{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VMHA5MYLVFYWN3YOYFBK3D6H6V","short_pith_number":"pith:VMHA5MYL","schema_version":"1.0","canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","source":{"kind":"arxiv","id":"1706.06706","version":1},"attestation_state":"computed","paper":{"title":"Compact Tensor Pooling for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Tommaso Furlanello, Yang Shi","submitted_at":"2017-06-20T23:55:32Z","abstract_excerpt":"Performing high level cognitive tasks requires the integration of feature maps with drastically different structure. In Visual Question Answering (VQA) image descriptors have spatial structures, while lexical inputs inherently follow a temporal sequence. The recently proposed Multimodal Compact Bilinear pooling (MCB) forms the outer products, via count-sketch approximation, of the visual and textual representation at each spatial location. While this procedure preserves spatial information locally, outer-products are taken independently for each fiber of the activation tensor, and therefore do"},"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":"1706.06706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-20T23:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"63904913197c2b9f2985da43f46863376665c3fb24fcf60f21fad1b84183c453","abstract_canon_sha256":"9a6d38a839287c21f6c4d1ff330bf98e668df07c846d3674295b7d1bf68a09ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:57.068565Z","signature_b64":"WKj5HGtztrrMl8B5+QuyH9MR1RT4XujLz/NJgzBtf9LjnGnFXMcSBefNxP6mZiQx3nCpHwjiQHSnvlr6QZ2PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab0e0eb30ba97166ef0ec142ad8fc7f557ba858ee2698f94d25314c6d5deddbe","last_reissued_at":"2026-05-18T00:41:57.067862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:57.067862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compact Tensor Pooling for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Tommaso Furlanello, Yang Shi","submitted_at":"2017-06-20T23:55:32Z","abstract_excerpt":"Performing high level cognitive tasks requires the integration of feature maps with drastically different structure. In Visual Question Answering (VQA) image descriptors have spatial structures, while lexical inputs inherently follow a temporal sequence. The recently proposed Multimodal Compact Bilinear pooling (MCB) forms the outer products, via count-sketch approximation, of the visual and textual representation at each spatial location. While this procedure preserves spatial information locally, outer-products are taken independently for each fiber of the activation tensor, and therefore do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06706","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":"1706.06706","created_at":"2026-05-18T00:41:57.067967+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.06706v1","created_at":"2026-05-18T00:41:57.067967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06706","created_at":"2026-05-18T00:41:57.067967+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMHA5MYLVFYW","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMHA5MYLVFYWN3YO","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMHA5MYL","created_at":"2026-05-18T12:31:49.984773+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/VMHA5MYLVFYWN3YOYFBK3D6H6V","json":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V.json","graph_json":"https://pith.science/api/pith-number/VMHA5MYLVFYWN3YOYFBK3D6H6V/graph.json","events_json":"https://pith.science/api/pith-number/VMHA5MYLVFYWN3YOYFBK3D6H6V/events.json","paper":"https://pith.science/paper/VMHA5MYL"},"agent_actions":{"view_html":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V","download_json":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V.json","view_paper":"https://pith.science/paper/VMHA5MYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.06706&json=true","fetch_graph":"https://pith.science/api/pith-number/VMHA5MYLVFYWN3YOYFBK3D6H6V/graph.json","fetch_events":"https://pith.science/api/pith-number/VMHA5MYLVFYWN3YOYFBK3D6H6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/action/storage_attestation","attest_author":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/action/author_attestation","sign_citation":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/action/citation_signature","submit_replication":"https://pith.science/pith/VMHA5MYLVFYWN3YOYFBK3D6H6V/action/replication_record"}},"created_at":"2026-05-18T00:41:57.067967+00:00","updated_at":"2026-05-18T00:41:57.067967+00:00"}