{"total":102,"rows":[{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742,"area":null},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985,"area":null},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301,"area":null},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"area":null},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175,"area":null},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113,"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":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"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":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2207.11148","title":"InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images","created":"2022-07-22","cited_by_count":82,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2201.08361","title":"Stitch it in Time: GAN-Based Facial Editing of Real Videos","created":"2022-01-20","cited_by_count":68,"area":null},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62,"area":null},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53,"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":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48,"area":null},{"id":"2107.07224","title":"StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN","created":"2021-07-15","cited_by_count":47,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2305.03989","title":"LEO: Generative Latent Image Animator for Human Video Synthesis","created":"2023-05-06","cited_by_count":40,"area":null},{"id":"2406.06062","title":"ProcessPainter: Learn Painting Process from Sequence Data","created":"2024-06-10","cited_by_count":38,"area":null},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37,"area":null},{"id":"2304.02777","title":"MoStGAN-V: Video Generation with Temporal Motion Styles","created":"2023-04-05","cited_by_count":37,"area":null},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35,"area":null},{"id":"2206.08549","title":"Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images","created":"2022-06-17","cited_by_count":35,"area":null},{"id":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","cited_by_count":34,"area":null},{"id":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32,"area":null},{"id":"2403.20193","title":"Motion Inversion for Video Customization","created":"2024-03-29","cited_by_count":30,"area":null},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2212.06384","title":"PV3D: A 3D Generative Model for Portrait Video Generation","created":"2022-12-13","cited_by_count":23,"area":null},{"id":"2209.07143","title":"HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator","created":"2022-09-15","cited_by_count":22,"area":null},{"id":"2308.16909","title":"StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation","created":"2023-08-31","cited_by_count":19,"area":null},{"id":"2206.14797","title":"3D-Aware Video Generation","created":"2022-06-29","cited_by_count":17,"area":null},{"id":"2209.04252","title":"Talking Head from Speech Audio using a Pre-trained Image Generator","created":"2022-09-09","cited_by_count":16,"area":null},{"id":"2303.15893","title":"VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANs","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2504.07940","title":"Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos","created":"2025-04-10","cited_by_count":16,"area":null},{"id":"2505.23525","title":"Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2303.16541","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","created":"2023-03-29","cited_by_count":15,"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":"2208.10922","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","created":"2022-08-23","cited_by_count":14,"area":null},{"id":"2308.06097","title":"RIGID: Recurrent GAN Inversion and Editing of Real Face Videos","created":"2023-08-11","cited_by_count":13,"area":null},{"id":"2312.12917","title":"Sign Language Production with Latent Motion Transformer","created":"2023-12-20","cited_by_count":13,"area":null},{"id":"2212.07413","title":"Towards Smooth Video Composition","created":"2022-12-14","cited_by_count":12,"area":null},{"id":"2303.03684","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","created":"2023-03-07","cited_by_count":12,"area":null},{"id":"2305.00521","title":"StyleLipSync: Style-based Personalized Lip-sync Video Generation","created":"2023-04-30","cited_by_count":12,"area":null},{"id":"2208.07862","title":"StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3","created":"2022-08-16","cited_by_count":11,"area":null},{"id":"2411.19537","title":"Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook","created":"2024-11-29","cited_by_count":10,"area":null},{"id":"2109.12492","title":"ISF-GAN: An Implicit Style Function for High-Resolution Image-to-Image Translation","created":"2021-09-26","cited_by_count":9,"area":null},{"id":"2112.14971","title":"Contrastive Fine-grained Class Clustering via Generative Adversarial Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2208.05617","title":"Language-Guided Face Animation by Recurrent StyleGAN-based Generator","created":"2022-08-11","cited_by_count":9,"area":null},{"id":"2205.13996","title":"Video2StyleGAN: Disentangling Local and Global Variations in a Video","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2210.05825","title":"Controllable Radiance Fields for Dynamic Face Synthesis","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2411.10818","title":"FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations","created":"2024-11-16","cited_by_count":8,"area":null},{"id":"2204.00239","title":"ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition","created":"2022-04-01","cited_by_count":7,"area":null},{"id":"2207.13320","title":"Generator Knows What Discriminator Should Learn in Unconditional GANs","created":"2022-07-27","cited_by_count":7,"area":null},{"id":"2210.16579","title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","created":"2022-10-29","cited_by_count":7,"area":null},{"id":"2303.11251","title":"Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2406.18131","title":"Sequential Disentanglement by Extracting Static Information From A Single Sequence Element","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2411.14762","title":"Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction","created":"2024-11-22","cited_by_count":6,"area":null},{"id":"2511.20426","title":"Block Cascading: Training Free Acceleration of Block-Causal Video Models","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2303.02906","title":"MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairs","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2504.19834","title":"AnimateAnywhere: Rouse the Background in Human Image Animation","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2203.14512","title":"Expressive Talking Head Video Encoding in StyleGAN2 Latent-Space","created":"2022-03-28","cited_by_count":4,"area":null},{"id":"2210.02872","title":"Text-driven Video Prediction","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2308.11216","title":"Hamiltonian GAN","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2403.11263","title":"Stylized Face Sketch Extraction via Generative Prior with Limited Data","created":"2024-03-17","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":"2408.05599","title":"Sequential Representation Learning via Static-Dynamic Conditional Disentanglement","created":"2024-08-10","cited_by_count":4,"area":null},{"id":"2508.09959","title":"LIA-X: Interpretable Latent Portrait Animator","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2304.06020","title":"VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2304.07483","title":"Video Generation Beyond a Single Clip","created":"2023-04-15","cited_by_count":3,"area":null},{"id":"2308.10441","title":"X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2311.11642","title":"Video Face Re-Aging: Toward Temporally Consistent Face Re-Aging","created":"2023-11-20","cited_by_count":3,"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":"2403.14186","title":"StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2212.05667","title":"Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2205.05764","title":"Deep Learning and Synthetic Media","created":"2022-05-11","cited_by_count":1,"area":null},{"id":"2306.00559","title":"We never go out of Style: Motion Disentanglement by Subspace Decomposition of Latent Space","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2308.15472","title":"Learning Modulated Transformation in GANs","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2407.21450","title":"Forecasting Future Videos from Novel Views via Disentangled 3D Scene Representation","created":"2024-07-31","cited_by_count":1,"area":null},{"id":"2508.11183","title":"Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2512.21276","title":"GriDiT: Factorized Grid-Based Diffusion for Efficient Long Image Sequence Generation","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2609.24330","title":"AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2610.03543","title":"DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2201.06888","title":"Autoencoding Video Latents for Adversarial Video Generation","created":"2022-01-18","cited_by_count":0,"area":null},{"id":"2310.17835","title":"One Style is All you Need to Generate a Video","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2311.03884","title":"MeVGAN: GAN-based Plugin Model for Video Generation with Applications in Colonoscopy","created":"2023-11-07","cited_by_count":0,"area":null}],"next_cursor":"100"}