{"list":"other","total":52,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2403.06976","title":"BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion","created":"2024-03-11","cited_by_count":202},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"1904.10247","title":"Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN","created":"2019-04-23","cited_by_count":87},{"id":"2312.03816","title":"AVID: Any-Length Video Inpainting with Diffusion Model","created":"2023-12-06","cited_by_count":82},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77},{"id":"2405.13865","title":"ReVideo: Remake a Video with Motion and Content Control","created":"2024-05-22","cited_by_count":74},{"id":"2412.18597","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","created":"2024-12-24","cited_by_count":74},{"id":"2312.16693","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","created":"2023-12-27","cited_by_count":70},{"id":"2208.06768","title":"Flow-Guided Transformer for Video Inpainting","created":"2022-08-14","cited_by_count":59},{"id":"1806.08482","title":"Video Inpainting by Jointly Learning Temporal Structure and Spatial Details","created":"2018-06-22","cited_by_count":58},{"id":"1908.11587","title":"Copy-and-Paste Networks for Deep Video Inpainting","created":"2019-08-30","cited_by_count":58},{"id":"2403.12035","title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","created":"2024-03-18","cited_by_count":50},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49},{"id":"2402.13185","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","created":"2024-02-20","cited_by_count":48},{"id":"2401.03395","title":"Deep Learning-based Image and Video Inpainting: A Survey","created":"2024-01-07","cited_by_count":44},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44},{"id":"2405.11794","title":"ViViD: Video Virtual Try-on using Diffusion Models","created":"2024-05-20","cited_by_count":42},{"id":"2009.05721","title":"Short-Term and Long-Term Context Aggregation Network for Video Inpainting","created":"2020-09-12","cited_by_count":35},{"id":"2104.03507","title":"Progressive Temporal Feature Alignment Network for Video Inpainting","created":"2021-04-08","cited_by_count":35},{"id":"2412.10316","title":"BrushEdit: All-In-One Image Inpainting and Editing","created":"2024-12-13","cited_by_count":31},{"id":"2104.06637","title":"Decoupled Spatial-Temporal Transformer for Video Inpainting","created":"2021-04-14","cited_by_count":28},{"id":"2407.21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","created":"2024-07-30","cited_by_count":26},{"id":"2402.04852","title":"Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning","created":"2024-02-07","cited_by_count":25}],"next_cursor":null}