{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GH4KSMZVDCANXBI3QLK3BMBUX2","short_pith_number":"pith:GH4KSMZV","schema_version":"1.0","canonical_sha256":"31f8a933351880db851b82d5b0b034beb6b665aaec8ee6da799028953fcf053d","source":{"kind":"arxiv","id":"2012.05473","version":2},"attestation_state":"computed","paper":{"title":"Tensor Composition Net for Visual Relationship Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Timothy M. Hospedales, Xueting Zhang, Yanwen Guo, Yongxin Yang, Yuting Qiang","submitted_at":"2020-12-10T06:27:20Z","abstract_excerpt":"We present a novel Tensor Composition Net (TCN) to predict visual relationships in images. Visual Relationship Prediction (VRP) provides a more challenging test of image understanding than conventional image tagging and is difficult to learn due to a large label-space and incomplete annotation. The key idea of our TCN is to exploit the low-rank property of the visual relationship tensor, so as to leverage correlations within and across objects and relations and make a structured prediction of all visual relationships in an image. To show the effectiveness of our model, we first empirically com"},"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":"2012.05473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-10T06:27:20Z","cross_cats_sorted":[],"title_canon_sha256":"ce6d782fd0cc991f0f8bc5aaff2ff4ea3a9656d4f9233871547579ea81448a5c","abstract_canon_sha256":"6e4b5022b05bc069c135e8509a47dd9a6a972a1513193e5fb06e11ecfc61b4ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:25.303731Z","signature_b64":"3/WRJJXNnZ8bUxOhYK1BbgwL24bZM81gvKE9IltfmUSpI9aBepyVd5IxBbrvZt9EHZdCS7w4N15LNjyvc+A4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f8a933351880db851b82d5b0b034beb6b665aaec8ee6da799028953fcf053d","last_reissued_at":"2026-07-05T03:55:25.303262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:25.303262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensor Composition Net for Visual Relationship Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Timothy M. Hospedales, Xueting Zhang, Yanwen Guo, Yongxin Yang, Yuting Qiang","submitted_at":"2020-12-10T06:27:20Z","abstract_excerpt":"We present a novel Tensor Composition Net (TCN) to predict visual relationships in images. Visual Relationship Prediction (VRP) provides a more challenging test of image understanding than conventional image tagging and is difficult to learn due to a large label-space and incomplete annotation. The key idea of our TCN is to exploit the low-rank property of the visual relationship tensor, so as to leverage correlations within and across objects and relations and make a structured prediction of all visual relationships in an image. To show the effectiveness of our model, we first empirically com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05473","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/2012.05473/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":"2012.05473","created_at":"2026-07-05T03:55:25.303335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05473v2","created_at":"2026-07-05T03:55:25.303335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05473","created_at":"2026-07-05T03:55:25.303335+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH4KSMZVDCAN","created_at":"2026-07-05T03:55:25.303335+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH4KSMZVDCANXBI3","created_at":"2026-07-05T03:55:25.303335+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH4KSMZV","created_at":"2026-07-05T03:55:25.303335+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/GH4KSMZVDCANXBI3QLK3BMBUX2","json":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2.json","graph_json":"https://pith.science/api/pith-number/GH4KSMZVDCANXBI3QLK3BMBUX2/graph.json","events_json":"https://pith.science/api/pith-number/GH4KSMZVDCANXBI3QLK3BMBUX2/events.json","paper":"https://pith.science/paper/GH4KSMZV"},"agent_actions":{"view_html":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2","download_json":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2.json","view_paper":"https://pith.science/paper/GH4KSMZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05473&json=true","fetch_graph":"https://pith.science/api/pith-number/GH4KSMZVDCANXBI3QLK3BMBUX2/graph.json","fetch_events":"https://pith.science/api/pith-number/GH4KSMZVDCANXBI3QLK3BMBUX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2/action/storage_attestation","attest_author":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2/action/author_attestation","sign_citation":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2/action/citation_signature","submit_replication":"https://pith.science/pith/GH4KSMZVDCANXBI3QLK3BMBUX2/action/replication_record"}},"created_at":"2026-07-05T03:55:25.303335+00:00","updated_at":"2026-07-05T03:55:25.303335+00:00"}