{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:WHAZW7SKXZIGIQVIQIWAOBJPM5","short_pith_number":"pith:WHAZW7SK","schema_version":"1.0","canonical_sha256":"b1c19b7e4abe506442a8822c07052f674724cf064f00d5fa832b58ee8f636e1a","source":{"kind":"arxiv","id":"1301.3323","version":4},"attestation_state":"computed","paper":{"title":"Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kazuyuki Aihara, Sainbayar Sukhbaatar, Takaki Makino","submitted_at":"2013-01-15T12:47:39Z","abstract_excerpt":"Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we propose a novel pooling method that can learn soft clustering of features from image sequences. It is trained to improve the temporal coherence of features, while keeping the information loss at minimum. Our method does not use spatial information, so it can be used with non-convolutional models too. Experiments on images extracted from natural videos showe"},"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":"1301.3323","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-15T12:47:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37d1840e36310683fbc4c8a4275a795138caece163b577d73f14ddfd703004b4","abstract_canon_sha256":"6642af68b1d072c7b4169c4fb8869bdac6ecd382fd8acd5debb616727e1b4fb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:41.064899Z","signature_b64":"/ZFWs5Qf+FXEHCupzSV/VucUIbTuMxzlgUfqzT4z4ni8Elv/ZpQZIkfd/dZsgegdBmFg3sbJytzf1thUENPIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1c19b7e4abe506442a8822c07052f674724cf064f00d5fa832b58ee8f636e1a","last_reissued_at":"2026-05-18T03:30:41.064111Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:41.064111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kazuyuki Aihara, Sainbayar Sukhbaatar, Takaki Makino","submitted_at":"2013-01-15T12:47:39Z","abstract_excerpt":"Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we propose a novel pooling method that can learn soft clustering of features from image sequences. It is trained to improve the temporal coherence of features, while keeping the information loss at minimum. Our method does not use spatial information, so it can be used with non-convolutional models too. Experiments on images extracted from natural videos showe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3323","kind":"arxiv","version":4},"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":"1301.3323","created_at":"2026-05-18T03:30:41.064235+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.3323v4","created_at":"2026-05-18T03:30:41.064235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3323","created_at":"2026-05-18T03:30:41.064235+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHAZW7SKXZIG","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHAZW7SKXZIGIQVI","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHAZW7SK","created_at":"2026-05-18T12:28:04.890932+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/WHAZW7SKXZIGIQVIQIWAOBJPM5","json":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5.json","graph_json":"https://pith.science/api/pith-number/WHAZW7SKXZIGIQVIQIWAOBJPM5/graph.json","events_json":"https://pith.science/api/pith-number/WHAZW7SKXZIGIQVIQIWAOBJPM5/events.json","paper":"https://pith.science/paper/WHAZW7SK"},"agent_actions":{"view_html":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5","download_json":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5.json","view_paper":"https://pith.science/paper/WHAZW7SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.3323&json=true","fetch_graph":"https://pith.science/api/pith-number/WHAZW7SKXZIGIQVIQIWAOBJPM5/graph.json","fetch_events":"https://pith.science/api/pith-number/WHAZW7SKXZIGIQVIQIWAOBJPM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5/action/storage_attestation","attest_author":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5/action/author_attestation","sign_citation":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5/action/citation_signature","submit_replication":"https://pith.science/pith/WHAZW7SKXZIGIQVIQIWAOBJPM5/action/replication_record"}},"created_at":"2026-05-18T03:30:41.064235+00:00","updated_at":"2026-05-18T03:30:41.064235+00:00"}