{"total":139,"rows":[{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658,"area":"wm"},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625,"area":"diffusion"},{"id":"2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","created":"2021-06-01","cited_by_count":224,"area":null},{"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":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175,"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":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125,"area":null},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116,"area":null},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2202.04770","title":"Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion","created":"2022-02-08","cited_by_count":96,"area":null},{"id":"2203.14954","title":"GIRAFFE HD: A High-Resolution 3D-aware Generative Model","created":"2022-03-28","cited_by_count":86,"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":"2106.01534","title":"Deconfounded Video Moment Retrieval with Causal Intervention","created":"2021-06-03","cited_by_count":84,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"area":null},{"id":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65,"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":"2211.14575","title":"Efficient Video Prediction via Sparsely Conditioned Flow Matching","created":"2022-11-26","cited_by_count":55,"area":"diffusion"},{"id":"2102.09546","title":"Deep Gait Recognition: A Survey","created":"2021-02-18","cited_by_count":54,"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":"2107.07224","title":"StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN","created":"2021-07-15","cited_by_count":47,"area":null},{"id":"2205.09928","title":"Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer","created":"2022-05-20","cited_by_count":47,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45,"area":"wm"},{"id":"2403.14148","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","created":"2024-03-21","cited_by_count":42,"area":"diffusion"},{"id":"2305.03989","title":"LEO: Generative Latent Image Animator for Human Video Synthesis","created":"2023-05-06","cited_by_count":40,"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":"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":"2104.10066","title":"EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task","created":"2021-04-16","cited_by_count":34,"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":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","cited_by_count":34,"area":null},{"id":"2106.15610","title":"An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild","created":"2021-06-29","cited_by_count":30,"area":null},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2303.17264","title":"Multifactor Sequential Disentanglement via Structured Koopman Autoencoders","created":"2023-03-30","cited_by_count":24,"area":null},{"id":"2108.01069","title":"Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning","created":"2021-08-02","cited_by_count":23,"area":"offlinerl"},{"id":"2101.07496","title":"Disentangled Recurrent Wasserstein Autoencoder","created":"2021-01-19","cited_by_count":22,"area":null},{"id":"2102.11456","title":"Representation Disentanglement for Multi-modal brain MR Analysis","created":"2021-02-23","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":"2310.18615","title":"Temporally Disentangled Representation Learning under Unknown Nonstationarity","created":"2023-10-28","cited_by_count":22,"area":null},{"id":"2111.10202","title":"Multimodal Emotion Recognition with High-level Speech and Text Features","created":"2021-09-29","cited_by_count":20,"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":"2304.10278","title":"Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis","created":"2023-04-20","cited_by_count":18,"area":"diffusion"},{"id":"2308.16154","title":"MMVP: Motion-Matrix-based Video Prediction","created":"2023-08-30","cited_by_count":18,"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":"2103.14017","title":"Scaling-up Disentanglement for Image Translation","created":"2021-03-25","cited_by_count":15,"area":null},{"id":"2107.06941","title":"Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation","created":"2021-07-14","cited_by_count":15,"area":null},{"id":"2111.06925","title":"Action2video: Generating Videos of Human 3D Actions","created":"2021-11-12","cited_by_count":15,"area":null},{"id":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2104.02687","title":"Strumming to the Beat: Audio-Conditioned Contrastive Video Textures","created":"2021-04-06","cited_by_count":14,"area":null},{"id":"2202.00368","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2203.11284","title":"A Contrastive Objective for Learning Disentangled Representations","created":"2022-03-21","cited_by_count":14,"area":null},{"id":"2410.23996","title":"An Information Criterion for Controlled Disentanglement of Multimodal Data","created":"2024-10-31","cited_by_count":14,"area":null},{"id":"2502.12632","title":"MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation","created":"2025-02-18","cited_by_count":14,"area":"diffusion"},{"id":"2112.10082","title":"MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks","created":"2021-12-19","cited_by_count":13,"area":null},{"id":"2212.06026","title":"Video Prediction by Efficient Transformers","created":"2022-12-12","cited_by_count":12,"area":null},{"id":"2103.10308","title":"Future Frame Prediction for Robot-assisted Surgery","created":"2021-03-18","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":"2210.07181","title":"MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2402.02346","title":"Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback","created":"2024-02-04","cited_by_count":9,"area":"diffusion"},{"id":"1907.13627","title":"Disentangled Relational Representations for Explaining and Learning from Demonstration","created":"2019-07-31","cited_by_count":8,"area":"offlinerl"},{"id":"2102.10544","title":"Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement","created":"2021-02-21","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":"2401.14718","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","created":"2024-01-26","cited_by_count":7,"area":"wm"},{"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":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2103.07292","title":"VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts","created":"2021-03-12","cited_by_count":6,"area":"moe"},{"id":"2205.05871","title":"Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2105.02799","title":"Object-centric Video Prediction without Annotation","created":"2021-05-06","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":"2208.02724","title":"Disentangled Representation Learning for RF Fingerprint Extraction under Unknown Channel Statistics","created":"2022-08-04","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":"2311.04833","title":"Anonymizing medical case-based explanations through disentanglement","created":"2023-11-08","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":"2110.03882","title":"ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning","created":"2021-10-08","cited_by_count":4,"area":null},{"id":"2211.02707","title":"Contrastive Learning for Diverse Disentangled Foreground Generation","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2308.12696","title":"Disentanglement Learning via Topology","created":"2023-08-24","cited_by_count":4,"area":null},{"id":"2408.05599","title":"Sequential Representation Learning via Static-Dynamic Conditional Disentanglement","created":"2024-08-10","cited_by_count":4,"area":null},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2102.00324","title":"Video Reenactment as Inductive Bias for Content-Motion Disentanglement","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2103.03240","title":"Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision","created":"2021-03-04","cited_by_count":3,"area":null},{"id":"2104.02052","title":"Generating Furry Cars: Disentangling Object Shape & Appearance across Multiple Domains","created":"2021-04-05","cited_by_count":3,"area":null},{"id":"2105.12774","title":"DSLR: Dynamic to Static LiDAR Scan Reconstruction Using Adversarially Trained Autoencoder","created":"2021-05-26","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":"2606.04432","title":"DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation","created":"2026-06-03","cited_by_count":3,"area":"diffusion"},{"id":"2103.06501","title":"Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement","created":"2021-03-11","cited_by_count":2,"area":null},{"id":"2108.13258","title":"Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation","created":"2021-08-30","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":"2211.12829","title":"Unsupervised 3D Keypoint Discovery with Multi-View Geometry","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2303.05166","title":"TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2309.11667","title":"Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2312.07051","title":"Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2410.05564","title":"Unsupervised Representation Learning from Sparse Transformation Analysis","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.11281","title":"DynaCLR: Contrastive Learning of Cellular Dynamics with Temporal Regularization","created":"2024-10-15","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":"2510.21706","title":"Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2603.25931","title":"DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation","created":"2026-03-26","cited_by_count":2,"area":"diffusion"}],"next_cursor":"100"}