{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:P7IGRMT3MGHQN3D2ZDOD2PP677","short_pith_number":"pith:P7IGRMT3","canonical_record":{"source":{"id":"2203.13253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-24T17:59:20Z","cross_cats_sorted":[],"title_canon_sha256":"68aa7158692ac967ac7765f336b0979344f04a9ade42f3cf01b3b3b8d74680e5","abstract_canon_sha256":"57cebc4f1f7310597d884f6db86a7c9efe77b426a7eedbd26a33f39d469e00ad"},"schema_version":"1.0"},"canonical_sha256":"7fd068b27b618f06ec7ac8dc3d3dfeffe86a7496fec1117152d861f78e05d3c6","source":{"kind":"arxiv","id":"2203.13253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13253","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13253v1","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13253","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"P7IGRMT3MGHQ","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"P7IGRMT3MGHQN3D2","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"P7IGRMT3","created_at":"2026-07-05T04:08:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:P7IGRMT3MGHQN3D2ZDOD2PP677","target":"record","payload":{"canonical_record":{"source":{"id":"2203.13253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-24T17:59:20Z","cross_cats_sorted":[],"title_canon_sha256":"68aa7158692ac967ac7765f336b0979344f04a9ade42f3cf01b3b3b8d74680e5","abstract_canon_sha256":"57cebc4f1f7310597d884f6db86a7c9efe77b426a7eedbd26a33f39d469e00ad"},"schema_version":"1.0"},"canonical_sha256":"7fd068b27b618f06ec7ac8dc3d3dfeffe86a7496fec1117152d861f78e05d3c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:22.323717Z","signature_b64":"iFlthdTJ5v1ZI5zDyTAjK/bq4DMGFWQrN7EzdtwAb9mrsBUhJBy8wT32+fOWB4LOGDrlCrmIG6pNNP1Jy8ooBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fd068b27b618f06ec7ac8dc3d3dfeffe86a7496fec1117152d861f78e05d3c6","last_reissued_at":"2026-07-05T04:08:22.323326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:22.323326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.13253","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zU+V3qJIxlxIb91fQTkTA71K10kNM9qvPJXuOxDZ3y9U6KKt5kFsH8QxhSNOn0EOe4OoYcIjLcJQqW9m1g1rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:43:08.955341Z"},"content_sha256":"d7c17f01431f73a1bbfff304f3e8aa1fe2512091da7825c14dd02473db23985f","schema_version":"1.0","event_id":"sha256:d7c17f01431f73a1bbfff304f3e8aa1fe2512091da7825c14dd02473db23985f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:P7IGRMT3MGHQN3D2ZDOD2PP677","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hisham Cholakkal, Jiale Cao, Michael Felsberg, Muhammad Haris Khan, Omkar Thawakar, Rao Muhammad Anwer, Salman Khan, Sanath Narayan","submitted_at":"2022-03-24T17:59:20Z","abstract_excerpt":"State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an attention computation ignores the multi-scale spatio-temporal feature relationships that are crucial to tackle target appearance deformations in videos. To address this issue, we propose a transformer-based VIS framework, named MS-STS VIS, that comprises a novel multi-scale spatio-temporal split (MS-STS) attention module in the encoder. The proposed MS-STS module "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13253","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/2203.13253/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xjbXHF7CekCKHywjWCvHNbFBnCLJU3/FYWUbCeoz3aBdOglSb5MeehKikQsNDrE9n5heWO22Kr3XqkNBuc43AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:43:08.955749Z"},"content_sha256":"d28b4a3dbb3b85b9419b11fdb7ac73e38450bc54086f229b9b29af3fdfe052cc","schema_version":"1.0","event_id":"sha256:d28b4a3dbb3b85b9419b11fdb7ac73e38450bc54086f229b9b29af3fdfe052cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7IGRMT3MGHQN3D2ZDOD2PP677/bundle.json","state_url":"https://pith.science/pith/P7IGRMT3MGHQN3D2ZDOD2PP677/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7IGRMT3MGHQN3D2ZDOD2PP677/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T18:43:08Z","links":{"resolver":"https://pith.science/pith/P7IGRMT3MGHQN3D2ZDOD2PP677","bundle":"https://pith.science/pith/P7IGRMT3MGHQN3D2ZDOD2PP677/bundle.json","state":"https://pith.science/pith/P7IGRMT3MGHQN3D2ZDOD2PP677/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7IGRMT3MGHQN3D2ZDOD2PP677/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P7IGRMT3MGHQN3D2ZDOD2PP677","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"57cebc4f1f7310597d884f6db86a7c9efe77b426a7eedbd26a33f39d469e00ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-24T17:59:20Z","title_canon_sha256":"68aa7158692ac967ac7765f336b0979344f04a9ade42f3cf01b3b3b8d74680e5"},"schema_version":"1.0","source":{"id":"2203.13253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13253","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13253v1","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13253","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"P7IGRMT3MGHQ","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"P7IGRMT3MGHQN3D2","created_at":"2026-07-05T04:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"P7IGRMT3","created_at":"2026-07-05T04:08:22Z"}],"graph_snapshots":[{"event_id":"sha256:d28b4a3dbb3b85b9419b11fdb7ac73e38450bc54086f229b9b29af3fdfe052cc","target":"graph","created_at":"2026-07-05T04:08:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.13253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an attention computation ignores the multi-scale spatio-temporal feature relationships that are crucial to tackle target appearance deformations in videos. To address this issue, we propose a transformer-based VIS framework, named MS-STS VIS, that comprises a novel multi-scale spatio-temporal split (MS-STS) attention module in the encoder. The proposed MS-STS module ","authors_text":"Fahad Shahbaz Khan, Hisham Cholakkal, Jiale Cao, Michael Felsberg, Muhammad Haris Khan, Omkar Thawakar, Rao Muhammad Anwer, Salman Khan, Sanath Narayan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-24T17:59:20Z","title":"Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13253","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d7c17f01431f73a1bbfff304f3e8aa1fe2512091da7825c14dd02473db23985f","target":"record","created_at":"2026-07-05T04:08:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"57cebc4f1f7310597d884f6db86a7c9efe77b426a7eedbd26a33f39d469e00ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-24T17:59:20Z","title_canon_sha256":"68aa7158692ac967ac7765f336b0979344f04a9ade42f3cf01b3b3b8d74680e5"},"schema_version":"1.0","source":{"id":"2203.13253","kind":"arxiv","version":1}},"canonical_sha256":"7fd068b27b618f06ec7ac8dc3d3dfeffe86a7496fec1117152d861f78e05d3c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fd068b27b618f06ec7ac8dc3d3dfeffe86a7496fec1117152d861f78e05d3c6","first_computed_at":"2026-07-05T04:08:22.323326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:22.323326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iFlthdTJ5v1ZI5zDyTAjK/bq4DMGFWQrN7EzdtwAb9mrsBUhJBy8wT32+fOWB4LOGDrlCrmIG6pNNP1Jy8ooBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:22.323717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7c17f01431f73a1bbfff304f3e8aa1fe2512091da7825c14dd02473db23985f","sha256:d28b4a3dbb3b85b9419b11fdb7ac73e38450bc54086f229b9b29af3fdfe052cc"],"state_sha256":"b4e6fefa0f25e740e593e4b85ab6474020e0350e3ec974ec083328cd7d4110fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnZJFFdgACyMGddAOMkgUBCaLletGhOn/yO6vANiFqGOFds8nNgiJU94ZjNkqUQE4vKkkqxXSQgE3EVUqVLvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:43:08.957799Z","bundle_sha256":"a748ee37f0683ff89d1c1a0991a8ea40e98d32b2def79b2a41b4604035ec30de"}}