{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4PSARZ7O6TU2CPCWQO5UL7XM3","short_pith_number":"pith:B4PSARZ7","schema_version":"1.0","canonical_sha256":"0f1f20473f77a74d09e2b41dda2ff766c479678fcdf22df013471881ea68d2d3","source":{"kind":"arxiv","id":"2408.15521","version":3},"attestation_state":"computed","paper":{"title":"A Simple Baseline with Single-encoder for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Byeongju Han, Dongyoon Wee, Ilchae Jung, Jeany Son, Seonghoon Yu, Taeoh Kim, Yunho Kim","submitted_at":"2024-08-28T04:14:01Z","abstract_excerpt":"Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g., Swin transformer and BERT (uni-modal encoders) or CLIP (a multi-modal dual-encoder), lack dense multi-modal interactions during pre-training, leading to a gap with a pixel-level RIS task. To bridge this gap, existing RIS methods often rely on multi-modal fusion modules that interact two encoders, but this approach leads to high computational costs. In this paper, we present a"},"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":"2408.15521","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T04:14:01Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"9510160c214bac7e6c77238c3ab53e636cbed9a1e647063757db7f138dc18773","abstract_canon_sha256":"478542e221ba213a604f4191905d29900fe0e2de4ad3d0226c2513576eb78c36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:31.973142Z","signature_b64":"PTqz+pwCvxR+ob29f0sevHwkxsAN7yL5nO+UiWkKT+cPWScPZIIK6qZXDq1CvzQTDupSxwycRq/jVkfI3lj6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1f20473f77a74d09e2b41dda2ff766c479678fcdf22df013471881ea68d2d3","last_reissued_at":"2026-07-05T11:22:31.972678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:31.972678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Baseline with Single-encoder for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Byeongju Han, Dongyoon Wee, Ilchae Jung, Jeany Son, Seonghoon Yu, Taeoh Kim, Yunho Kim","submitted_at":"2024-08-28T04:14:01Z","abstract_excerpt":"Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g., Swin transformer and BERT (uni-modal encoders) or CLIP (a multi-modal dual-encoder), lack dense multi-modal interactions during pre-training, leading to a gap with a pixel-level RIS task. To bridge this gap, existing RIS methods often rely on multi-modal fusion modules that interact two encoders, but this approach leads to high computational costs. In this paper, we present a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15521","kind":"arxiv","version":3},"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/2408.15521/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":"2408.15521","created_at":"2026-07-05T11:22:31.972736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15521v3","created_at":"2026-07-05T11:22:31.972736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15521","created_at":"2026-07-05T11:22:31.972736+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4PSARZ7O6TU","created_at":"2026-07-05T11:22:31.972736+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4PSARZ7O6TU2CPC","created_at":"2026-07-05T11:22:31.972736+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4PSARZ7","created_at":"2026-07-05T11:22:31.972736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13667","citing_title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3","json":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3.json","graph_json":"https://pith.science/api/pith-number/B4PSARZ7O6TU2CPCWQO5UL7XM3/graph.json","events_json":"https://pith.science/api/pith-number/B4PSARZ7O6TU2CPCWQO5UL7XM3/events.json","paper":"https://pith.science/paper/B4PSARZ7"},"agent_actions":{"view_html":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3","download_json":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3.json","view_paper":"https://pith.science/paper/B4PSARZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15521&json=true","fetch_graph":"https://pith.science/api/pith-number/B4PSARZ7O6TU2CPCWQO5UL7XM3/graph.json","fetch_events":"https://pith.science/api/pith-number/B4PSARZ7O6TU2CPCWQO5UL7XM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3/action/storage_attestation","attest_author":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3/action/author_attestation","sign_citation":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3/action/citation_signature","submit_replication":"https://pith.science/pith/B4PSARZ7O6TU2CPCWQO5UL7XM3/action/replication_record"}},"created_at":"2026-07-05T11:22:31.972736+00:00","updated_at":"2026-07-05T11:22:31.972736+00:00"}