{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z7C3CXXBSSKN5KMHDVSG2CPN4Y","short_pith_number":"pith:Z7C3CXXB","schema_version":"1.0","canonical_sha256":"cfc5b15ee19494dea9871d646d09ede6233ac76d631b3661e5ab7000e54d7564","source":{"kind":"arxiv","id":"2408.06840","version":2},"attestation_state":"computed","paper":{"title":"Dynamic and Compressive Adaptation of Transformers From Images to Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guozhen Zhang, Jingyu Liu, Kai Ma, Kevin Zhao, Limin Wang, Shengming Cao, Xiaotong Zhao","submitted_at":"2024-08-13T12:01:22Z","abstract_excerpt":"Recently, the remarkable success of pre-trained Vision Transformers (ViTs) from image-text matching has sparked an interest in image-to-video adaptation. However, most current approaches retain the full forward pass for each frame, leading to a high computation overhead for processing entire videos. In this paper, we present InTI, a novel approach for compressive image-to-video adaptation using dynamic Inter-frame Token Interpolation. InTI aims to softly preserve the informative tokens without disrupting their coherent spatiotemporal structure. Specifically, each token pair at identical positi"},"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":"2408.06840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-13T12:01:22Z","cross_cats_sorted":[],"title_canon_sha256":"d92c52ca535dcdd7274cd1821ccb91061e1403c7c66f1ebb37e4721851274be5","abstract_canon_sha256":"e4532e9acc45c5b38bdc1110fd230d4786b98dc6f5413c1a7887bb2fddba461a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:10.342751Z","signature_b64":"u8m/WxuMCkxNW0kcqXsnwFBTIA5hq3UdmiGiH0CgsR9S4aacX8OPOtmZv6KTepLEJm4Jfr2cYLMMcGvvNNi4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc5b15ee19494dea9871d646d09ede6233ac76d631b3661e5ab7000e54d7564","last_reissued_at":"2026-07-05T08:55:10.342296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:10.342296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic and Compressive Adaptation of Transformers From Images to Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guozhen Zhang, Jingyu Liu, Kai Ma, Kevin Zhao, Limin Wang, Shengming Cao, Xiaotong Zhao","submitted_at":"2024-08-13T12:01:22Z","abstract_excerpt":"Recently, the remarkable success of pre-trained Vision Transformers (ViTs) from image-text matching has sparked an interest in image-to-video adaptation. However, most current approaches retain the full forward pass for each frame, leading to a high computation overhead for processing entire videos. In this paper, we present InTI, a novel approach for compressive image-to-video adaptation using dynamic Inter-frame Token Interpolation. InTI aims to softly preserve the informative tokens without disrupting their coherent spatiotemporal structure. Specifically, each token pair at identical positi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06840","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/2408.06840/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":"2408.06840","created_at":"2026-07-05T08:55:10.342361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06840v2","created_at":"2026-07-05T08:55:10.342361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06840","created_at":"2026-07-05T08:55:10.342361+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7C3CXXBSSKN","created_at":"2026-07-05T08:55:10.342361+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7C3CXXBSSKN5KMH","created_at":"2026-07-05T08:55:10.342361+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7C3CXXB","created_at":"2026-07-05T08:55:10.342361+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/Z7C3CXXBSSKN5KMHDVSG2CPN4Y","json":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y.json","graph_json":"https://pith.science/api/pith-number/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/graph.json","events_json":"https://pith.science/api/pith-number/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/events.json","paper":"https://pith.science/paper/Z7C3CXXB"},"agent_actions":{"view_html":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y","download_json":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y.json","view_paper":"https://pith.science/paper/Z7C3CXXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06840&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/action/storage_attestation","attest_author":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/action/author_attestation","sign_citation":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/action/citation_signature","submit_replication":"https://pith.science/pith/Z7C3CXXBSSKN5KMHDVSG2CPN4Y/action/replication_record"}},"created_at":"2026-07-05T08:55:10.342361+00:00","updated_at":"2026-07-05T08:55:10.342361+00:00"}