{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FPROL5Q3MP7ZG3HM4IQESHQPZR","short_pith_number":"pith:FPROL5Q3","schema_version":"1.0","canonical_sha256":"2be2e5f61b63ff936cece220491e0fcc5e6283a2558d8b0573737509d5b7f343","source":{"kind":"arxiv","id":"2403.08268","version":1},"attestation_state":"computed","paper":{"title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andong Wang, Chengfei Cai, Chenyang Qi, Heung-Yeung Shum, Hongfa Wang, Qifeng Chen, Wei Liu, Xiu Li, Yingqing He, Yue Ma, ZhiFeng Li","submitted_at":"2024-03-13T05:44:37Z","abstract_excerpt":"Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to control the movement of different objects or regions. Additionally, current I2V methods require users not only to describe the target motion but also to provide redundant detailed descriptions of frame contents. These two issues hinder the practical utilization of current I2V tools. In this paper, we propose a practical framework, named Follow-Your-Clic"},"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":"2403.08268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T05:44:37Z","cross_cats_sorted":[],"title_canon_sha256":"3e3e3a90dfb94dfc0b65665d62490970ec4abf0c5e7a6a9b38f0aea7e7361707","abstract_canon_sha256":"4448e1aaaf23e16d66243727e00da2080a21a096afa6fa21b6f377588508ad28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:36.510612Z","signature_b64":"TR5+RnwonZhVVkUBbz+Lj3oh5wQTwav+VL8gTxqTRg0b4qFZikWXdBXdDq7F6zeDBOlSKOcsT/F7tuI73T/jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2be2e5f61b63ff936cece220491e0fcc5e6283a2558d8b0573737509d5b7f343","last_reissued_at":"2026-07-05T07:55:36.510142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:36.510142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andong Wang, Chengfei Cai, Chenyang Qi, Heung-Yeung Shum, Hongfa Wang, Qifeng Chen, Wei Liu, Xiu Li, Yingqing He, Yue Ma, ZhiFeng Li","submitted_at":"2024-03-13T05:44:37Z","abstract_excerpt":"Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to control the movement of different objects or regions. Additionally, current I2V methods require users not only to describe the target motion but also to provide redundant detailed descriptions of frame contents. These two issues hinder the practical utilization of current I2V tools. In this paper, we propose a practical framework, named Follow-Your-Clic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08268","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/2403.08268/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":"2403.08268","created_at":"2026-07-05T07:55:36.510199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08268v1","created_at":"2026-07-05T07:55:36.510199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08268","created_at":"2026-07-05T07:55:36.510199+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPROL5Q3MP7Z","created_at":"2026-07-05T07:55:36.510199+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPROL5Q3MP7ZG3HM","created_at":"2026-07-05T07:55:36.510199+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPROL5Q3","created_at":"2026-07-05T07:55:36.510199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.03603","citing_title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01955","citing_title":"MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR","json":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR.json","graph_json":"https://pith.science/api/pith-number/FPROL5Q3MP7ZG3HM4IQESHQPZR/graph.json","events_json":"https://pith.science/api/pith-number/FPROL5Q3MP7ZG3HM4IQESHQPZR/events.json","paper":"https://pith.science/paper/FPROL5Q3"},"agent_actions":{"view_html":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR","download_json":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR.json","view_paper":"https://pith.science/paper/FPROL5Q3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08268&json=true","fetch_graph":"https://pith.science/api/pith-number/FPROL5Q3MP7ZG3HM4IQESHQPZR/graph.json","fetch_events":"https://pith.science/api/pith-number/FPROL5Q3MP7ZG3HM4IQESHQPZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR/action/storage_attestation","attest_author":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR/action/author_attestation","sign_citation":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR/action/citation_signature","submit_replication":"https://pith.science/pith/FPROL5Q3MP7ZG3HM4IQESHQPZR/action/replication_record"}},"created_at":"2026-07-05T07:55:36.510199+00:00","updated_at":"2026-07-05T07:55:36.510199+00:00"}