{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EMB2CYX7DCRMN2LHZU4ZJPNYVP","short_pith_number":"pith:EMB2CYX7","schema_version":"1.0","canonical_sha256":"2303a162ff18a2c6e967cd3994bdb8abc48601e90a0566e1944d054b28e7c95e","source":{"kind":"arxiv","id":"2312.08010","version":2},"attestation_state":"computed","paper":{"title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Shahzad Ahmad, Sukalpa Chanda, Yogesh S Rawat","submitted_at":"2023-12-13T09:33:08Z","abstract_excerpt":"Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks. Building on this success, efforts have been made to adapt these image-based visual-language models, such as CLIP, for videos extending their zero-shot capabilities to the video domain. While these adaptations have shown promising results, they come at a significant computational cost and struggle with effectively modeling the crucial temporal aspects inherent to the video domain. In this study, we present EZ-CLIP, a si"},"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":"2312.08010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T09:33:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3dc19c0ddf936514f0e3fee66905d868dbdf007c5fd0f58b8ae882f23b622f44","abstract_canon_sha256":"34626fa3d6a40514c1e4e03183867e314fb73f54bce7aa806a596e8ad29c2430"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:23.568118Z","signature_b64":"r6134bPwppKbC+YpA+xxYb64j+wzqMyVRingRVcqM9RVK+tHVNQJc1yYYpe+B0rCentby3L6VIVWgf6STq+yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2303a162ff18a2c6e967cd3994bdb8abc48601e90a0566e1944d054b28e7c95e","last_reissued_at":"2026-07-05T07:35:23.567647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:23.567647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Shahzad Ahmad, Sukalpa Chanda, Yogesh S Rawat","submitted_at":"2023-12-13T09:33:08Z","abstract_excerpt":"Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks. Building on this success, efforts have been made to adapt these image-based visual-language models, such as CLIP, for videos extending their zero-shot capabilities to the video domain. While these adaptations have shown promising results, they come at a significant computational cost and struggle with effectively modeling the crucial temporal aspects inherent to the video domain. In this study, we present EZ-CLIP, a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08010","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/2312.08010/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":"2312.08010","created_at":"2026-07-05T07:35:23.567706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08010v2","created_at":"2026-07-05T07:35:23.567706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08010","created_at":"2026-07-05T07:35:23.567706+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMB2CYX7DCRM","created_at":"2026-07-05T07:35:23.567706+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMB2CYX7DCRMN2LH","created_at":"2026-07-05T07:35:23.567706+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMB2CYX7","created_at":"2026-07-05T07:35:23.567706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22595","citing_title":"EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17062","citing_title":"Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP","json":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP.json","graph_json":"https://pith.science/api/pith-number/EMB2CYX7DCRMN2LHZU4ZJPNYVP/graph.json","events_json":"https://pith.science/api/pith-number/EMB2CYX7DCRMN2LHZU4ZJPNYVP/events.json","paper":"https://pith.science/paper/EMB2CYX7"},"agent_actions":{"view_html":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP","download_json":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP.json","view_paper":"https://pith.science/paper/EMB2CYX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08010&json=true","fetch_graph":"https://pith.science/api/pith-number/EMB2CYX7DCRMN2LHZU4ZJPNYVP/graph.json","fetch_events":"https://pith.science/api/pith-number/EMB2CYX7DCRMN2LHZU4ZJPNYVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP/action/storage_attestation","attest_author":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP/action/author_attestation","sign_citation":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP/action/citation_signature","submit_replication":"https://pith.science/pith/EMB2CYX7DCRMN2LHZU4ZJPNYVP/action/replication_record"}},"created_at":"2026-07-05T07:35:23.567706+00:00","updated_at":"2026-07-05T07:35:23.567706+00:00"}