{"total":78,"rows":[{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"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":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2105.02201","title":"PD-GAN: Probabilistic Diverse GAN for Image Inpainting","created":"2021-05-05","cited_by_count":80,"area":null},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76,"area":null},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61,"area":null},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2404.04808","title":"MemFlow: Optical Flow Estimation and Prediction with Memory","created":"2024-04-07","cited_by_count":55,"area":null},{"id":"2105.14859","title":"Consistency Regularization for Variational Auto-Encoders","created":"2021-05-31","cited_by_count":51,"area":null},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49,"area":null},{"id":"2209.00852","title":"Geometry Aligned Variational Transformer for Image-conditioned Layout Generation","created":"2022-09-02","cited_by_count":33,"area":null},{"id":"2104.11212","title":"Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation","created":"2021-04-22","cited_by_count":32,"area":null},{"id":"2108.02760","title":"SLAMP: Stochastic Latent Appearance and Motion Prediction","created":"2021-08-05","cited_by_count":32,"area":null},{"id":"2106.08752","title":"Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation","created":"2021-06-16","cited_by_count":28,"area":null},{"id":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26,"area":null},{"id":"2211.08701","title":"Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction","created":"2022-11-16","cited_by_count":22,"area":null},{"id":"2101.00734","title":"Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey","created":"2021-01-04","cited_by_count":21,"area":null},{"id":"2104.09498","title":"Comparing Correspondences: Video Prediction with Correspondence-wise Losses","created":"2021-04-19","cited_by_count":16,"area":null},{"id":"2203.11305","title":"Generative Adversarial Network for Future Hand Segmentation from Egocentric Video","created":"2022-03-21","cited_by_count":16,"area":null},{"id":"2203.17070","title":"Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes","created":"2022-03-31","cited_by_count":15,"area":null},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2110.11681","title":"Conditional Variational Autoencoder for Learned Image Reconstruction","created":"2021-10-22","cited_by_count":13,"area":null},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2210.09563","title":"FedForgery: Generalized Face Forgery Detection with Residual Federated Learning","created":"2022-10-18","cited_by_count":12,"area":null},{"id":"2212.08896","title":"Human Image Generation: A Comprehensive Survey","created":"2022-12-17","cited_by_count":11,"area":null},{"id":"2304.06707","title":"Toward Reliable Human Pose Forecasting with Uncertainty","created":"2023-04-13","cited_by_count":11,"area":null},{"id":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2403.04899","title":"Towards Scene Graph Anticipation","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2509.21592","title":"What Happens Next? Anticipating Future Motion by Generating Point Trajectories","created":"2025-09-25","cited_by_count":10,"area":null},{"id":"2310.08312","title":"GePSAn: Generative Procedure Step Anticipation in Cooking Videos","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2401.10564","title":"Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting","created":"2024-01-19","cited_by_count":9,"area":null},{"id":"2104.03962","title":"Panoptic Segmentation Forecasting","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2303.14554","title":"Deep Kernel Methods Learn Better: From Cards to Process Optimization","created":"2023-03-25","cited_by_count":7,"area":null},{"id":"2306.05023","title":"Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders","created":"2023-06-08","cited_by_count":7,"area":null},{"id":"2308.04770","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2409.05790","title":"Predicting Critical Heat Flux with Uncertainty Quantification and Domain Generalization Using Conditional Variational Autoencoders and Deep Neural Networks","created":"2024-09-09","cited_by_count":6,"area":null},{"id":"2312.13714","title":"Bootstrap Masked Visual Modeling via Hard Patches Mining","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2101.02726","title":"A Novel Regression Loss for Non-Parametric Uncertainty Optimization","created":"2021-01-07","cited_by_count":4,"area":null},{"id":"2106.03665","title":"Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2308.10120","title":"Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasets","created":"2023-08-19","cited_by_count":4,"area":null},{"id":"2512.02846","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","created":"2025-12-02","cited_by_count":4,"area":null},{"id":"2204.07157","title":"Joint Forecasting of Panoptic Segmentations with Difference Attention","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2209.11277","title":"FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2106.05953","title":"PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2305.09006","title":"Physics-enhanced Gaussian Process Variational Autoencoder","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2410.04989","title":"Conditional Variational Autoencoders for Probabilistic Pose Regression","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2101.02974","title":"Approaching Neural Network Uncertainty Realism","created":"2021-01-08","cited_by_count":1,"area":null},{"id":"2101.12050","title":"VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wild","created":"2021-01-28","cited_by_count":1,"area":null},{"id":"2103.14182","title":"Self-Attentive 3D Human Pose and Shape Estimation from Videos","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2103.17261","title":"Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos","created":"2021-03-31","cited_by_count":1,"area":null},{"id":"2108.04496","title":"Regularized Sequential Latent Variable Models with Adversarial Neural Networks","created":"2021-08-10","cited_by_count":1,"area":null},{"id":"2202.05795","title":"Meta-learning with GANs for anomaly detection, with deployment in high-speed rail inspection system","created":"2022-02-11","cited_by_count":1,"area":null},{"id":"2208.09411","title":"Wildfire Forecasting with Satellite Images and Deep Generative Model","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2311.00961","title":"Concatenated Masked Autoencoders as Spatial-Temporal Learner","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2410.19063","title":"An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2506.01414","title":"Self-supervised Latent Space Optimization with Nebula Variational Coding","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2604.11737","title":"Learning Long-term Motion Embeddings for Efficient Kinematics Generation","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2607.16192","title":"MotionForesight: Re-purposing Video Models for Future 3D Scene-Flow Prediction","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2108.04899","title":"Analysis of ODE2VAE with Examples","created":"2021-08-10","cited_by_count":0,"area":null},{"id":"2112.04401","title":"FPPN: Future Pseudo-LiDAR Frame Prediction for Autonomous Driving","created":"2021-12-08","cited_by_count":0,"area":null},{"id":"2204.13678","title":"Unified Simulation, Perception, and Generation of Human Behavior","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2209.10693","title":"Stochastic Future Prediction in Real World Driving Scenarios","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2302.14395","title":"Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2304.00935","title":"Learning Sparsity of Representations with Discrete Latent Variables","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2306.15938","title":"Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2309.07504","title":"Connected Autonomous Vehicle Motion Planning with Video Predictions from Smart, Self-Supervised Infrastructure","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2310.17835","title":"One Style is All you Need to Generate a Video","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2409.15750","title":"The Roles of Generative Artificial Intelligence in Internet of Electric Vehicles","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2504.07260","title":"Quantifying Epistemic Uncertainty in Absolute Pose Regression","created":"2025-04-09","cited_by_count":0,"area":null},{"id":"2610.16591","title":"JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an Image","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}