{"total":41,"rows":[{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35,"area":null},{"id":"2505.15145","title":"CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation","created":"2025-05-21","cited_by_count":23,"area":null},{"id":"2510.18873","title":"DSI-Bench: A Benchmark for Dynamic Spatial Intelligence","created":"2025-10-21","cited_by_count":23,"area":null},{"id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2510.08673","title":"Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation","created":"2025-10-09","cited_by_count":19,"area":null},{"id":"2510.20661","title":"UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset","created":"2025-10-23","cited_by_count":18,"area":null},{"id":"2512.20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs","created":"2025-12-23","cited_by_count":12,"area":null},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10,"area":null},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2510.05097","title":"Pulp Motion: Framing-aware multimodal camera and human motion generation","created":"2025-10-06","cited_by_count":8,"area":null},{"id":"2510.07249","title":"TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2512.19020","title":"CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2604.24762","title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2512.03619","title":"LAMP: Language-Assisted Motion Planning for Controllable Video Generation","created":"2025-12-03","cited_by_count":4,"area":null},{"id":"2604.20157","title":"HumanScore: Benchmarking Human Motions in Generated Videos","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2605.29563","title":"Planning with the Views","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2603.14790","title":"Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.14615","title":"CalibAnyView: Beyond Single-View Camera Calibration in the Wild","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2506.16047","title":"Leveraging Optimal Transport for Distributed Two-Sample Testing: An Integrated Transportation Distance-based Framework","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2512.12209","title":"CineLOG: A Training Free Approach for Cinematic Long Video Generation","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.13371","title":"Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.14815","title":"Probing into Camera Control of Video Models","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.03043","title":"Natural Language Camera Movement Understanding","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.24591","title":"CameraAnything: Refilming Videos with Arbitrary Camera Control","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2512.11301","title":"MultiEgo: A Multi-View Egocentric Video Dataset for 4D Scene Reconstruction","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.19129","title":"CLIP-Guided Unsupervised Semantic-Aware Exposure Correction","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.18448","title":"Seeking Universal Shot Language Understanding Solutions","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2607.21576","title":"Self-Supervised Learning of Structured Dynamics from Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.09082","title":"F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.30068","title":"TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02847","title":"RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.06652","title":"VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.08938","title":"EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.01661","title":"DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}