{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DODNNKDGI2XCYZINFMYRZKAHTL","short_pith_number":"pith:DODNNKDG","canonical_record":{"source":{"id":"2208.12801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-26T17:51:02Z","cross_cats_sorted":[],"title_canon_sha256":"6756ec50fd1347620ac5b80689b9a3e07dd1c69f6a85d2456e1dc002f747a5d5","abstract_canon_sha256":"23d99b519ce64c5f2dc9917664803033b324de9ba863d5fcb5ff3b7f8941cf4c"},"schema_version":"1.0"},"canonical_sha256":"1b86d6a86646ae2c650d2b311ca8079adf24581ed536c969ccc8cf8bb8be3077","source":{"kind":"arxiv","id":"2208.12801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12801","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12801v2","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12801","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"pith_short_12","alias_value":"DODNNKDGI2XC","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"pith_short_16","alias_value":"DODNNKDGI2XCYZIN","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"pith_short_8","alias_value":"DODNNKDG","created_at":"2026-07-05T05:21:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DODNNKDGI2XCYZINFMYRZKAHTL","target":"record","payload":{"canonical_record":{"source":{"id":"2208.12801","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-26T17:51:02Z","cross_cats_sorted":[],"title_canon_sha256":"6756ec50fd1347620ac5b80689b9a3e07dd1c69f6a85d2456e1dc002f747a5d5","abstract_canon_sha256":"23d99b519ce64c5f2dc9917664803033b324de9ba863d5fcb5ff3b7f8941cf4c"},"schema_version":"1.0"},"canonical_sha256":"1b86d6a86646ae2c650d2b311ca8079adf24581ed536c969ccc8cf8bb8be3077","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:02.716425Z","signature_b64":"3iwAMY8UVJvzGbup/PnLZLhu9Xl/hOaz9ZXS7Ovh5uGiuaWhzQ7GVnVdCSwiW3SJt80DAJBjweD2MczmoPEQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b86d6a86646ae2c650d2b311ca8079adf24581ed536c969ccc8cf8bb8be3077","last_reissued_at":"2026-07-05T05:21:02.716014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:02.716014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.12801","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:21:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aTfJMt0cR0qRbbQL0gmGIRgk3I6D3WVJgzAuAeNIu1Q4RFrizFhJoOIooffLJetbXVVxvsumftOwByo8MhVoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:39:41.139333Z"},"content_sha256":"7c7dcac42fe672afc4984e919aad59f0bc38a94ce20641fa37f197b868369af1","schema_version":"1.0","event_id":"sha256:7c7dcac42fe672afc4984e919aad59f0bc38a94ce20641fa37f197b868369af1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DODNNKDGI2XCYZINFMYRZKAHTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VMFormer: End-to-End Video Matting with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Humphrey Shi, Jiachen Li, Marianna Ohanyan, Shant Navasardyan, Vidit Goel, Yunchao Wei","submitted_at":"2022-08-26T17:51:02Z","abstract_excerpt":"Video matting aims to predict the alpha mattes for each frame from a given input video sequence. Recent solutions to video matting have been dominated by deep convolutional neural networks (CNN) for the past few years, which have become the de-facto standard for both academia and industry. However, they have inbuilt inductive bias of locality and do not capture global characteristics of an image due to the CNN-based architectures. They also lack long-range temporal modeling considering computational costs when dealing with feature maps of multiple frames. In this paper, we propose VMFormer: a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12801","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/2208.12801/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":"2026-07-05T05:21:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5+479P9/xShjQV6JLDEjBP9qG9uIWTaHijUDqxP8BSLyIbsJ3sZWkzY+TwVHJyoLm+gH4WSC3lG2JzqswaQ/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:39:41.140233Z"},"content_sha256":"952e07c762d5909caabd6627c312fc0d168baeb5fdd8a090bc0c1a6f7f4a58f0","schema_version":"1.0","event_id":"sha256:952e07c762d5909caabd6627c312fc0d168baeb5fdd8a090bc0c1a6f7f4a58f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DODNNKDGI2XCYZINFMYRZKAHTL/bundle.json","state_url":"https://pith.science/pith/DODNNKDGI2XCYZINFMYRZKAHTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DODNNKDGI2XCYZINFMYRZKAHTL/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":"2026-08-07T15:39:41Z","links":{"resolver":"https://pith.science/pith/DODNNKDGI2XCYZINFMYRZKAHTL","bundle":"https://pith.science/pith/DODNNKDGI2XCYZINFMYRZKAHTL/bundle.json","state":"https://pith.science/pith/DODNNKDGI2XCYZINFMYRZKAHTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DODNNKDGI2XCYZINFMYRZKAHTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DODNNKDGI2XCYZINFMYRZKAHTL","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":"23d99b519ce64c5f2dc9917664803033b324de9ba863d5fcb5ff3b7f8941cf4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-26T17:51:02Z","title_canon_sha256":"6756ec50fd1347620ac5b80689b9a3e07dd1c69f6a85d2456e1dc002f747a5d5"},"schema_version":"1.0","source":{"id":"2208.12801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12801","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12801v2","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12801","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"pith_short_12","alias_value":"DODNNKDGI2XC","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"pith_short_16","alias_value":"DODNNKDGI2XCYZIN","created_at":"2026-07-05T05:21:02Z"},{"alias_kind":"pith_short_8","alias_value":"DODNNKDG","created_at":"2026-07-05T05:21:02Z"}],"graph_snapshots":[{"event_id":"sha256:952e07c762d5909caabd6627c312fc0d168baeb5fdd8a090bc0c1a6f7f4a58f0","target":"graph","created_at":"2026-07-05T05:21:02Z","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/2208.12801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video matting aims to predict the alpha mattes for each frame from a given input video sequence. Recent solutions to video matting have been dominated by deep convolutional neural networks (CNN) for the past few years, which have become the de-facto standard for both academia and industry. However, they have inbuilt inductive bias of locality and do not capture global characteristics of an image due to the CNN-based architectures. They also lack long-range temporal modeling considering computational costs when dealing with feature maps of multiple frames. In this paper, we propose VMFormer: a ","authors_text":"Humphrey Shi, Jiachen Li, Marianna Ohanyan, Shant Navasardyan, Vidit Goel, Yunchao Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-26T17:51:02Z","title":"VMFormer: End-to-End Video Matting with Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12801","kind":"arxiv","version":2},"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":"sha256:7c7dcac42fe672afc4984e919aad59f0bc38a94ce20641fa37f197b868369af1","target":"record","created_at":"2026-07-05T05:21:02Z","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":"23d99b519ce64c5f2dc9917664803033b324de9ba863d5fcb5ff3b7f8941cf4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-26T17:51:02Z","title_canon_sha256":"6756ec50fd1347620ac5b80689b9a3e07dd1c69f6a85d2456e1dc002f747a5d5"},"schema_version":"1.0","source":{"id":"2208.12801","kind":"arxiv","version":2}},"canonical_sha256":"1b86d6a86646ae2c650d2b311ca8079adf24581ed536c969ccc8cf8bb8be3077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b86d6a86646ae2c650d2b311ca8079adf24581ed536c969ccc8cf8bb8be3077","first_computed_at":"2026-07-05T05:21:02.716014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:02.716014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3iwAMY8UVJvzGbup/PnLZLhu9Xl/hOaz9ZXS7Ovh5uGiuaWhzQ7GVnVdCSwiW3SJt80DAJBjweD2MczmoPEQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:02.716425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c7dcac42fe672afc4984e919aad59f0bc38a94ce20641fa37f197b868369af1","sha256:952e07c762d5909caabd6627c312fc0d168baeb5fdd8a090bc0c1a6f7f4a58f0"],"state_sha256":"3c764b3229b90b97ae5d5c9f0071c2bcceca009a5443d57ad3a475a8d284fddc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoKAYqK+Q5yGaKiUZMLq69RAqwKjOXExzAjQz3o883Ctg5lEi5XoHRRoThHUjC0cbF4s1VDzirOnY1+uCe8JDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:39:41.146389Z","bundle_sha256":"a76692fa0f01a9ce3fdfc057c0ef0c958472ff5043f81b7bb26da56f1508fd83"}}