{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RTXUJEYKJGKTUEVWTWYY2E6RHS","short_pith_number":"pith:RTXUJEYK","schema_version":"1.0","canonical_sha256":"8cef44930a49953a12b69db18d13d13c8e9892ba039901a54e047b06607add75","source":{"kind":"arxiv","id":"2112.08275","version":2},"attestation_state":"computed","paper":{"title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junfeng Wu, Song Bai, Wenqing Zhang, Xiang Bai, Yi Jiang","submitted_at":"2021-12-15T17:09:18Z","abstract_excerpt":"In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently. To achieve this, SeqFormer locates an instance in each frame and aggregates temporal information to learn a powerful representation of a video-level instance, which is used to predict the mask sequences on each frame dynamically. "},"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":"2112.08275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-15T17:09:18Z","cross_cats_sorted":[],"title_canon_sha256":"600d8046f242c32b019c3379c0ab89a3a66d64ed5f45c8a50b3a16c5b4012bad","abstract_canon_sha256":"7b94fbead62481434c87f63af7c85d2ebb33de4d57142ccc8d9801f463c95ffe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:15.743064Z","signature_b64":"HpLXW3R3Me04O7VHWp0Su3TpQFw6jYLg3fgMBmXNavN2+zL8uHRb1kEG1pCbAorLUndUyGSQhMbRmUIBITTgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cef44930a49953a12b69db18d13d13c8e9892ba039901a54e047b06607add75","last_reissued_at":"2026-07-05T04:42:15.742664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:15.742664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junfeng Wu, Song Bai, Wenqing Zhang, Xiang Bai, Yi Jiang","submitted_at":"2021-12-15T17:09:18Z","abstract_excerpt":"In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently. To achieve this, SeqFormer locates an instance in each frame and aggregates temporal information to learn a powerful representation of a video-level instance, which is used to predict the mask sequences on each frame dynamically. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08275","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/2112.08275/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":"2112.08275","created_at":"2026-07-05T04:42:15.742722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08275v2","created_at":"2026-07-05T04:42:15.742722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08275","created_at":"2026-07-05T04:42:15.742722+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTXUJEYKJGKT","created_at":"2026-07-05T04:42:15.742722+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTXUJEYKJGKTUEVW","created_at":"2026-07-05T04:42:15.742722+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTXUJEYK","created_at":"2026-07-05T04:42:15.742722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20140","citing_title":"SA-VIS: Sparse frame Annotations for training Video Instance Segmentation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20140","citing_title":"SA-VIS: Sparse frame Annotations for training Video Instance Segmentation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS","json":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS.json","graph_json":"https://pith.science/api/pith-number/RTXUJEYKJGKTUEVWTWYY2E6RHS/graph.json","events_json":"https://pith.science/api/pith-number/RTXUJEYKJGKTUEVWTWYY2E6RHS/events.json","paper":"https://pith.science/paper/RTXUJEYK"},"agent_actions":{"view_html":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS","download_json":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS.json","view_paper":"https://pith.science/paper/RTXUJEYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08275&json=true","fetch_graph":"https://pith.science/api/pith-number/RTXUJEYKJGKTUEVWTWYY2E6RHS/graph.json","fetch_events":"https://pith.science/api/pith-number/RTXUJEYKJGKTUEVWTWYY2E6RHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS/action/storage_attestation","attest_author":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS/action/author_attestation","sign_citation":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS/action/citation_signature","submit_replication":"https://pith.science/pith/RTXUJEYKJGKTUEVWTWYY2E6RHS/action/replication_record"}},"created_at":"2026-07-05T04:42:15.742722+00:00","updated_at":"2026-07-05T04:42:15.742722+00:00"}