{"total":109,"rows":[{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"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":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163,"area":null},{"id":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153,"area":null},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"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":"2207.11148","title":"InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images","created":"2022-07-22","cited_by_count":82,"area":null},{"id":"2112.03806","title":"OOD-GNN: Out-of-Distribution Generalized Graph Neural Network","created":"2021-12-07","cited_by_count":78,"area":null},{"id":"2207.08132","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","created":"2022-07-17","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":"2103.15537","title":"Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization","created":"2021-03-29","cited_by_count":69,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","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":"2207.05027","title":"Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations","created":"2022-07-11","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":"2110.15255","title":"Self-Supervised Learning Disentangled Group Representation as Feature","created":"2021-10-28","cited_by_count":47,"area":null},{"id":"2105.02685","title":"A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations","created":"2021-05-06","cited_by_count":37,"area":null},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37,"area":null},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37,"area":null},{"id":"2110.02951","title":"Video Autoencoder: self-supervised disentanglement of static 3D structure and motion","created":"2021-10-06","cited_by_count":34,"area":null},{"id":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32,"area":null},{"id":"2412.04842","title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","created":"2024-12-06","cited_by_count":27,"area":null},{"id":"2210.04458","title":"OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2101.07496","title":"Disentangled Recurrent Wasserstein Autoencoder","created":"2021-01-19","cited_by_count":22,"area":null},{"id":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2104.09762","title":"Learning Semantic-Aware Dynamics for Video Prediction","created":"2021-04-20","cited_by_count":21,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2103.04693","title":"Unsupervised Object-Based Transition Models for 3D Partially Observable Environments","created":"2021-03-08","cited_by_count":20,"area":null},{"id":"2310.16167","title":"iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis","created":"2023-10-24","cited_by_count":20,"area":null},{"id":"2108.11800","title":"Efficient Out-of-Distribution Detection Using Latent Space of $\\beta$-VAE for Cyber-Physical Systems","created":"2021-08-26","cited_by_count":19,"area":null},{"id":"2206.06131","title":"Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers","created":"2022-06-10","cited_by_count":18,"area":null},{"id":"2206.11493","title":"Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization","created":"2022-06-23","cited_by_count":18,"area":null},{"id":"2308.16154","title":"MMVP: Motion-Matrix-based Video Prediction","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2210.03466","title":"Latent Neural ODEs with Sparse Bayesian Multiple Shooting","created":"2022-10-07","cited_by_count":17,"area":null},{"id":"2101.07046","title":"Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models","created":"2021-01-18","cited_by_count":14,"area":null},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2410.01376","title":"Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2109.12548","title":"Disentangled Feature Representation for Few-shot Image Classification","created":"2021-09-26","cited_by_count":12,"area":null},{"id":"2212.06026","title":"Video Prediction by Efficient Transformers","created":"2022-12-12","cited_by_count":12,"area":null},{"id":"2211.10666","title":"VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2110.03446","title":"A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2104.01122","title":"M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers","created":"2021-04-02","cited_by_count":8,"area":null},{"id":"2303.01869","title":"Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2104.03962","title":"Panoptic Segmentation Forecasting","created":"2021-04-08","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":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2406.18131","title":"Sequential Disentanglement by Extracting Static Information From A Single Sequence Element","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2412.16155","title":"Can Generative Video Models Help Pose Estimation?","created":"2024-12-20","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":"2106.11712","title":"Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting","created":"2021-06-22","cited_by_count":6,"area":null},{"id":"2303.03432","title":"A polar prediction model for learning to represent visual transformations","created":"2023-03-06","cited_by_count":6,"area":null},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2112.01641","title":"Hamiltonian latent operators for content and motion disentanglement in image sequences","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2210.01322","title":"Representing Spatial Trajectories as Distributions","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2307.06701","title":"S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2403.05064","title":"Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision","created":"2024-03-08","cited_by_count":5,"area":null},{"id":"2406.19253","title":"Advection Augmented Convolutional Neural Networks","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2411.00530","title":"DeepSeq2: Enhanced Sequential Circuit Learning with Disentangled Representations","created":"2024-11-01","cited_by_count":5,"area":null},{"id":"2102.03586","title":"CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning","created":"2021-02-06","cited_by_count":4,"area":null},{"id":"2102.12061","title":"Deep Video Prediction for Time Series Forecasting","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2110.03498","title":"On the relationship between disentanglement and multi-task learning","created":"2021-10-07","cited_by_count":4,"area":null},{"id":"2110.03882","title":"ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning","created":"2021-10-08","cited_by_count":4,"area":null},{"id":"2303.05066","title":"Distortion-Disentangled Contrastive Learning","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2303.08811","title":"Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis","created":"2023-03-15","cited_by_count":4,"area":null},{"id":"2410.22288","title":"Motion Graph Unleashed: A Novel Approach to Video Prediction","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2102.00324","title":"Video Reenactment as Inductive Bias for Content-Motion Disentanglement","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2111.10539","title":"Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation","created":"2021-11-20","cited_by_count":3,"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":"2308.10441","title":"X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2105.06660","title":"Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2110.00547","title":"Self-Supervised Decomposition, Disentanglement and Prediction of Video Sequences while Interpreting Dynamics: A Koopman Perspective","created":"2021-10-01","cited_by_count":2,"area":null},{"id":"2110.12978","title":"MoDeRNN: Towards Fine-grained Motion Details for Spatiotemporal Predictive Learning","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2110.14392","title":"TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction","created":"2021-10-27","cited_by_count":2,"area":null},{"id":"2201.00100","title":"Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images","created":"2022-01-01","cited_by_count":2,"area":null},{"id":"2205.01314","title":"Distilling Governing Laws and Source Input for Dynamical Systems from Videos","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2212.11642","title":"Predictive Coding Based Multiscale Network with Encoder-Decoder LSTM for Video Prediction","created":"2022-12-22","cited_by_count":2,"area":null},{"id":"2304.07099","title":"Prior based Sampling for Adaptive LiDAR","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2308.11079","title":"Long-Term Prediction of Natural Video Sequences with Robust Video Predictors","created":"2023-08-21","cited_by_count":2,"area":null},{"id":"2507.02619","title":"L-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2101.09500","title":"Disentangled Sequence Clustering for Human Intention Inference","created":"2021-01-23","cited_by_count":1,"area":null},{"id":"2102.13329","title":"Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2106.04776","title":"Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2107.07713","title":"Towards an Interpretable Latent Space in Structured Models for Video Prediction","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2204.02494","title":"Leveraging Disentangled Representations to Improve Vision-Based Keystroke Inference Attacks Under Low Data","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2209.07699","title":"Graph Contrastive Learning with Cross-view Reconstruction","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2210.04023","title":"Multi-Task Dynamical Systems","created":"2022-10-08","cited_by_count":1,"area":null},{"id":"2310.05829","title":"USTEP: Spatio-Temporal Predictive Learning under A Unified View","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2403.17530","title":"Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classification","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2406.13317","title":"M4Fog: A Global Multi-Regional, Multi-Modal, and Multi-Stage Dataset for Marine Fog Detection and Forecasting to Bridge Ocean and Atmosphere","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2509.21783","title":"Prompt-guided Disentangled Representation for Action Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.17313","title":"Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2105.11062","title":"Taylor saves for later: disentanglement for video prediction using Taylor representation","created":"2021-05-24","cited_by_count":0,"area":null},{"id":"2106.03502","title":"Efficient training for future video generation based on hierarchical disentangled representation of latent variables","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2108.04899","title":"Analysis of ODE2VAE with Examples","created":"2021-08-10","cited_by_count":0,"area":null}],"next_cursor":"100"}