{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KKOG6OJWJO37PCLW5XMEAO4W6C","short_pith_number":"pith:KKOG6OJW","schema_version":"1.0","canonical_sha256":"529c6f39364bb7f78976edd8403b96f0ab94bcfd23b31ef9eaede954473d7367","source":{"kind":"arxiv","id":"2412.16153","version":2},"attestation_state":"computed","paper":{"title":"MotiF: Making Text Count in Image Animation with Motion Focal Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Sun, Rohit Girdhar, Saketh Rambhatla, Samaneh Azadi, Shijie Wang, Xi Yin","submitted_at":"2024-12-20T18:57:06Z","abstract_excerpt":"Text-Image-to-Video (TI2V) generation aims to generate a video from an image following a text description, which is also referred to as text-guided image animation. Most existing methods struggle to generate videos that align well with the text prompts, particularly when motion is specified. To overcome this limitation, we introduce MotiF, a simple yet effective approach that directs the model's learning to the regions with more motion, thereby improving the text alignment and motion generation. We use optical flow to generate a motion heatmap and weight the loss according to the intensity of "},"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":"2412.16153","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:57:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"546fdbc3e6145744af8e79991831658ec528f02243af6382e922acb53ce86653","abstract_canon_sha256":"48b31df48658d91e22708e178c64c2d7c53d5345087d8a1ed967dc06e61bcf5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:41.076546Z","signature_b64":"pTANpLH84atOeWGU1cjmd/Q2wyr4uFzL+WEKcTrfZvHNf9ofs4XMmzkcK4CJkP84TnE+5CkYue+2cIzLIQOcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"529c6f39364bb7f78976edd8403b96f0ab94bcfd23b31ef9eaede954473d7367","last_reissued_at":"2026-07-05T10:37:41.075765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:41.075765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotiF: Making Text Count in Image Animation with Motion Focal Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Sun, Rohit Girdhar, Saketh Rambhatla, Samaneh Azadi, Shijie Wang, Xi Yin","submitted_at":"2024-12-20T18:57:06Z","abstract_excerpt":"Text-Image-to-Video (TI2V) generation aims to generate a video from an image following a text description, which is also referred to as text-guided image animation. Most existing methods struggle to generate videos that align well with the text prompts, particularly when motion is specified. To overcome this limitation, we introduce MotiF, a simple yet effective approach that directs the model's learning to the regions with more motion, thereby improving the text alignment and motion generation. We use optical flow to generate a motion heatmap and weight the loss according to the intensity of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16153","kind":"arxiv","version":2},"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/2412.16153/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":"2412.16153","created_at":"2026-07-05T10:37:41.075861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16153v2","created_at":"2026-07-05T10:37:41.075861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16153","created_at":"2026-07-05T10:37:41.075861+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKOG6OJWJO37","created_at":"2026-07-05T10:37:41.075861+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKOG6OJWJO37PCLW","created_at":"2026-07-05T10:37:41.075861+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKOG6OJW","created_at":"2026-07-05T10:37:41.075861+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/KKOG6OJWJO37PCLW5XMEAO4W6C","json":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C.json","graph_json":"https://pith.science/api/pith-number/KKOG6OJWJO37PCLW5XMEAO4W6C/graph.json","events_json":"https://pith.science/api/pith-number/KKOG6OJWJO37PCLW5XMEAO4W6C/events.json","paper":"https://pith.science/paper/KKOG6OJW"},"agent_actions":{"view_html":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C","download_json":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C.json","view_paper":"https://pith.science/paper/KKOG6OJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16153&json=true","fetch_graph":"https://pith.science/api/pith-number/KKOG6OJWJO37PCLW5XMEAO4W6C/graph.json","fetch_events":"https://pith.science/api/pith-number/KKOG6OJWJO37PCLW5XMEAO4W6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C/action/storage_attestation","attest_author":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C/action/author_attestation","sign_citation":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C/action/citation_signature","submit_replication":"https://pith.science/pith/KKOG6OJWJO37PCLW5XMEAO4W6C/action/replication_record"}},"created_at":"2026-07-05T10:37:41.075861+00:00","updated_at":"2026-07-05T10:37:41.075861+00:00"}