{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y2543CG7ASKQUCXUB3OJRMSP47","short_pith_number":"pith:Y2543CG7","schema_version":"1.0","canonical_sha256":"c6bbcd88df04950a0af40edc98b24fe7ebd03be1ea70a6a4d242ddf7976db97b","source":{"kind":"arxiv","id":"1803.07485","version":1},"attestation_state":"computed","paper":{"title":"Actor and Action Video Segmentation from a Sentence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Ghodrati, Cees G.M. Snoek, Kirill Gavrilyuk, Zhenyang Li","submitted_at":"2018-03-20T15:29:38Z","abstract_excerpt":"This paper strives for pixel-level segmentation of actors and their actions in video content. Different from existing works, which all learn to segment from a fixed vocabulary of actor and action pairs, we infer the segmentation from a natural language input sentence. This allows to distinguish between fine-grained actors in the same super-category, identify actor and action instances, and segment pairs that are outside of the actor and action vocabulary. We propose a fully-convolutional model for pixel-level actor and action segmentation using an encoder-decoder architecture optimized for vid"},"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":"1803.07485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-20T15:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"d68350af8bd5aaeaaa3ee3d4955a7d41f5814f9c1fc1f7bfa501f6ae6e4800ad","abstract_canon_sha256":"43b919c609b11793bc37069aff77dd64cbe9a10c7c6b307a372c28175a0a670a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:33.063161Z","signature_b64":"yVC5NhI1AwovoDRcwQj8GbREoIm+SSYQ+nIKXeemue2Fnjy9z7YOOFdtVy5SJRcZBvnA6iz4oMc4TLRoWwmwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6bbcd88df04950a0af40edc98b24fe7ebd03be1ea70a6a4d242ddf7976db97b","last_reissued_at":"2026-05-18T00:20:33.062578Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:33.062578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Actor and Action Video Segmentation from a Sentence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Ghodrati, Cees G.M. Snoek, Kirill Gavrilyuk, Zhenyang Li","submitted_at":"2018-03-20T15:29:38Z","abstract_excerpt":"This paper strives for pixel-level segmentation of actors and their actions in video content. Different from existing works, which all learn to segment from a fixed vocabulary of actor and action pairs, we infer the segmentation from a natural language input sentence. This allows to distinguish between fine-grained actors in the same super-category, identify actor and action instances, and segment pairs that are outside of the actor and action vocabulary. We propose a fully-convolutional model for pixel-level actor and action segmentation using an encoder-decoder architecture optimized for vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07485","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":"1803.07485","created_at":"2026-05-18T00:20:33.062646+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.07485v1","created_at":"2026-05-18T00:20:33.062646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07485","created_at":"2026-05-18T00:20:33.062646+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2543CG7ASKQ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2543CG7ASKQUCXU","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2543CG7","created_at":"2026-05-18T12:33:04.347982+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/Y2543CG7ASKQUCXUB3OJRMSP47","json":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47.json","graph_json":"https://pith.science/api/pith-number/Y2543CG7ASKQUCXUB3OJRMSP47/graph.json","events_json":"https://pith.science/api/pith-number/Y2543CG7ASKQUCXUB3OJRMSP47/events.json","paper":"https://pith.science/paper/Y2543CG7"},"agent_actions":{"view_html":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47","download_json":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47.json","view_paper":"https://pith.science/paper/Y2543CG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.07485&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2543CG7ASKQUCXUB3OJRMSP47/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2543CG7ASKQUCXUB3OJRMSP47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47/action/storage_attestation","attest_author":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47/action/author_attestation","sign_citation":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47/action/citation_signature","submit_replication":"https://pith.science/pith/Y2543CG7ASKQUCXUB3OJRMSP47/action/replication_record"}},"created_at":"2026-05-18T00:20:33.062646+00:00","updated_at":"2026-05-18T00:20:33.062646+00:00"}