{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BZDSJGKYIXKWJTUTUFGMOIFBWR","short_pith_number":"pith:BZDSJGKY","schema_version":"1.0","canonical_sha256":"0e4724995845d564ce93a14cc720a1b462bb4535318e38dfce724e7430b1acd7","source":{"kind":"arxiv","id":"2403.17823","version":2},"attestation_state":"computed","paper":{"title":"Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Eyma\\\"el, Anthony Cioppa, Bernard Ghanem, Marc Van Droogenbroeck, Renaud Vandeghen, Silvio Giancola","submitted_at":"2024-03-26T16:04:19Z","abstract_excerpt":"Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sour"},"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":"2403.17823","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T16:04:19Z","cross_cats_sorted":[],"title_canon_sha256":"a129165bfbca02bf7639ed847c026180d02188ccc97a5dc161de39f752cf5305","abstract_canon_sha256":"9e83900794375c78f1d4f85c838aea9f630c5fae1b046945012b75df5907e3ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:16.051650Z","signature_b64":"LrAUJNLIQC6b4GFSdKBwLjAQe1exleWXA5MK+j303dqTk7nEEcTVZDCTzCzz8uMU8U7M9/4fB7CYT/bUJQH4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e4724995845d564ce93a14cc720a1b462bb4535318e38dfce724e7430b1acd7","last_reissued_at":"2026-07-05T10:15:16.051131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:16.051131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Eyma\\\"el, Anthony Cioppa, Bernard Ghanem, Marc Van Droogenbroeck, Renaud Vandeghen, Silvio Giancola","submitted_at":"2024-03-26T16:04:19Z","abstract_excerpt":"Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sour"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17823","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/2403.17823/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":"2403.17823","created_at":"2026-07-05T10:15:16.051190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17823v2","created_at":"2026-07-05T10:15:16.051190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17823","created_at":"2026-07-05T10:15:16.051190+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZDSJGKYIXKW","created_at":"2026-07-05T10:15:16.051190+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZDSJGKYIXKWJTUT","created_at":"2026-07-05T10:15:16.051190+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZDSJGKY","created_at":"2026-07-05T10:15:16.051190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09068","citing_title":"Infinite Video Understanding","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR","json":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR.json","graph_json":"https://pith.science/api/pith-number/BZDSJGKYIXKWJTUTUFGMOIFBWR/graph.json","events_json":"https://pith.science/api/pith-number/BZDSJGKYIXKWJTUTUFGMOIFBWR/events.json","paper":"https://pith.science/paper/BZDSJGKY"},"agent_actions":{"view_html":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR","download_json":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR.json","view_paper":"https://pith.science/paper/BZDSJGKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17823&json=true","fetch_graph":"https://pith.science/api/pith-number/BZDSJGKYIXKWJTUTUFGMOIFBWR/graph.json","fetch_events":"https://pith.science/api/pith-number/BZDSJGKYIXKWJTUTUFGMOIFBWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR/action/storage_attestation","attest_author":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR/action/author_attestation","sign_citation":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR/action/citation_signature","submit_replication":"https://pith.science/pith/BZDSJGKYIXKWJTUTUFGMOIFBWR/action/replication_record"}},"created_at":"2026-07-05T10:15:16.051190+00:00","updated_at":"2026-07-05T10:15:16.051190+00:00"}