{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CYDYX5C6FNVIT4PQ6QWXPOXMHG","short_pith_number":"pith:CYDYX5C6","schema_version":"1.0","canonical_sha256":"16078bf45e2b6a89f1f0f42d77baec3998f14e4f38ce3539b9328d50ac4e8341","source":{"kind":"arxiv","id":"2004.00849","version":2},"attestation_state":"computed","paper":{"title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bei Liu, Dongmei Fu, Jianlong Fu, Zhaoyang Zeng, Zhicheng Huang","submitted_at":"2020-04-02T07:39:28Z","abstract_excerpt":"We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image pixels and language semantics directly from image and sentence pairs instead of using region-based image features as the most recent vision and language tasks. Our Pixel-BERT which aligns semantic connection in pixel and text level solves the limitation of task-specific visual representation for vision and language tasks. It also relieves the cost of boundi"},"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":"2004.00849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-02T07:39:28Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"e4260a4d4063220719c375b818c04e0c9b98c1a5c232637dcc206a36d34186b4","abstract_canon_sha256":"22fa01afc2b2fe34a118155314b56fd05bed079f22d987c4700b5d8241057ae6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:46.416934Z","signature_b64":"zdNmIeklJ3WvNDklPycxcwSbrx69hjzv+Vxtmow/NLcbDWthpIA05SO97wLbtLffmsWS/BOoYqWLtVbJjnyfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16078bf45e2b6a89f1f0f42d77baec3998f14e4f38ce3539b9328d50ac4e8341","last_reissued_at":"2026-07-05T01:11:46.416533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:46.416533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bei Liu, Dongmei Fu, Jianlong Fu, Zhaoyang Zeng, Zhicheng Huang","submitted_at":"2020-04-02T07:39:28Z","abstract_excerpt":"We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image pixels and language semantics directly from image and sentence pairs instead of using region-based image features as the most recent vision and language tasks. Our Pixel-BERT which aligns semantic connection in pixel and text level solves the limitation of task-specific visual representation for vision and language tasks. It also relieves the cost of boundi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00849","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/2004.00849/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":"2004.00849","created_at":"2026-07-05T01:11:46.416592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.00849v2","created_at":"2026-07-05T01:11:46.416592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00849","created_at":"2026-07-05T01:11:46.416592+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYDYX5C6FNVI","created_at":"2026-07-05T01:11:46.416592+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYDYX5C6FNVIT4PQ","created_at":"2026-07-05T01:11:46.416592+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYDYX5C6","created_at":"2026-07-05T01:11:46.416592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00428","citing_title":"HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":287,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2501.04001","citing_title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG","json":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG.json","graph_json":"https://pith.science/api/pith-number/CYDYX5C6FNVIT4PQ6QWXPOXMHG/graph.json","events_json":"https://pith.science/api/pith-number/CYDYX5C6FNVIT4PQ6QWXPOXMHG/events.json","paper":"https://pith.science/paper/CYDYX5C6"},"agent_actions":{"view_html":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG","download_json":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG.json","view_paper":"https://pith.science/paper/CYDYX5C6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.00849&json=true","fetch_graph":"https://pith.science/api/pith-number/CYDYX5C6FNVIT4PQ6QWXPOXMHG/graph.json","fetch_events":"https://pith.science/api/pith-number/CYDYX5C6FNVIT4PQ6QWXPOXMHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG/action/storage_attestation","attest_author":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG/action/author_attestation","sign_citation":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG/action/citation_signature","submit_replication":"https://pith.science/pith/CYDYX5C6FNVIT4PQ6QWXPOXMHG/action/replication_record"}},"created_at":"2026-07-05T01:11:46.416592+00:00","updated_at":"2026-07-05T01:11:46.416592+00:00"}