{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2012.07810","title":"Real-Time High-Resolution Background Matting","created":"2020-12-14","cited_by_count":173},{"id":"2109.11418","title":"Layered Neural Atlases for Consistent Video Editing","created":"2021-09-23","cited_by_count":137},{"id":"2205.15838","title":"D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video","created":"2022-05-31","cited_by_count":137},{"id":"2011.11961","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","created":"2020-11-24","cited_by_count":127},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100},{"id":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"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":"2403.18818","title":"ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion","created":"2024-03-27","cited_by_count":71},{"id":"2204.07151","title":"Deformable Sprites for Unsupervised Video Decomposition","created":"2022-04-14","cited_by_count":61},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60},{"id":"2208.06768","title":"Flow-Guided Transformer for Video Inpainting","created":"2022-08-14","cited_by_count":59},{"id":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54},{"id":"2009.07833","title":"Layered Neural Rendering for Retiming People in Video","created":"2020-09-16","cited_by_count":51},{"id":"2105.06993","title":"Omnimatte: Associating Objects and Their Effects in Video","created":"2021-05-14","cited_by_count":50},{"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":"2004.01180","title":"Learning to See Through Obstructions","created":"2020-04-02","cited_by_count":38},{"id":"2403.13044","title":"Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos","created":"2024-03-19","cited_by_count":38},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"2401.10226","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","created":"2024-01-18","cited_by_count":33},{"id":"1812.01461","title":"The Visual Centrifuge: Model-Free Layered Video Representations","created":"2018-12-04","cited_by_count":23},{"id":"2309.07749","title":"OmnimatteRF: Robust Omnimatte with 3D Background Modeling","created":"2023-09-14","cited_by_count":14},{"id":"2407.21017","title":"Matting by Generation","created":"2024-07-30","cited_by_count":13},{"id":"2410.13832","title":"VidPanos: Generative Panoramic Videos from Casual Panning Videos","created":"2024-10-17","cited_by_count":12},{"id":"2211.02145","title":"FactorMatte: Redefining Video Matting for Re-Composition Tasks","created":"2022-11-03","cited_by_count":8},{"id":"1910.11306","title":"Controllable Attention for Structured Layered Video Decomposition","created":"2019-10-24","cited_by_count":7},{"id":"2303.09370","title":"Learning Physical-Spatio-Temporal Features for Video Shadow Removal","created":"2023-03-16","cited_by_count":3}],"next_cursor":null}