{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ZJKQG332LTF3ID5YX7TS2WFB4","short_pith_number":"pith:5ZJKQG33","schema_version":"1.0","canonical_sha256":"ee52a81b7bd2e65da07dc5ff396ac50f1b06a053ca076f369516ec68049be50a","source":{"kind":"arxiv","id":"2412.10702","version":2},"attestation_state":"computed","paper":{"title":"Memory Efficient Matting with Adaptive Token Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyi Zhang, Luoqi Liu, Ting Liu, Xiaochao Qu, Yao Zhao, Yihan Hu, Yiheng Lin, Yunchao Wei","submitted_at":"2024-12-14T06:21:24Z","abstract_excerpt":"Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadratic complexity of global self-attention. To address this issue, we propose MEMatte, a \\textbf{m}emory-\\textbf{e}fficient \\textbf{m}atting framework for processing high-resolution images. MEMatte incorporates a router before each global attention block, directing informative tokens to the global attention while routing other tokens to a Lightweight Token Refinement Module (LTRM). Specifically, the router employs a loc"},"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":"2412.10702","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T06:21:24Z","cross_cats_sorted":[],"title_canon_sha256":"ee59dab357811ca4f2c6447392a8455c1b2e5787385e0c04ef43e407ae1c4a90","abstract_canon_sha256":"e76573113941e212eae4d1f540ab5437de90589a6acbfe7f5acca86be1b8e16c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:37.185361Z","signature_b64":"Xi0DqcVjs2utdIeyaQY5txy/3XDrrhSeKZsGUA6nbbWy3JF81MgR2toF+VgIV28pUctwuMy/xVAYltOh1PSYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee52a81b7bd2e65da07dc5ff396ac50f1b06a053ca076f369516ec68049be50a","last_reissued_at":"2026-07-05T09:50:37.184854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:37.184854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Efficient Matting with Adaptive Token Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyi Zhang, Luoqi Liu, Ting Liu, Xiaochao Qu, Yao Zhao, Yihan Hu, Yiheng Lin, Yunchao Wei","submitted_at":"2024-12-14T06:21:24Z","abstract_excerpt":"Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadratic complexity of global self-attention. To address this issue, we propose MEMatte, a \\textbf{m}emory-\\textbf{e}fficient \\textbf{m}atting framework for processing high-resolution images. MEMatte incorporates a router before each global attention block, directing informative tokens to the global attention while routing other tokens to a Lightweight Token Refinement Module (LTRM). Specifically, the router employs a loc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10702","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/2412.10702/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":"2412.10702","created_at":"2026-07-05T09:50:37.184915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10702v2","created_at":"2026-07-05T09:50:37.184915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10702","created_at":"2026-07-05T09:50:37.184915+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZJKQG332LTF","created_at":"2026-07-05T09:50:37.184915+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZJKQG332LTF3ID5","created_at":"2026-07-05T09:50:37.184915+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZJKQG33","created_at":"2026-07-05T09:50:37.184915+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/5ZJKQG332LTF3ID5YX7TS2WFB4","json":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4.json","graph_json":"https://pith.science/api/pith-number/5ZJKQG332LTF3ID5YX7TS2WFB4/graph.json","events_json":"https://pith.science/api/pith-number/5ZJKQG332LTF3ID5YX7TS2WFB4/events.json","paper":"https://pith.science/paper/5ZJKQG33"},"agent_actions":{"view_html":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4","download_json":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4.json","view_paper":"https://pith.science/paper/5ZJKQG33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10702&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZJKQG332LTF3ID5YX7TS2WFB4/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZJKQG332LTF3ID5YX7TS2WFB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4/action/storage_attestation","attest_author":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4/action/author_attestation","sign_citation":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4/action/citation_signature","submit_replication":"https://pith.science/pith/5ZJKQG332LTF3ID5YX7TS2WFB4/action/replication_record"}},"created_at":"2026-07-05T09:50:37.184915+00:00","updated_at":"2026-07-05T09:50:37.184915+00:00"}