{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A75754N76NVMSKMDUKPFMTF4R2","short_pith_number":"pith:A75754N7","schema_version":"1.0","canonical_sha256":"07fbfef1bff36ac92983a29e564cbc8eb8b03d6da1547a52469efad1e80cb46c","source":{"kind":"arxiv","id":"2208.13721","version":3},"attestation_state":"computed","paper":{"title":"CounTR: Transformer-based Generalised Visual Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Chang Liu, Weidi Xie, Yujie Zhong","submitted_at":"2022-08-29T17:02:45Z","abstract_excerpt":"In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of \"exemplars\", i.e. zero-shot or few-shot counting. To this end, we make the following four contributions: (1) We introduce a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given \"exemplars\" with the attention mechanism;(2) We adopt a t"},"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":"2208.13721","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-29T17:02:45Z","cross_cats_sorted":[],"title_canon_sha256":"734a48d5607615f9fbde511c347fe3fb5d2cfca46ef156f151691612d8f5c84b","abstract_canon_sha256":"0dc8d8147ca2420540d7b809e92da700309eb055ed3e3a961483da57ae5fe14c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:47.023419Z","signature_b64":"zTb5CE6qvrom/7h9Lq9JUPa8bkGbSGGwj545cEOq8U4dKp+e6ZIBFwKFGOranr8BVjQxLatlX+R1Zpk5ZaZDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07fbfef1bff36ac92983a29e564cbc8eb8b03d6da1547a52469efad1e80cb46c","last_reissued_at":"2026-07-05T06:16:47.023008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:47.023008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CounTR: Transformer-based Generalised Visual Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Chang Liu, Weidi Xie, Yujie Zhong","submitted_at":"2022-08-29T17:02:45Z","abstract_excerpt":"In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of \"exemplars\", i.e. zero-shot or few-shot counting. To this end, we make the following four contributions: (1) We introduce a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given \"exemplars\" with the attention mechanism;(2) We adopt a t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13721","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/2208.13721/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":"2208.13721","created_at":"2026-07-05T06:16:47.023061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.13721v3","created_at":"2026-07-05T06:16:47.023061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13721","created_at":"2026-07-05T06:16:47.023061+00:00"},{"alias_kind":"pith_short_12","alias_value":"A75754N76NVM","created_at":"2026-07-05T06:16:47.023061+00:00"},{"alias_kind":"pith_short_16","alias_value":"A75754N76NVMSKMD","created_at":"2026-07-05T06:16:47.023061+00:00"},{"alias_kind":"pith_short_8","alias_value":"A75754N7","created_at":"2026-07-05T06:16:47.023061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23835","citing_title":"ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17561","citing_title":"RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18063","citing_title":"The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2","json":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2.json","graph_json":"https://pith.science/api/pith-number/A75754N76NVMSKMDUKPFMTF4R2/graph.json","events_json":"https://pith.science/api/pith-number/A75754N76NVMSKMDUKPFMTF4R2/events.json","paper":"https://pith.science/paper/A75754N7"},"agent_actions":{"view_html":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2","download_json":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2.json","view_paper":"https://pith.science/paper/A75754N7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.13721&json=true","fetch_graph":"https://pith.science/api/pith-number/A75754N76NVMSKMDUKPFMTF4R2/graph.json","fetch_events":"https://pith.science/api/pith-number/A75754N76NVMSKMDUKPFMTF4R2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2/action/storage_attestation","attest_author":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2/action/author_attestation","sign_citation":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2/action/citation_signature","submit_replication":"https://pith.science/pith/A75754N76NVMSKMDUKPFMTF4R2/action/replication_record"}},"created_at":"2026-07-05T06:16:47.023061+00:00","updated_at":"2026-07-05T06:16:47.023061+00:00"}