{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KKZ7LB3P6DJWVMDLEE6PIABJ5F","short_pith_number":"pith:KKZ7LB3P","schema_version":"1.0","canonical_sha256":"52b3f5876ff0d36ab06b213cf40029e966fca5031c9bca23d1316b4796834b73","source":{"kind":"arxiv","id":"2104.13682","version":1},"attestation_state":"computed","paper":{"title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsoo Kim, Eun-Sol Kim, Hyunwoo J. Kim, Jaewoo Kang, Junhyun Lee","submitted_at":"2021-04-28T10:10:29Z","abstract_excerpt":"Human-Object Interaction (HOI) detection is a task of identifying \"a set of interactions\" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods have indirectly addressed this task by detecting human and object instances and individually inferring every pair of the detected instances. In this paper, we present a novel framework, referred to by HOTR, which directly predicts a set of <human, object, interaction> triplets from an image based on a transforme"},"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":"2104.13682","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-28T10:10:29Z","cross_cats_sorted":[],"title_canon_sha256":"cdb48c5717423d4123e955a0dc9abcb39a81861dc1efd8b7d36950be83d37158","abstract_canon_sha256":"4fda9ccce58bade8cf0d099b18dceb19b591c26cc7db76b28fb18ed6c9abb0e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:57.279187Z","signature_b64":"0zpOiUtt18zWq+//ANPVWQpW2FMgvWPmShVubcS6D7Zg/QhxIjTthZ+4gtRYOSIfFT1lFND3fVO4c3l1EMq9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b3f5876ff0d36ab06b213cf40029e966fca5031c9bca23d1316b4796834b73","last_reissued_at":"2026-07-05T02:35:57.278749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:57.278749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsoo Kim, Eun-Sol Kim, Hyunwoo J. Kim, Jaewoo Kang, Junhyun Lee","submitted_at":"2021-04-28T10:10:29Z","abstract_excerpt":"Human-Object Interaction (HOI) detection is a task of identifying \"a set of interactions\" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels. Most existing methods have indirectly addressed this task by detecting human and object instances and individually inferring every pair of the detected instances. In this paper, we present a novel framework, referred to by HOTR, which directly predicts a set of <human, object, interaction> triplets from an image based on a transforme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13682","kind":"arxiv","version":1},"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/2104.13682/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":"2104.13682","created_at":"2026-07-05T02:35:57.278806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13682v1","created_at":"2026-07-05T02:35:57.278806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13682","created_at":"2026-07-05T02:35:57.278806+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKZ7LB3P6DJW","created_at":"2026-07-05T02:35:57.278806+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKZ7LB3P6DJWVMDL","created_at":"2026-07-05T02:35:57.278806+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKZ7LB3P","created_at":"2026-07-05T02:35:57.278806+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/KKZ7LB3P6DJWVMDLEE6PIABJ5F","json":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F.json","graph_json":"https://pith.science/api/pith-number/KKZ7LB3P6DJWVMDLEE6PIABJ5F/graph.json","events_json":"https://pith.science/api/pith-number/KKZ7LB3P6DJWVMDLEE6PIABJ5F/events.json","paper":"https://pith.science/paper/KKZ7LB3P"},"agent_actions":{"view_html":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F","download_json":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F.json","view_paper":"https://pith.science/paper/KKZ7LB3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13682&json=true","fetch_graph":"https://pith.science/api/pith-number/KKZ7LB3P6DJWVMDLEE6PIABJ5F/graph.json","fetch_events":"https://pith.science/api/pith-number/KKZ7LB3P6DJWVMDLEE6PIABJ5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F/action/storage_attestation","attest_author":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F/action/author_attestation","sign_citation":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F/action/citation_signature","submit_replication":"https://pith.science/pith/KKZ7LB3P6DJWVMDLEE6PIABJ5F/action/replication_record"}},"created_at":"2026-07-05T02:35:57.278806+00:00","updated_at":"2026-07-05T02:35:57.278806+00:00"}