{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AOZOFGKB6XDMPQ32OJXEBANVAS","short_pith_number":"pith:AOZOFGKB","schema_version":"1.0","canonical_sha256":"03b2e29941f5c6c7c37a726e4081b504a3c6a4c9b8c047327a90db00f9a9c67d","source":{"kind":"arxiv","id":"2207.08549","version":1},"attestation_state":"computed","paper":{"title":"Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghuan Lu, Dong Wei, Jiashun Chen, Kai Ma, Munan Ning, Xinyu Shi, Yefeng Zheng, Yu Zhang","submitted_at":"2022-07-18T12:12:42Z","abstract_excerpt":"Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. "},"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":"2207.08549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T12:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"bc401ab4696a1a824d50ae7f7491bf23b0e571ca6fc10d7c8e323fa7ef06aeaf","abstract_canon_sha256":"a833d91db4dfafdc65b0b05fcee83933e06b22a75647cd726ac863158469645f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:05.805467Z","signature_b64":"7RlTJ1G3za1UI1T6NFbVL5zyVp8C0zrFKDtED1mWh3/x4N4Z4xNeh/nqT30R0EPXUG+UrSbj1kqi+FrbTTN0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b2e29941f5c6c7c37a726e4081b504a3c6a4c9b8c047327a90db00f9a9c67d","last_reissued_at":"2026-07-05T04:41:05.805049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:05.805049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghuan Lu, Dong Wei, Jiashun Chen, Kai Ma, Munan Ning, Xinyu Shi, Yefeng Zheng, Yu Zhang","submitted_at":"2022-07-18T12:12:42Z","abstract_excerpt":"Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08549","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/2207.08549/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":"2207.08549","created_at":"2026-07-05T04:41:05.805108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08549v1","created_at":"2026-07-05T04:41:05.805108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08549","created_at":"2026-07-05T04:41:05.805108+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOZOFGKB6XDM","created_at":"2026-07-05T04:41:05.805108+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOZOFGKB6XDMPQ32","created_at":"2026-07-05T04:41:05.805108+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOZOFGKB","created_at":"2026-07-05T04:41:05.805108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13774","citing_title":"Segment Any Class (SAC): Multi-Class Few-Shot Semantic Segmentation via Class Region Proposals","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS","json":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS.json","graph_json":"https://pith.science/api/pith-number/AOZOFGKB6XDMPQ32OJXEBANVAS/graph.json","events_json":"https://pith.science/api/pith-number/AOZOFGKB6XDMPQ32OJXEBANVAS/events.json","paper":"https://pith.science/paper/AOZOFGKB"},"agent_actions":{"view_html":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS","download_json":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS.json","view_paper":"https://pith.science/paper/AOZOFGKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08549&json=true","fetch_graph":"https://pith.science/api/pith-number/AOZOFGKB6XDMPQ32OJXEBANVAS/graph.json","fetch_events":"https://pith.science/api/pith-number/AOZOFGKB6XDMPQ32OJXEBANVAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS/action/storage_attestation","attest_author":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS/action/author_attestation","sign_citation":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS/action/citation_signature","submit_replication":"https://pith.science/pith/AOZOFGKB6XDMPQ32OJXEBANVAS/action/replication_record"}},"created_at":"2026-07-05T04:41:05.805108+00:00","updated_at":"2026-07-05T04:41:05.805108+00:00"}