{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EMNBOTA4B4IGDAHWVFXV2D4VUH","short_pith_number":"pith:EMNBOTA4","schema_version":"1.0","canonical_sha256":"231a174c1c0f106180f6a96f5d0f95a1ebf3fb37885a03106f1ac9bd20f1be4e","source":{"kind":"arxiv","id":"1612.04949","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fumin Shen, Hao Liu, Heng Tao Shen, Lixin Duan, Yang Yang","submitted_at":"2016-12-15T07:19:46Z","abstract_excerpt":"Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a.k.a., image description, has been remarkably advanced in recent years. Nonetheless, most existing paradigms may suffer from the deficiency of invariance to images with different scaling, rotation, etc.; and effective integration of standalone attention to form a holistic end-to-end system. In this paper, we propose a novel image captioning architecture, termed Recurrent Image Captioner (\\textbf{RIC}), which al"},"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":"1612.04949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-15T07:19:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"28056c75ecdd9cac199d1b2313e823a6547ba0d7ab70fe8dde6eb4c8f0d667e4","abstract_canon_sha256":"3a4a2ef696ddfcf159f044ad34e7f3654bebd3967ada922e70ab9ad66a601cb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:53.829039Z","signature_b64":"+xE5J2WvaO7P+OnhIoijlo9wPxXrBWDf/FZWKsZvIr6JWY+E6vCYsqneBAYflbcXKclO54rcc07eHdLWkpfBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"231a174c1c0f106180f6a96f5d0f95a1ebf3fb37885a03106f1ac9bd20f1be4e","last_reissued_at":"2026-05-18T00:54:53.828198Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:53.828198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fumin Shen, Hao Liu, Heng Tao Shen, Lixin Duan, Yang Yang","submitted_at":"2016-12-15T07:19:46Z","abstract_excerpt":"Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a.k.a., image description, has been remarkably advanced in recent years. Nonetheless, most existing paradigms may suffer from the deficiency of invariance to images with different scaling, rotation, etc.; and effective integration of standalone attention to form a holistic end-to-end system. In this paper, we propose a novel image captioning architecture, termed Recurrent Image Captioner (\\textbf{RIC}), which al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04949","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":"1612.04949","created_at":"2026-05-18T00:54:53.828324+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.04949v1","created_at":"2026-05-18T00:54:53.828324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04949","created_at":"2026-05-18T00:54:53.828324+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMNBOTA4B4IG","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMNBOTA4B4IGDAHW","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMNBOTA4","created_at":"2026-05-18T12:30:12.583610+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/EMNBOTA4B4IGDAHWVFXV2D4VUH","json":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH.json","graph_json":"https://pith.science/api/pith-number/EMNBOTA4B4IGDAHWVFXV2D4VUH/graph.json","events_json":"https://pith.science/api/pith-number/EMNBOTA4B4IGDAHWVFXV2D4VUH/events.json","paper":"https://pith.science/paper/EMNBOTA4"},"agent_actions":{"view_html":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH","download_json":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH.json","view_paper":"https://pith.science/paper/EMNBOTA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.04949&json=true","fetch_graph":"https://pith.science/api/pith-number/EMNBOTA4B4IGDAHWVFXV2D4VUH/graph.json","fetch_events":"https://pith.science/api/pith-number/EMNBOTA4B4IGDAHWVFXV2D4VUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH/action/storage_attestation","attest_author":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH/action/author_attestation","sign_citation":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH/action/citation_signature","submit_replication":"https://pith.science/pith/EMNBOTA4B4IGDAHWVFXV2D4VUH/action/replication_record"}},"created_at":"2026-05-18T00:54:53.828324+00:00","updated_at":"2026-05-18T00:54:53.828324+00:00"}