{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DDIUHV2X5P7HGDUISAKUYUNEZF","short_pith_number":"pith:DDIUHV2X","schema_version":"1.0","canonical_sha256":"18d143d757ebfe730e8890154c51a4c95368023db7f3138f887944cbe7296db4","source":{"kind":"arxiv","id":"2411.13836","version":1},"attestation_state":"computed","paper":{"title":"CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiale Cao, Jin Xie, Lin Sun, Xiaoheng Jiang, Yanwei Pang","submitted_at":"2024-11-21T04:54:30Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional training. The key is to improve spatial representation of image-level CLIP, such as replacing self-attention map at last layer with self-self attention map or vision foundation model based attention map. In this paper, we present a novel hierarchical framework, named CLIPer, that hierarchically improves spatial representation of CLIP. The proposed CLIPer includ"},"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":"2411.13836","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T04:54:30Z","cross_cats_sorted":[],"title_canon_sha256":"77a7b3f867a0c20bc7f1323e9e8067b99619b46591f3b777d648dc50a196077b","abstract_canon_sha256":"d953b961c9469d0b277afa3ba2659708055e87266f3528019a3a404fddff00c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:37.794802Z","signature_b64":"b5HGz3CbHPRlkAAvhQbkVUqfPJFzVRVauZD/AyuEYApP2c3MMhxSS7eedjZ3W7HSQxmakN3tPQD0Yobe8Cx3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18d143d757ebfe730e8890154c51a4c95368023db7f3138f887944cbe7296db4","last_reissued_at":"2026-07-05T09:38:37.794393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:37.794393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiale Cao, Jin Xie, Lin Sun, Xiaoheng Jiang, Yanwei Pang","submitted_at":"2024-11-21T04:54:30Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional training. The key is to improve spatial representation of image-level CLIP, such as replacing self-attention map at last layer with self-self attention map or vision foundation model based attention map. In this paper, we present a novel hierarchical framework, named CLIPer, that hierarchically improves spatial representation of CLIP. The proposed CLIPer includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13836","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/2411.13836/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":"2411.13836","created_at":"2026-07-05T09:38:37.794454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13836v1","created_at":"2026-07-05T09:38:37.794454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13836","created_at":"2026-07-05T09:38:37.794454+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDIUHV2X5P7H","created_at":"2026-07-05T09:38:37.794454+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDIUHV2X5P7HGDUI","created_at":"2026-07-05T09:38:37.794454+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDIUHV2X","created_at":"2026-07-05T09:38:37.794454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.13181","citing_title":"Perception Encoder: The best visual embeddings are not at the output of the network","ref_index":128,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF","json":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF.json","graph_json":"https://pith.science/api/pith-number/DDIUHV2X5P7HGDUISAKUYUNEZF/graph.json","events_json":"https://pith.science/api/pith-number/DDIUHV2X5P7HGDUISAKUYUNEZF/events.json","paper":"https://pith.science/paper/DDIUHV2X"},"agent_actions":{"view_html":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF","download_json":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF.json","view_paper":"https://pith.science/paper/DDIUHV2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13836&json=true","fetch_graph":"https://pith.science/api/pith-number/DDIUHV2X5P7HGDUISAKUYUNEZF/graph.json","fetch_events":"https://pith.science/api/pith-number/DDIUHV2X5P7HGDUISAKUYUNEZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF/action/storage_attestation","attest_author":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF/action/author_attestation","sign_citation":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF/action/citation_signature","submit_replication":"https://pith.science/pith/DDIUHV2X5P7HGDUISAKUYUNEZF/action/replication_record"}},"created_at":"2026-07-05T09:38:37.794454+00:00","updated_at":"2026-07-05T09:38:37.794454+00:00"}