{"list":"other","total":71,"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"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":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"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":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"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":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2408.06070","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","created":"2024-08-12","cited_by_count":159},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"2207.09137","title":"ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild","created":"2022-07-19","cited_by_count":92},{"id":"2401.00896","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","created":"2023-12-31","cited_by_count":91},{"id":"2401.09985","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","created":"2024-01-18","cited_by_count":89},{"id":"2307.14073","title":"VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet","created":"2023-07-26","cited_by_count":83},{"id":"2408.02629","title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","created":"2024-08-05","cited_by_count":62},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52},{"id":"2404.15789","title":"MotionMaster: Training-free Camera Motion Transfer For Video Generation","created":"2024-04-24","cited_by_count":51},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28},{"id":"2401.01651","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","created":"2024-01-03","cited_by_count":27},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27},{"id":"2305.07214","title":"MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition","created":"2023-05-12","cited_by_count":26},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25},{"id":"2306.08713","title":"What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations","created":"2023-06-14","cited_by_count":25},{"id":"2107.03120","title":"Cross-View Exocentric to Egocentric Video Synthesis","created":"2021-07-07","cited_by_count":20},{"id":"2309.02423","title":"EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding","created":"2023-09-05","cited_by_count":15},{"id":"2403.09194","title":"Intention-driven Ego-to-Exo Video Generation","created":"2024-03-14","cited_by_count":13}],"next_cursor":null}