{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WVT23S36LZYISMQSUG57A2ZWCG","short_pith_number":"pith:WVT23S36","schema_version":"1.0","canonical_sha256":"b567adcb7e5e70893212a1bbf06b3611857576fd57b0d63551db7b137e3d4a69","source":{"kind":"arxiv","id":"1711.06354","version":1},"attestation_state":"computed","paper":{"title":"Grounded Objects and Interactions for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asim Kadav, Chih-Yao Ma, Ghassan AlRegib, Hans Peter Graf, Iain Melvin, Zsolt Kira","submitted_at":"2017-11-16T23:39:08Z","abstract_excerpt":"We address the problem of video captioning by grounding language generation on object interactions in the video. Existing work mostly focuses on overall scene understanding with often limited or no emphasis on object interactions to address the problem of video understanding. In this paper, we propose SINet-Caption that learns to generate captions grounded over higher-order interactions between arbitrary groups of objects for fine-grained video understanding. We discuss the challenges and benefits of such an approach. We further demonstrate state-of-the-art results on the ActivityNet Captions "},"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":"1711.06354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-16T23:39:08Z","cross_cats_sorted":[],"title_canon_sha256":"e7c6fdca77c1d373b9abe0e408c5b6e8add6635eaec0169fad3a19a238e8db47","abstract_canon_sha256":"52fbfc1f6d4964b4e4ccdaa1587a471786bd87252026231425ef83c01fa1aa4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:21.347940Z","signature_b64":"RM04w1AjC82xG6sJK4IrGJej72zq8TFuMfgYAcGa+oIGhbRZkS5OydUYbh8LNhqCtAEA5f3JoiLaNeML5rfTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b567adcb7e5e70893212a1bbf06b3611857576fd57b0d63551db7b137e3d4a69","last_reissued_at":"2026-05-18T00:30:21.347306Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:21.347306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded Objects and Interactions for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asim Kadav, Chih-Yao Ma, Ghassan AlRegib, Hans Peter Graf, Iain Melvin, Zsolt Kira","submitted_at":"2017-11-16T23:39:08Z","abstract_excerpt":"We address the problem of video captioning by grounding language generation on object interactions in the video. Existing work mostly focuses on overall scene understanding with often limited or no emphasis on object interactions to address the problem of video understanding. In this paper, we propose SINet-Caption that learns to generate captions grounded over higher-order interactions between arbitrary groups of objects for fine-grained video understanding. We discuss the challenges and benefits of such an approach. We further demonstrate state-of-the-art results on the ActivityNet Captions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06354","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":""},"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":"1711.06354","created_at":"2026-05-18T00:30:21.347393+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.06354v1","created_at":"2026-05-18T00:30:21.347393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06354","created_at":"2026-05-18T00:30:21.347393+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVT23S36LZYI","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVT23S36LZYISMQS","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVT23S36","created_at":"2026-05-18T12:31:53.515858+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/WVT23S36LZYISMQSUG57A2ZWCG","json":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG.json","graph_json":"https://pith.science/api/pith-number/WVT23S36LZYISMQSUG57A2ZWCG/graph.json","events_json":"https://pith.science/api/pith-number/WVT23S36LZYISMQSUG57A2ZWCG/events.json","paper":"https://pith.science/paper/WVT23S36"},"agent_actions":{"view_html":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG","download_json":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG.json","view_paper":"https://pith.science/paper/WVT23S36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.06354&json=true","fetch_graph":"https://pith.science/api/pith-number/WVT23S36LZYISMQSUG57A2ZWCG/graph.json","fetch_events":"https://pith.science/api/pith-number/WVT23S36LZYISMQSUG57A2ZWCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG/action/storage_attestation","attest_author":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG/action/author_attestation","sign_citation":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG/action/citation_signature","submit_replication":"https://pith.science/pith/WVT23S36LZYISMQSUG57A2ZWCG/action/replication_record"}},"created_at":"2026-05-18T00:30:21.347393+00:00","updated_at":"2026-05-18T00:30:21.347393+00:00"}