{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QDDKVCNMDJFY3EQC7UYMQTXATG","short_pith_number":"pith:QDDKVCNM","canonical_record":{"source":{"id":"2102.04762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T11:27:59Z","cross_cats_sorted":[],"title_canon_sha256":"d98c672f07857cd9595ed66d09dfb943f662b50740fe7bcf01ab7bb34cd2aa1d","abstract_canon_sha256":"f5fff17765898b963c74ece96d13a1c9881601391d227be36dc90fd014b2014b"},"schema_version":"1.0"},"canonical_sha256":"80c6aa89ac1a4b8d9202fd30c84ee09981003abe2801044d8d38d0b12ab8850c","source":{"kind":"arxiv","id":"2102.04762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04762","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04762v1","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04762","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"QDDKVCNMDJFY","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"QDDKVCNMDJFY3EQC","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"QDDKVCNM","created_at":"2026-07-05T02:14:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QDDKVCNMDJFY3EQC7UYMQTXATG","target":"record","payload":{"canonical_record":{"source":{"id":"2102.04762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T11:27:59Z","cross_cats_sorted":[],"title_canon_sha256":"d98c672f07857cd9595ed66d09dfb943f662b50740fe7bcf01ab7bb34cd2aa1d","abstract_canon_sha256":"f5fff17765898b963c74ece96d13a1c9881601391d227be36dc90fd014b2014b"},"schema_version":"1.0"},"canonical_sha256":"80c6aa89ac1a4b8d9202fd30c84ee09981003abe2801044d8d38d0b12ab8850c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:04.531478Z","signature_b64":"+co2pnw5Dq9yy6cq6V+HIAdT3gP7x4JwxfgToMWVh2Vs/9q+Rjm3Co9ESpDMu5mzn4CcFP0pXe042J3A89ydCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80c6aa89ac1a4b8d9202fd30c84ee09981003abe2801044d8d38d0b12ab8850c","last_reissued_at":"2026-07-05T02:14:04.530988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:04.530988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.04762","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":"2026-07-05T02:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"coK3V8ZnT7qfmQqT+RR25K0JZ4EefQkpNqfsU5WkO7Pw3Z0GlzS85ptqptN6nRT+NWa7LdgtIspHp2OjABBWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:49:04.718325Z"},"content_sha256":"bcd1a6364ba9b21b8c811154e7ea6d34525410497eeb80ed5e373f13127b277f","schema_version":"1.0","event_id":"sha256:bcd1a6364ba9b21b8c811154e7ea6d34525410497eeb80ed5e373f13127b277f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QDDKVCNMDJFY3EQC7UYMQTXATG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linwei Ye, Mrigank Rochan, Xiaoqin Zhang, Yang Wang, Zhi Liu","submitted_at":"2021-02-09T11:27:59Z","abstract_excerpt":"We consider the problem of referring segmentation in images and videos with natural language. Given an input image (or video) and a referring expression, the goal is to segment the entity referred by the expression in the image or video. In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the visual input. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04762","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/2102.04762/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":"2026-07-05T02:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z06eET8MfizgkYZ0xTu2EOXxldDhIfyvrQt6KNGs0+7/35vVGKvYNrLq1pCW3OGoFOYns39GEfh3LhaXbptTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:49:04.718926Z"},"content_sha256":"24f99e01574c88688ee8b4d074d3b43aedc89240ec5c51a84aaaa3057e5bcb41","schema_version":"1.0","event_id":"sha256:24f99e01574c88688ee8b4d074d3b43aedc89240ec5c51a84aaaa3057e5bcb41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDDKVCNMDJFY3EQC7UYMQTXATG/bundle.json","state_url":"https://pith.science/pith/QDDKVCNMDJFY3EQC7UYMQTXATG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDDKVCNMDJFY3EQC7UYMQTXATG/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":"2026-08-23T15:49:04Z","links":{"resolver":"https://pith.science/pith/QDDKVCNMDJFY3EQC7UYMQTXATG","bundle":"https://pith.science/pith/QDDKVCNMDJFY3EQC7UYMQTXATG/bundle.json","state":"https://pith.science/pith/QDDKVCNMDJFY3EQC7UYMQTXATG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDDKVCNMDJFY3EQC7UYMQTXATG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QDDKVCNMDJFY3EQC7UYMQTXATG","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":"f5fff17765898b963c74ece96d13a1c9881601391d227be36dc90fd014b2014b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T11:27:59Z","title_canon_sha256":"d98c672f07857cd9595ed66d09dfb943f662b50740fe7bcf01ab7bb34cd2aa1d"},"schema_version":"1.0","source":{"id":"2102.04762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04762","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04762v1","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04762","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"QDDKVCNMDJFY","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"QDDKVCNMDJFY3EQC","created_at":"2026-07-05T02:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"QDDKVCNM","created_at":"2026-07-05T02:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:24f99e01574c88688ee8b4d074d3b43aedc89240ec5c51a84aaaa3057e5bcb41","target":"graph","created_at":"2026-07-05T02:14:04Z","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/2102.04762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of referring segmentation in images and videos with natural language. Given an input image (or video) and a referring expression, the goal is to segment the entity referred by the expression in the image or video. In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features. Our model can adaptively focus on informative words in the referring expression and important regions in the visual input. W","authors_text":"Linwei Ye, Mrigank Rochan, Xiaoqin Zhang, Yang Wang, Zhi Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T11:27:59Z","title":"Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04762","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:bcd1a6364ba9b21b8c811154e7ea6d34525410497eeb80ed5e373f13127b277f","target":"record","created_at":"2026-07-05T02:14:04Z","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":"f5fff17765898b963c74ece96d13a1c9881601391d227be36dc90fd014b2014b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-09T11:27:59Z","title_canon_sha256":"d98c672f07857cd9595ed66d09dfb943f662b50740fe7bcf01ab7bb34cd2aa1d"},"schema_version":"1.0","source":{"id":"2102.04762","kind":"arxiv","version":1}},"canonical_sha256":"80c6aa89ac1a4b8d9202fd30c84ee09981003abe2801044d8d38d0b12ab8850c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80c6aa89ac1a4b8d9202fd30c84ee09981003abe2801044d8d38d0b12ab8850c","first_computed_at":"2026-07-05T02:14:04.530988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:04.530988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+co2pnw5Dq9yy6cq6V+HIAdT3gP7x4JwxfgToMWVh2Vs/9q+Rjm3Co9ESpDMu5mzn4CcFP0pXe042J3A89ydCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:04.531478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.04762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcd1a6364ba9b21b8c811154e7ea6d34525410497eeb80ed5e373f13127b277f","sha256:24f99e01574c88688ee8b4d074d3b43aedc89240ec5c51a84aaaa3057e5bcb41"],"state_sha256":"35c1b75a9bb5bceefc0f082b81c296900052dfb100ae0e4e82cb4000d4ba1b50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ETXQwLtXapiMPlXz1xwmTpLreSifOMW/EqqKEHZs1UxTbiLlHvu7DbUMk3skzEvv/ESv4TUyotB3M+utVS3zBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:49:04.723197Z","bundle_sha256":"6243b1ea4056e5f5c64ebaee6948b31df3a6bc8c48c3b5755ac63f99e12db4cc"}}