{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ON4XZXADQCI6VGSFOJW6GWBUH5","short_pith_number":"pith:ON4XZXAD","schema_version":"1.0","canonical_sha256":"73797cdc038091ea9a45726de358343f49edbe65c6222d4a30562cde46f7ce44","source":{"kind":"arxiv","id":"2304.05634","version":1},"attestation_state":"computed","paper":{"title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Kumar Singh, Dhruv Srivastava, Makarand Tapaswi","submitted_at":"2023-04-12T06:31:14Z","abstract_excerpt":"Movie story analysis requires understanding characters' emotions and mental states. Towards this goal, we formulate emotion understanding as predicting a diverse and multi-label set of emotions at the level of a movie scene and for each character. We propose EmoTx, a multimodal Transformer-based architecture that ingests videos, multiple characters, and dialog utterances to make joint predictions. By leveraging annotations from the MovieGraphs dataset, we aim to predict classic emotions (e.g. happy, angry) and other mental states (e.g. honest, helpful). We conduct experiments on the most frequ"},"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":"2304.05634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T06:31:14Z","cross_cats_sorted":[],"title_canon_sha256":"d9209a679867b4da02a871eacb52eb4a808d1d088db62c544b42987eefc9a2f1","abstract_canon_sha256":"ec101ffd3c4e9789a954f8cfa3bd0088e6338204f8dde19443f3793c6b34128c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:21.530801Z","signature_b64":"sJe09N0+Zb8chcmRRsDnQ9oFZE6N2SJdDmh5uJM86FNxYWxgFppTtSew/QyEjkRzDch7N3EWzellfdF6MiuADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73797cdc038091ea9a45726de358343f49edbe65c6222d4a30562cde46f7ce44","last_reissued_at":"2026-07-05T06:00:21.530344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:21.530344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Kumar Singh, Dhruv Srivastava, Makarand Tapaswi","submitted_at":"2023-04-12T06:31:14Z","abstract_excerpt":"Movie story analysis requires understanding characters' emotions and mental states. Towards this goal, we formulate emotion understanding as predicting a diverse and multi-label set of emotions at the level of a movie scene and for each character. We propose EmoTx, a multimodal Transformer-based architecture that ingests videos, multiple characters, and dialog utterances to make joint predictions. By leveraging annotations from the MovieGraphs dataset, we aim to predict classic emotions (e.g. happy, angry) and other mental states (e.g. honest, helpful). We conduct experiments on the most frequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05634","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/2304.05634/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":"2304.05634","created_at":"2026-07-05T06:00:21.530407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05634v1","created_at":"2026-07-05T06:00:21.530407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05634","created_at":"2026-07-05T06:00:21.530407+00:00"},{"alias_kind":"pith_short_12","alias_value":"ON4XZXADQCI6","created_at":"2026-07-05T06:00:21.530407+00:00"},{"alias_kind":"pith_short_16","alias_value":"ON4XZXADQCI6VGSF","created_at":"2026-07-05T06:00:21.530407+00:00"},{"alias_kind":"pith_short_8","alias_value":"ON4XZXAD","created_at":"2026-07-05T06:00:21.530407+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/ON4XZXADQCI6VGSFOJW6GWBUH5","json":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5.json","graph_json":"https://pith.science/api/pith-number/ON4XZXADQCI6VGSFOJW6GWBUH5/graph.json","events_json":"https://pith.science/api/pith-number/ON4XZXADQCI6VGSFOJW6GWBUH5/events.json","paper":"https://pith.science/paper/ON4XZXAD"},"agent_actions":{"view_html":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5","download_json":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5.json","view_paper":"https://pith.science/paper/ON4XZXAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05634&json=true","fetch_graph":"https://pith.science/api/pith-number/ON4XZXADQCI6VGSFOJW6GWBUH5/graph.json","fetch_events":"https://pith.science/api/pith-number/ON4XZXADQCI6VGSFOJW6GWBUH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5/action/storage_attestation","attest_author":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5/action/author_attestation","sign_citation":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5/action/citation_signature","submit_replication":"https://pith.science/pith/ON4XZXADQCI6VGSFOJW6GWBUH5/action/replication_record"}},"created_at":"2026-07-05T06:00:21.530407+00:00","updated_at":"2026-07-05T06:00:21.530407+00:00"}