07-05T08:23:37.869246+00:00","updated_at":"2026-07-05T08:23:37.869246+00:00"}