{"total":1436,"rows":[{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778,"area":"diffusion"},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408,"area":null},{"id":"2104.00954","title":"Skillful Precipitation Nowcasting using Deep Generative Models of Radar","created":"2021-04-02","cited_by_count":311,"area":null},{"id":"2103.07719","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","created":"2021-03-13","cited_by_count":299,"area":null},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2106.12931","title":"Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting","created":"2021-06-24","cited_by_count":210,"area":null},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184,"area":null},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182,"area":null},{"id":"2202.08516","title":"SAITS: Self-Attention-based Imputation for Time Series","created":"2022-02-17","cited_by_count":169,"area":null},{"id":"2211.02556","title":"Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast","created":"2022-11-03","cited_by_count":166,"area":null},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159,"area":null},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154,"area":null},{"id":"2207.05833","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","created":"2022-07-12","cited_by_count":152,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"area":"wm"},{"id":"2107.07933","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","created":"2021-07-16","cited_by_count":143,"area":null},{"id":"2303.14483","title":"Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey","created":"2023-03-25","cited_by_count":140,"area":null},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137,"area":null},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133,"area":null},{"id":"2112.03558","title":"Graph Neural Controlled Differential Equations for Traffic Forecasting","created":"2021-12-07","cited_by_count":133,"area":null},{"id":"2310.06119","title":"Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis","created":"2023-10-09","cited_by_count":117,"area":null},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112,"area":"ssm"},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2307.07494","title":"TALL: Thumbnail Layout for Deepfake Video Detection","created":"2023-07-14","cited_by_count":100,"area":null},{"id":"2106.01862","title":"Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks","created":"2021-06-03","cited_by_count":99,"area":null},{"id":"2106.14103","title":"PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs","created":"2021-06-26","cited_by_count":98,"area":null},{"id":"2307.10422","title":"PreDiff: Precipitation Nowcasting with Latent Diffusion Models","created":"2023-07-19","cited_by_count":98,"area":"diffusion"},{"id":"2209.04934","title":"Clifford Neural Layers for PDE Modeling","created":"2022-09-08","cited_by_count":92,"area":null},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"area":null},{"id":"2207.08560","title":"Latency-Aware Collaborative Perception","created":"2022-07-18","cited_by_count":86,"area":null},{"id":"2101.06541","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","created":"2021-01-16","cited_by_count":84,"area":null},{"id":"2201.09113","title":"Predicting Physics in Mesh-reduced Space with Temporal Attention","created":"2022-01-22","cited_by_count":84,"area":null},{"id":"2404.02668","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","created":"2024-04-03","cited_by_count":81,"area":"ssm"},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77,"area":null},{"id":"2303.10462","title":"Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review","created":"2023-03-18","cited_by_count":75,"area":null},{"id":"2412.14123","title":"AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities","created":"2024-12-18","cited_by_count":74,"area":null},{"id":"2108.09091","title":"DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction","created":"2021-08-20","cited_by_count":73,"area":null},{"id":"2310.02642","title":"GET: Group Event Transformer for Event-Based Vision","created":"2023-10-04","cited_by_count":73,"area":null},{"id":"2204.02028","title":"A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts","created":"2022-04-05","cited_by_count":66,"area":null},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64,"area":null},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64,"area":null},{"id":"2305.02310","title":"Real-Time Radiance Fields for Single-Image Portrait View Synthesis","created":"2023-05-03","cited_by_count":64,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63,"area":null},{"id":"2104.00924","title":"Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning","created":"2021-04-02","cited_by_count":62,"area":null},{"id":"2106.04781","title":"Encoding physics to learn reaction-diffusion processes","created":"2021-06-09","cited_by_count":61,"area":null},{"id":"2312.06734","title":"DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting","created":"2023-12-11","cited_by_count":61,"area":null},{"id":"2203.07363","title":"Implicit Motion Handling for Video Camouflaged Object Detection","created":"2022-03-14","cited_by_count":60,"area":null},{"id":"2309.16940","title":"Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow","created":"2023-09-29","cited_by_count":58,"area":null},{"id":"2112.05126","title":"IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo","created":"2021-12-09","cited_by_count":56,"area":null},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56,"area":null},{"id":"2304.12891","title":"Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification","created":"2023-04-25","cited_by_count":56,"area":"diffusion"},{"id":"2402.04290","title":"CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling","created":"2024-02-06","cited_by_count":56,"area":null},{"id":"2507.02939","title":"Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting","created":"2025-06-27","cited_by_count":55,"area":"distill"},{"id":"2103.02243","title":"MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions","created":"2021-03-03","cited_by_count":54,"area":null},{"id":"2104.10642","title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","created":"2021-04-21","cited_by_count":54,"area":null},{"id":"2306.11249","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","created":"2023-06-20","cited_by_count":54,"area":null},{"id":"2309.01017","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","created":"2023-09-02","cited_by_count":54,"area":null},{"id":"2205.13817","title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models","created":"2022-05-27","cited_by_count":53,"area":"wm"},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2312.15709","title":"TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning","created":"2023-12-25","cited_by_count":52,"area":null},{"id":"2308.14419","title":"Graph-based Asynchronous Event Processing for Rapid Object Recognition","created":"2023-08-28","cited_by_count":51,"area":null},{"id":"2104.04258","title":"Counter-Strike Deathmatch with Large-Scale Behavioural Cloning","created":"2021-04-09","cited_by_count":50,"area":"offlinerl"},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49,"area":null},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49,"area":null},{"id":"2307.15042","title":"TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","created":"2023-07-27","cited_by_count":49,"area":"diffusion"},{"id":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2105.11982","title":"Quantifying Uncertainty in Deep Spatiotemporal Forecasting","created":"2021-05-25","cited_by_count":48,"area":null},{"id":"2112.02363","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","created":"2021-12-04","cited_by_count":47,"area":null},{"id":"2305.17852","title":"Hierarchical Neural Memory Network for Low Latency Event Processing","created":"2023-05-29","cited_by_count":47,"area":null},{"id":"2208.12079","title":"Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection","created":"2022-08-25","cited_by_count":46,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2101.00590","title":"RegNet: Self-Regulated Network for Image Classification","created":"2021-01-03","cited_by_count":44,"area":null},{"id":"2204.04746","title":"CholecTriplet2021: A benchmark challenge for surgical action triplet recognition","created":"2022-04-10","cited_by_count":44,"area":null},{"id":"2305.11421","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","created":"2023-05-19","cited_by_count":44,"area":null},{"id":"2206.00923","title":"Modeling Image Composition for Complex Scene Generation","created":"2022-06-02","cited_by_count":43,"area":null},{"id":"2306.14451","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","created":"2023-06-26","cited_by_count":43,"area":null},{"id":"2102.08820","title":"Crop mapping from image time series: deep learning with multi-scale label hierarchies","created":"2021-02-17","cited_by_count":42,"area":null},{"id":"2105.04281","title":"Visual Grounding with Transformers","created":"2021-05-10","cited_by_count":42,"area":null},{"id":"2106.06898","title":"Learning Dissipative Dynamics in Chaotic Systems","created":"2021-06-13","cited_by_count":42,"area":null},{"id":"2110.04076","title":"Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks","created":"2021-09-28","cited_by_count":42,"area":"wm"},{"id":"2112.06351","title":"Neural Point Process for Learning Spatiotemporal Event Dynamics","created":"2021-12-12","cited_by_count":42,"area":null},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2501.06019","title":"BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response","created":"2025-01-10","cited_by_count":41,"area":null},{"id":"2301.09152","title":"Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data","created":"2023-01-22","cited_by_count":40,"area":null},{"id":"2307.00754","title":"ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection","created":"2023-07-03","cited_by_count":40,"area":"diffusion"},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2404.14999","title":"A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data","created":"2024-04-23","cited_by_count":39,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2110.09766","title":"Memory-Augmented Deep Unfolding Network for Compressive Sensing","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2205.10468","title":"Deep Learning for Omnidirectional Vision: A Survey and New Perspectives","created":"2022-05-21","cited_by_count":38,"area":null},{"id":"2203.06622","title":"Multi-Bracket High Dynamic Range Imaging with Event Cameras","created":"2022-03-13","cited_by_count":37,"area":null},{"id":"2305.06382","title":"HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks","created":"2023-05-10","cited_by_count":37,"area":null},{"id":"2103.17235","title":"FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation","created":"2021-03-31","cited_by_count":36,"area":null}],"next_cursor":"100"}