{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ADF5IR67INCD6WAAFZ6CV3JXRI","short_pith_number":"pith:ADF5IR67","schema_version":"1.0","canonical_sha256":"00cbd447df43443f58002e7c2aed378a19ccb74ae8fe495d0657cfba4d109f41","source":{"kind":"arxiv","id":"1610.09003","version":1},"attestation_state":"computed","paper":{"title":"Cross-Modal Scene Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Hamed Pirsiavash, Lluis Castrejon, Yusuf Aytar","submitted_at":"2016-10-27T20:24:36Z","abstract_excerpt":"People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for cross-modal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic o"},"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":"1610.09003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-10-27T20:24:36Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"afbf9ab86ec21bb212027a0a03529a7a59a5df2f3ff3e8fbf9bc6b29fe7b2116","abstract_canon_sha256":"c709276df4352edc670747e9e0953bfac52381a590db1884dcb71367517d07bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:59.449410Z","signature_b64":"ZSgoDkHzkwZqOJUGmLJi1LiICZ5h1KNxGnlJZhWR2jQ/AVxlUkxp8PLZ7b8XHN6B7EDbWxV5vcmA0RMTbmWMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00cbd447df43443f58002e7c2aed378a19ccb74ae8fe495d0657cfba4d109f41","last_reissued_at":"2026-05-18T01:00:59.448737Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:59.448737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Scene Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Hamed Pirsiavash, Lluis Castrejon, Yusuf Aytar","submitted_at":"2016-10-27T20:24:36Z","abstract_excerpt":"People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for cross-modal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09003","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":""},"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":"1610.09003","created_at":"2026-05-18T01:00:59.448865+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.09003v1","created_at":"2026-05-18T01:00:59.448865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09003","created_at":"2026-05-18T01:00:59.448865+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADF5IR67INCD","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADF5IR67INCD6WAA","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADF5IR67","created_at":"2026-05-18T12:30:07.202191+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/ADF5IR67INCD6WAAFZ6CV3JXRI","json":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI.json","graph_json":"https://pith.science/api/pith-number/ADF5IR67INCD6WAAFZ6CV3JXRI/graph.json","events_json":"https://pith.science/api/pith-number/ADF5IR67INCD6WAAFZ6CV3JXRI/events.json","paper":"https://pith.science/paper/ADF5IR67"},"agent_actions":{"view_html":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI","download_json":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI.json","view_paper":"https://pith.science/paper/ADF5IR67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.09003&json=true","fetch_graph":"https://pith.science/api/pith-number/ADF5IR67INCD6WAAFZ6CV3JXRI/graph.json","fetch_events":"https://pith.science/api/pith-number/ADF5IR67INCD6WAAFZ6CV3JXRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI/action/storage_attestation","attest_author":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI/action/author_attestation","sign_citation":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI/action/citation_signature","submit_replication":"https://pith.science/pith/ADF5IR67INCD6WAAFZ6CV3JXRI/action/replication_record"}},"created_at":"2026-05-18T01:00:59.448865+00:00","updated_at":"2026-05-18T01:00:59.448865+00:00"}