{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"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":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"1905.01164","title":"SinGAN: Learning a Generative Model from a Single Natural Image","created":"2019-05-02","cited_by_count":348},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2305.08891","title":"Common Diffusion Noise Schedules and Sample Steps are Flawed","created":"2023-05-15","cited_by_count":310},{"id":"2306.14435","title":"DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing","created":"2023-06-26","cited_by_count":294},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"2305.10973","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","created":"2023-05-18","cited_by_count":219},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"2305.18264","title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","created":"2023-05-29","cited_by_count":139},{"id":"2303.17599","title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models","created":"2023-03-30","cited_by_count":137},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"1709.07592","title":"Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks","created":"2017-09-22","cited_by_count":89},{"id":"2303.08340","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","created":"2023-03-15","cited_by_count":82},{"id":"1903.07414","title":"A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization","created":"2019-03-15","cited_by_count":76},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61},{"id":"1812.02246","title":"Photo Wake-Up: 3D Character Animation from a Single Photo","created":"2018-12-05","cited_by_count":60},{"id":"2011.15128","title":"Animating Pictures with Eulerian Motion Fields","created":"2020-11-30","cited_by_count":55},{"id":"2112.03051","title":"Controllable Animation of Fluid Elements in Still Images","created":"2021-12-06","cited_by_count":45},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38},{"id":"2303.02881","title":"KBNet: Kernel Basis Network for Image Restoration","created":"2023-03-06","cited_by_count":33},{"id":"2302.11797","title":"Region-Aware Diffusion for Zero-shot Text-driven Image Editing","created":"2023-02-23","cited_by_count":25},{"id":"2401.10150","title":"Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation","created":"2024-01-18","cited_by_count":25},{"id":"2303.05724","title":"3D Cinemagraphy from a Single Image","created":"2023-03-10","cited_by_count":24},{"id":"2305.20049","title":"A Unified Conditional Framework for Diffusion-based Image Restoration","created":"2023-05-31","cited_by_count":22},{"id":"2307.03190","title":"Text-Guided Synthesis of Eulerian Cinemagraphs","created":"2023-07-06","cited_by_count":22},{"id":"2311.18835","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","created":"2023-11-30","cited_by_count":14},{"id":"2309.14207","title":"Automatic Animation of Hair Blowing in Still Portrait Photos","created":"2023-09-25","cited_by_count":13},{"id":"2303.01503","title":"FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation","created":"2023-03-02","cited_by_count":7}],"next_cursor":null}