{"total":106,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341,"area":null},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174,"area":null},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168,"area":null},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149,"area":null},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"area":null},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"area":null},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124,"area":null},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117,"area":null},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111,"area":null},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107,"area":null},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105,"area":null},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101,"area":null},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95,"area":null},{"id":"2405.19707","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","created":"2024-05-30","cited_by_count":92,"area":null},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66,"area":null},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60,"area":null},{"id":"2502.10059","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","created":"2025-02-14","cited_by_count":57,"area":null},{"id":"2406.13527","title":"4K4DGen: Panoramic 4D Generation at 4K Resolution","created":"2024-06-19","cited_by_count":54,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51,"area":null},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2407.08674","title":"Still-Moving: Customized Video Generation without Customized Video Data","created":"2024-07-11","cited_by_count":50,"area":null},{"id":"2305.12328","title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","created":"2023-05-21","cited_by_count":44,"area":null},{"id":"2501.16550","title":"PhysAnimator: Physics-Guided Generative Cartoon Animation","created":"2025-01-27","cited_by_count":42,"area":null},{"id":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","cited_by_count":41,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2412.15214","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","created":"2024-12-19","cited_by_count":39,"area":null},{"id":"2411.16683","title":"Generative Omnimatte: Learning to Decompose Video into Layers","created":"2024-11-25","cited_by_count":38,"area":null},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35,"area":null},{"id":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35,"area":null},{"id":"2404.12388","title":"VideoGigaGAN: Towards Detail-rich Video Super-Resolution","created":"2024-04-18","cited_by_count":30,"area":null},{"id":"2505.20287","title":"MotionPro: A Precise Motion Controller for Image-to-Video Generation","created":"2025-05-26","cited_by_count":30,"area":null},{"id":"2401.01651","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","created":"2024-01-03","cited_by_count":27,"area":null},{"id":"2402.02085","title":"Detecting AI-Generated Video via Frame Consistency","created":"2024-02-03","cited_by_count":26,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2410.18978","title":"Framer: Interactive Frame Interpolation","created":"2024-10-24","cited_by_count":24,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2307.03190","title":"Text-Guided Synthesis of Eulerian Cinemagraphs","created":"2023-07-06","cited_by_count":22,"area":null},{"id":"2508.03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation","created":"2025-08-05","cited_by_count":22,"area":null},{"id":"2403.14611","title":"Explorative Inbetweening of Time and Space","created":"2024-03-21","cited_by_count":21,"area":null},{"id":"2405.20334","title":"VividDream: Generating 3D Scene with Ambient Dynamics","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21,"area":null},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2501.03059","title":"Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation","created":"2025-01-06","cited_by_count":20,"area":null},{"id":"2312.02919","title":"Fine-grained Controllable Video Generation via Object Appearance and Context","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2408.08189","title":"FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance","created":"2024-08-15","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2601.11035","title":"Your One-Stop Solution for AI-Generated Video Detection","created":"2026-01-16","cited_by_count":15,"area":null},{"id":"2410.02786","title":"Robust Symmetry Detection via Riemannian Langevin Dynamics","created":"2024-09-18","cited_by_count":14,"area":null},{"id":"2503.11412","title":"MTV-Inpaint: Multi-Task Long Video Inpainting","created":"2025-03-14","cited_by_count":14,"area":null},{"id":"2403.01800","title":"AtomoVideo: High Fidelity Image-to-Video Generation","created":"2024-03-04","cited_by_count":12,"area":null},{"id":"2501.06035","title":"Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction","created":"2025-01-10","cited_by_count":12,"area":null},{"id":"2503.00948","title":"Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think","created":"2025-03-02","cited_by_count":12,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2402.01590","title":"NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties","created":"2024-02-02","cited_by_count":10,"area":null},{"id":"2412.16153","title":"MotiF: Making Text Count in Image Animation with Motion Focal Loss","created":"2024-12-20","cited_by_count":10,"area":null},{"id":"2402.01239","title":"PRIME: Protect Your Videos From Malicious Editing","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2404.13680","title":"Zero-shot High-fidelity and Pose-controllable Character Animation","created":"2024-04-21","cited_by_count":9,"area":null},{"id":"2412.01987","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2311.16635","title":"MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2403.09638","title":"SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2410.06241","title":"ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2410.18538","title":"SMITE: Segment Me In TimE","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2503.01115","title":"WeGen: A Unified Model for Interactive Multimodal Generation as We Chat","created":"2025-03-03","cited_by_count":7,"area":null},{"id":"2407.21554","title":"Conditioned Prompt-Optimization for Continual Deepfake Detection","created":"2024-07-31","cited_by_count":6,"area":null},{"id":"2311.15445","title":"FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration","created":"2023-11-26","cited_by_count":5,"area":null},{"id":"2408.07605","title":"Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2412.10718","title":"Grid: Omni Visual Generation","created":"2024-12-14","cited_by_count":5,"area":null},{"id":"2401.13363","title":"Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2406.08845","title":"Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2409.17091","title":"Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2312.04561","title":"GenDeF: Learning Generative Deformation Field for Video Generation","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2405.13951","title":"Text Prompting for Multi-Concept Video Customization by Autoregressive Generation","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2410.24219","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2412.18966","title":"ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2502.17863","title":"A Survey: Spatiotemporal Consistency in Video Generation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2602.08961","title":"MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2602.12304","title":"OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.25707","title":"TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2503.10678","title":"VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2505.08239","title":"ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstruction","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2510.11107","title":"MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2603.19048","title":"Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2401.06035","title":"RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2408.10119","title":"Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2503.11044","title":"PSF-4D: A Progressive Sampling Framework for View Consistent 4D Editing","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2507.00334","title":"Populate-A-Scene: Affordance-Aware Human Video Generation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2508.09858","title":"HumanGenesis: Agent-Based Geometric and Generative Modeling for Synthetic Human Dynamics","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2602.19512","title":"Variational Trajectory Optimization of Anisotropic Diffusion Schedules","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2607.01962","title":"NeoMap: Training-free Novel-View Synthesis from Single Images and Videos","created":"2026-07-02","cited_by_count":1,"area":null}],"next_cursor":"100"}