{"total":23,"rows":[{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"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":"2211.13319","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","created":"2022-11-23","cited_by_count":76,"area":null},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53,"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":"2206.04452","title":"Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer","created":"2022-06-09","cited_by_count":30,"area":null},{"id":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26,"area":null},{"id":"2212.05005","title":"Memories are One-to-Many Mapping Alleviators in Talking Face Generation","created":"2022-12-09","cited_by_count":22,"area":null},{"id":"2207.13286","title":"Vector Quantized Image-to-Image Translation","created":"2022-07-27","cited_by_count":16,"area":null},{"id":"2210.12683","title":"GAN-based Facial Attribute Manipulation","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"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":"2308.14152","title":"Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers","created":"2023-08-27","cited_by_count":7,"area":null},{"id":"2312.06116","title":"Stellar: Systematic Evaluation of Human-Centric Personalized Text-to-Image Methods","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2507.02900","title":"Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions","created":"2025-06-23","cited_by_count":6,"area":null},{"id":"2206.03010","title":"MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learning","created":"2022-06-07","cited_by_count":5,"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":"2401.11631","title":"Text-to-Image Cross-Modal Generation: A Systematic Review","created":"2024-01-21","cited_by_count":5,"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":"2501.02621","title":"LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2403.14368","title":"CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2603.05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","created":"2026-03-06","cited_by_count":1,"area":null}],"next_cursor":null}