{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TR3ZEGYECUVGTHDTYBPD3HMZBZ","short_pith_number":"pith:TR3ZEGYE","schema_version":"1.0","canonical_sha256":"9c77921b04152a699c73c05e3d9d990e4130653a953f03fc05dd1c8c0e038021","source":{"kind":"arxiv","id":"2504.15376","version":2},"attestation_state":"computed","paper":{"title":"Towards Understanding Camera Motions in Any Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chancharik Mitra, Chuang Gan, Daniel Jiang, Deva Ramanan, Hewei Wang, Jay Karhade, Mingyu Chen, Rushikesh Zawar, Sifan Liu, Siyuan Cen, Tiffany Ling, Xue Bai, Yilun Du, Yuhan Huang, Zhiqiu Lin","submitted_at":"2025-04-21T18:34:57Z","abstract_excerpt":"We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality control process. One of our contributions is a taxonomy of camera motion primitives, designed in collaboration with cinematographers. We find, for example, that some motions like \"follow\" (or tracking) require understanding scene content like moving subjects. We conduct a large-scale human study to quantify human annotation performance, revealing that domain e"},"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":"2504.15376","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T18:34:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"1d4d955c881e11462dcc1a52b4f7e67c3cceef2efccd897dd233c62dce198a5c","abstract_canon_sha256":"d197b2a854493ddc1f9ae63336fadf4cbdcdb3b33b6618bcb3a6e7d986fdcbee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:22.254488Z","signature_b64":"atojD9Zdm+kkWTzUd7nG34VAYWuvPZpJspLYqF/D7xZliDSG+BSZG9EJivGoWIVfakgBcXXmTJ9G3hby3NMmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c77921b04152a699c73c05e3d9d990e4130653a953f03fc05dd1c8c0e038021","last_reissued_at":"2026-07-05T12:01:22.253990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:22.253990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding Camera Motions in Any Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chancharik Mitra, Chuang Gan, Daniel Jiang, Deva Ramanan, Hewei Wang, Jay Karhade, Mingyu Chen, Rushikesh Zawar, Sifan Liu, Siyuan Cen, Tiffany Ling, Xue Bai, Yilun Du, Yuhan Huang, Zhiqiu Lin","submitted_at":"2025-04-21T18:34:57Z","abstract_excerpt":"We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality control process. One of our contributions is a taxonomy of camera motion primitives, designed in collaboration with cinematographers. We find, for example, that some motions like \"follow\" (or tracking) require understanding scene content like moving subjects. We conduct a large-scale human study to quantify human annotation performance, revealing that domain e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15376","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/2504.15376/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":"2504.15376","created_at":"2026-07-05T12:01:22.254050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15376v2","created_at":"2026-07-05T12:01:22.254050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15376","created_at":"2026-07-05T12:01:22.254050+00:00"},{"alias_kind":"pith_short_12","alias_value":"TR3ZEGYECUVG","created_at":"2026-07-05T12:01:22.254050+00:00"},{"alias_kind":"pith_short_16","alias_value":"TR3ZEGYECUVGTHDT","created_at":"2026-07-05T12:01:22.254050+00:00"},{"alias_kind":"pith_short_8","alias_value":"TR3ZEGYE","created_at":"2026-07-05T12:01:22.254050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24636","citing_title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26964","citing_title":"Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14815","citing_title":"Probing into Camera Control of Video Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26964","citing_title":"Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20165","citing_title":"CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00181","citing_title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09433","citing_title":"Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03877","citing_title":"DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24762","citing_title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20157","citing_title":"HumanScore: Benchmarking Human Motions in Generated Videos","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ","json":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ.json","graph_json":"https://pith.science/api/pith-number/TR3ZEGYECUVGTHDTYBPD3HMZBZ/graph.json","events_json":"https://pith.science/api/pith-number/TR3ZEGYECUVGTHDTYBPD3HMZBZ/events.json","paper":"https://pith.science/paper/TR3ZEGYE"},"agent_actions":{"view_html":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ","download_json":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ.json","view_paper":"https://pith.science/paper/TR3ZEGYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15376&json=true","fetch_graph":"https://pith.science/api/pith-number/TR3ZEGYECUVGTHDTYBPD3HMZBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TR3ZEGYECUVGTHDTYBPD3HMZBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ/action/storage_attestation","attest_author":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ/action/author_attestation","sign_citation":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ/action/citation_signature","submit_replication":"https://pith.science/pith/TR3ZEGYECUVGTHDTYBPD3HMZBZ/action/replication_record"}},"created_at":"2026-07-05T12:01:22.254050+00:00","updated_at":"2026-07-05T12:01:22.254050+00:00"}