{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TZMJQ2FHMQTLD7K3D24FZ7VZ5E","short_pith_number":"pith:TZMJQ2FH","schema_version":"1.0","canonical_sha256":"9e589868a76426b1fd5b1eb85cfeb9e932b1c017ab903ca6805b6407e3e9ceb7","source":{"kind":"arxiv","id":"1907.12347","version":2},"attestation_state":"computed","paper":{"title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Tianhan Wei, Xiang Li, Yau Pun Chen, Yu-Wing Tai","submitted_at":"2019-07-29T11:47:25Z","abstract_excerpt":"Over the past few years, we have witnessed the success of deep learning in image recognition thanks to the availability of large-scale human-annotated datasets such as PASCAL VOC, ImageNet, and COCO. Although these datasets have covered a wide range of object categories, there are still a significant number of objects that are not included. Can we perform the same task without a lot of human annotations? In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only. To evaluate and validate the performance of our approach"},"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":"1907.12347","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-29T11:47:25Z","cross_cats_sorted":[],"title_canon_sha256":"2657753babdd2a54062220a12b15dee872620204a71e9da25da8bbe724646307","abstract_canon_sha256":"3c3f131414ad414fcb4a3048b9b85aff7b66e1415e9ff0ff4a8fe6ee3a5feec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:00.748090Z","signature_b64":"fYx7UTsbG0+15WPdgvW7iQdPo8Y3PVhfJnmIcE/NQEfKnBjnhlnMqwwA4MBhVJdVwf4r9pHhATmUhqK+nroxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e589868a76426b1fd5b1eb85cfeb9e932b1c017ab903ca6805b6407e3e9ceb7","last_reissued_at":"2026-07-05T02:02:00.747654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:00.747654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Tianhan Wei, Xiang Li, Yau Pun Chen, Yu-Wing Tai","submitted_at":"2019-07-29T11:47:25Z","abstract_excerpt":"Over the past few years, we have witnessed the success of deep learning in image recognition thanks to the availability of large-scale human-annotated datasets such as PASCAL VOC, ImageNet, and COCO. Although these datasets have covered a wide range of object categories, there are still a significant number of objects that are not included. Can we perform the same task without a lot of human annotations? In this paper, we are interested in few-shot object segmentation where the number of annotated training examples are limited to 5 only. To evaluate and validate the performance of our approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12347","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/1907.12347/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":"1907.12347","created_at":"2026-07-05T02:02:00.747711+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.12347v2","created_at":"2026-07-05T02:02:00.747711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12347","created_at":"2026-07-05T02:02:00.747711+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZMJQ2FHMQTL","created_at":"2026-07-05T02:02:00.747711+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZMJQ2FHMQTLD7K3","created_at":"2026-07-05T02:02:00.747711+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZMJQ2FH","created_at":"2026-07-05T02:02:00.747711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E","json":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E.json","graph_json":"https://pith.science/api/pith-number/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/graph.json","events_json":"https://pith.science/api/pith-number/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/events.json","paper":"https://pith.science/paper/TZMJQ2FH"},"agent_actions":{"view_html":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E","download_json":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E.json","view_paper":"https://pith.science/paper/TZMJQ2FH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.12347&json=true","fetch_graph":"https://pith.science/api/pith-number/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/graph.json","fetch_events":"https://pith.science/api/pith-number/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/action/storage_attestation","attest_author":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/action/author_attestation","sign_citation":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/action/citation_signature","submit_replication":"https://pith.science/pith/TZMJQ2FHMQTLD7K3D24FZ7VZ5E/action/replication_record"}},"created_at":"2026-07-05T02:02:00.747711+00:00","updated_at":"2026-07-05T02:02:00.747711+00:00"}