{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CAMJJIFQHUADKFUCICTM4LSES","short_pith_number":"pith:5CAMJJIF","schema_version":"1.0","canonical_sha256":"e880c4a50581e801a8b41205367172249084206f50c0c8de22f93853baad0aca","source":{"kind":"arxiv","id":"2306.06354","version":3},"attestation_state":"computed","paper":{"title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Igor Gilitschenski, Xudong Liu, Ziyi Wu","submitted_at":"2023-06-10T06:05:35Z","abstract_excerpt":"Recent advances in zero-shot and few-shot classification heavily rely on the success of pre-trained vision-language models (VLMs) such as CLIP. Due to a shortage of large-scale datasets, training such models for event camera data remains infeasible. Thus, adapting existing VLMs across modalities to event vision is an important research challenge. In this work, we introduce EventCLIP, a novel approach that utilizes CLIP for zero-shot and few-shot event-based object recognition. We first generalize CLIP's image encoder to event data by converting raw events to 2D grid-based representations. To f"},"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":"2306.06354","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-10T06:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"8c9ef6963d06f10f3141789bf90c158d9aeeb54a332c9f93fb59cac82813d079","abstract_canon_sha256":"350e0a50ea7c9d9678e65e822644f73ccebc5709df7bd0d776f485bde9fab6d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:42.556962Z","signature_b64":"UXgl8YkLGXT6mHqeB2AlUysmz1da6mtqndwEmVWC37L0JhnLyIOKyksHlD2O2STPyIap22nBa79tppzv2odfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e880c4a50581e801a8b41205367172249084206f50c0c8de22f93853baad0aca","last_reissued_at":"2026-07-05T07:13:42.556522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:42.556522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Igor Gilitschenski, Xudong Liu, Ziyi Wu","submitted_at":"2023-06-10T06:05:35Z","abstract_excerpt":"Recent advances in zero-shot and few-shot classification heavily rely on the success of pre-trained vision-language models (VLMs) such as CLIP. Due to a shortage of large-scale datasets, training such models for event camera data remains infeasible. Thus, adapting existing VLMs across modalities to event vision is an important research challenge. In this work, we introduce EventCLIP, a novel approach that utilizes CLIP for zero-shot and few-shot event-based object recognition. We first generalize CLIP's image encoder to event data by converting raw events to 2D grid-based representations. To f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06354","kind":"arxiv","version":3},"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/2306.06354/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":"2306.06354","created_at":"2026-07-05T07:13:42.556580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06354v3","created_at":"2026-07-05T07:13:42.556580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06354","created_at":"2026-07-05T07:13:42.556580+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CAMJJIFQHUA","created_at":"2026-07-05T07:13:42.556580+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CAMJJIFQHUADKFU","created_at":"2026-07-05T07:13:42.556580+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CAMJJIF","created_at":"2026-07-05T07:13:42.556580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07001","citing_title":"Ego-Human Motion Prediction with 3D-Aware LLM","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18242","citing_title":"EventDrive: Event Cameras for Vision-Language Driving Intelligence","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19329","citing_title":"RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19506","citing_title":"EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19329","citing_title":"RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23032","citing_title":"Generative Event Pretraining with Foundation Model Alignment","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06782","citing_title":"EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES","json":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES.json","graph_json":"https://pith.science/api/pith-number/5CAMJJIFQHUADKFUCICTM4LSES/graph.json","events_json":"https://pith.science/api/pith-number/5CAMJJIFQHUADKFUCICTM4LSES/events.json","paper":"https://pith.science/paper/5CAMJJIF"},"agent_actions":{"view_html":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES","download_json":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES.json","view_paper":"https://pith.science/paper/5CAMJJIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06354&json=true","fetch_graph":"https://pith.science/api/pith-number/5CAMJJIFQHUADKFUCICTM4LSES/graph.json","fetch_events":"https://pith.science/api/pith-number/5CAMJJIFQHUADKFUCICTM4LSES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES/action/storage_attestation","attest_author":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES/action/author_attestation","sign_citation":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES/action/citation_signature","submit_replication":"https://pith.science/pith/5CAMJJIFQHUADKFUCICTM4LSES/action/replication_record"}},"created_at":"2026-07-05T07:13:42.556580+00:00","updated_at":"2026-07-05T07:13:42.556580+00:00"}