{"list":"other","total":79,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"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":"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"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":"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":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"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":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"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":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"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":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2009.03465","title":"LaSOT: A High-quality Large-scale Single Object Tracking Benchmark","created":"2020-09-08","cited_by_count":132},{"id":"2501.08331","title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","created":"2025-01-14","cited_by_count":117},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93},{"id":"2212.04500","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","created":"2022-12-08","cited_by_count":90},{"id":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77},{"id":"2312.07509","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","created":"2023-12-12","cited_by_count":76},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71},{"id":"2211.13222","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","created":"2022-11-23","cited_by_count":68},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68},{"id":"2406.15339","title":"Image Conductor: Precision Control for Interactive Video Synthesis","created":"2024-06-21","cited_by_count":63},{"id":"2412.03859","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","created":"2024-12-05","cited_by_count":60},{"id":"2311.18830","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","created":"2023-11-30","cited_by_count":57},{"id":"2406.16863","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","created":"2024-06-24","cited_by_count":56},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46},{"id":"2410.13830","title":"DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control","created":"2024-10-17","cited_by_count":43},{"id":"2408.11475","title":"TrackGo: A Flexible and Efficient Method for Controllable Video Generation","created":"2024-08-21","cited_by_count":39},{"id":"2412.15214","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","created":"2024-12-19","cited_by_count":39},{"id":"2405.20325","title":"MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion","created":"2024-05-30","cited_by_count":29},{"id":"2502.16587","title":"Human2Robot: Learning Robot Actions from Paired Human-Robot Videos","created":"2025-02-23","cited_by_count":25},{"id":"2406.06465","title":"AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction","created":"2024-06-10","cited_by_count":21},{"id":"2311.14768","title":"AdaDiff: Adaptive Step Selection for Fast Diffusion Models","created":"2023-11-24","cited_by_count":20},{"id":"2501.03059","title":"Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation","created":"2025-01-06","cited_by_count":20},{"id":"2311.18837","title":"VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models","created":"2023-11-30","cited_by_count":19},{"id":"2412.07721","title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","created":"2024-12-10","cited_by_count":18},{"id":"2408.15241","title":"GenRec: Unifying Video Generation and Recognition with Diffusion Models","created":"2024-08-27","cited_by_count":11},{"id":"2501.09008","title":"SimGen: A Diffusion-Based Framework for Simultaneous Surgical Image and Segmentation Mask Generation","created":"2025-01-15","cited_by_count":5}],"next_cursor":null}