{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CZWDOW2CI5V7KOUYRWC22SXD7","short_pith_number":"pith:5CZWDOW2","schema_version":"1.0","canonical_sha256":"e8b361bada123b5fa9d4c46c2d6a571fca19e8e50c8db74b1a7550154e4a8777","source":{"kind":"arxiv","id":"2408.17422","version":5},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Action Localization with Iterative Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Atsushi Kanehira, Jun Takamatsu, Katsushi Ikeuchi, Kazuhiro Sasabuchi, Naoki Wake","submitted_at":"2024-08-30T17:12:14Z","abstract_excerpt":"Video action localization aims to find the timings of specific actions from a long video. Although existing learning-based approaches have been successful, they require annotating videos, which comes with a considerable labor cost. This paper proposes a training-free, open-vocabulary approach based on emerging off-the-shelf vision-language models (VLMs). The challenge stems from the fact that VLMs are neither designed to process long videos nor tailored for finding actions. We overcome these problems by extending an iterative visual prompting technique. Specifically, we sample video frames and"},"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":"2408.17422","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-30T17:12:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"11dda639c0e6d785151ae512af495e487a6ee6eef50c02f5433d1f735d900a14","abstract_canon_sha256":"739a0957f587c79c6f909ef4578e71276e3b2b518d90abaaff9c8dba38db8a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:11.183430Z","signature_b64":"i4dn/HT5ZNVmlncyMksef3jc6bo8BOJcsSmYQxdHb++9WucBXBnUz7SkvYkRfE5IaZBLSb+yBE7TFAndPs0wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8b361bada123b5fa9d4c46c2d6a571fca19e8e50c8db74b1a7550154e4a8777","last_reissued_at":"2026-07-05T10:45:11.182902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:11.182902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Action Localization with Iterative Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Atsushi Kanehira, Jun Takamatsu, Katsushi Ikeuchi, Kazuhiro Sasabuchi, Naoki Wake","submitted_at":"2024-08-30T17:12:14Z","abstract_excerpt":"Video action localization aims to find the timings of specific actions from a long video. Although existing learning-based approaches have been successful, they require annotating videos, which comes with a considerable labor cost. This paper proposes a training-free, open-vocabulary approach based on emerging off-the-shelf vision-language models (VLMs). The challenge stems from the fact that VLMs are neither designed to process long videos nor tailored for finding actions. We overcome these problems by extending an iterative visual prompting technique. Specifically, we sample video frames and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.17422","kind":"arxiv","version":5},"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/2408.17422/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":"2408.17422","created_at":"2026-07-05T10:45:11.182962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.17422v5","created_at":"2026-07-05T10:45:11.182962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.17422","created_at":"2026-07-05T10:45:11.182962+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CZWDOW2CI5V","created_at":"2026-07-05T10:45:11.182962+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CZWDOW2CI5V7KOU","created_at":"2026-07-05T10:45:11.182962+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CZWDOW2","created_at":"2026-07-05T10:45:11.182962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24371","citing_title":"Grid-LOGAT: Grid Based Local and Global Area Transcription for Video Question Answering","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7","json":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7.json","graph_json":"https://pith.science/api/pith-number/5CZWDOW2CI5V7KOUYRWC22SXD7/graph.json","events_json":"https://pith.science/api/pith-number/5CZWDOW2CI5V7KOUYRWC22SXD7/events.json","paper":"https://pith.science/paper/5CZWDOW2"},"agent_actions":{"view_html":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7","download_json":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7.json","view_paper":"https://pith.science/paper/5CZWDOW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.17422&json=true","fetch_graph":"https://pith.science/api/pith-number/5CZWDOW2CI5V7KOUYRWC22SXD7/graph.json","fetch_events":"https://pith.science/api/pith-number/5CZWDOW2CI5V7KOUYRWC22SXD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7/action/storage_attestation","attest_author":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7/action/author_attestation","sign_citation":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7/action/citation_signature","submit_replication":"https://pith.science/pith/5CZWDOW2CI5V7KOUYRWC22SXD7/action/replication_record"}},"created_at":"2026-07-05T10:45:11.182962+00:00","updated_at":"2026-07-05T10:45:11.182962+00:00"}