{"total":75,"rows":[{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","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":"2103.12902","title":"Region Similarity Representation Learning","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"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":"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":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2203.13641","title":"StretchBEV: Stretching Future Instance Prediction Spatially and Temporally","created":"2022-03-25","cited_by_count":47,"area":null},{"id":"2112.03051","title":"Controllable Animation of Fluid Elements in Still Images","created":"2021-12-06","cited_by_count":45,"area":null},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38,"area":null},{"id":"2309.16118","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","created":"2023-09-28","cited_by_count":35,"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":"2108.02760","title":"SLAMP: Stochastic Latent Appearance and Motion Prediction","created":"2021-08-05","cited_by_count":32,"area":null},{"id":"2106.07643","title":"Unsupervised Learning of Visual 3D Keypoints for Control","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2102.11811","title":"Dynamic Neural Garments","created":"2021-02-23","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":"2304.13723","title":"A Control-Centric Benchmark for Video Prediction","created":"2023-04-26","cited_by_count":25,"area":null},{"id":"2104.06697","title":"Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction","created":"2021-04-14","cited_by_count":23,"area":null},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23,"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":"2312.13604","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos","created":"2023-12-21","cited_by_count":21,"area":null},{"id":"2309.05098","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","created":"2023-09-10","cited_by_count":20,"area":null},{"id":"2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","created":"2021-12-02","cited_by_count":19,"area":null},{"id":"2205.15821","title":"Unsupervised Image Representation Learning with Deep Latent Particles","created":"2022-05-31","cited_by_count":19,"area":null},{"id":"2306.05957","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","created":"2023-06-09","cited_by_count":19,"area":null},{"id":"2205.10636","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","created":"2022-05-21","cited_by_count":17,"area":null},{"id":"2404.13474","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","created":"2024-04-20","cited_by_count":16,"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":"2107.13170","title":"Accurate Grid Keypoint Learning for Efficient Video Prediction","created":"2021-07-28","cited_by_count":13,"area":null},{"id":"2303.03684","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","created":"2023-03-07","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":"2210.07181","title":"MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2108.05658","title":"Conditional Temporal Variational AutoEncoder for Action Video Prediction","created":"2021-08-12","cited_by_count":9,"area":null},{"id":"2104.04275","title":"GATSBI: Generative Agent-centric Spatio-temporal Object Interaction","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2203.10528","title":"Stochastic Video Prediction with Structure and Motion","created":"2022-03-20","cited_by_count":8,"area":null},{"id":"2111.01604","title":"A Critical Study on the Recent Deep Learning Based Semi-Supervised Video Anomaly Detection Methods","created":"2021-11-02","cited_by_count":7,"area":null},{"id":"2106.09051","title":"Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure","created":"2021-06-16","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":"2210.07697","title":"Multi-Task Learning based Video Anomaly Detection with Attention","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2303.17216","title":"Few-shot Geometry-Aware Keypoint Localization","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2511.07409","title":"DIMO: Diverse 3D Motion Generation for Arbitrary Objects","created":"2025-11-10","cited_by_count":6,"area":null},{"id":"2109.05928","title":"Vision-based system identification and 3D keypoint discovery using dynamics constraints","created":"2021-09-13","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":"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":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2211.06027","title":"Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2405.10598","title":"Top-Down Guidance for Learning Object-Centric Representations","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2202.08418","title":"Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2212.04741","title":"Physically Plausible Animation of Human Upper Body from a Single Image","created":"2022-12-09","cited_by_count":2,"area":null},{"id":"2310.04617","title":"SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2408.08108","title":"Unsupervised Part Discovery via Dual Representation Alignment","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2504.05537","title":"Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling","created":"2025-04-07","cited_by_count":2,"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":"2106.07995","title":"Learning of feature points without additional supervision improves reinforcement learning from images","created":"2021-06-15","cited_by_count":1,"area":null},{"id":"2202.09006","title":"KINet: Unsupervised Forward Models for Robotic Pushing Manipulation","created":"2022-02-18","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":"2210.08391","title":"Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy","created":"2022-10-15","cited_by_count":1,"area":null},{"id":"2303.09807","title":"TKN: Transformer-based Keypoint Prediction Network For Real-time Video Prediction","created":"2023-03-17","cited_by_count":1,"area":null},{"id":"2403.10079","title":"Learning Physical Dynamics for Object-centric Visual Prediction","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2403.11337","title":"Enhancing Bandwidth Efficiency for Video Motion Transfer Applications using Deep Learning Based Keypoint Prediction","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2107.10068","title":"From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting","created":"2021-07-21","cited_by_count":0,"area":null},{"id":"2205.01924","title":"Zero-Episode Few-Shot Contrastive Predictive Coding: Solving intelligence tests without prior training","created":"2022-05-04","cited_by_count":0,"area":null},{"id":"2206.03061","title":"Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2206.11030","title":"KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images","created":"2022-06-22","cited_by_count":0,"area":null},{"id":"2206.14802","title":"Visual Foresight With a Local Dynamics Model","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2209.15404","title":"Entropy-driven Unsupervised Keypoint Representation Learning in Videos","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2312.00592","title":"Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version)","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2410.05882","title":"Frame forecasting in cine MRI using the PCA respiratory motion model: comparing recurrent neural networks trained online and transformers","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2601.08278","title":"One-Shot Identification with Different Neural Network Approaches","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2607.15400","title":"Unsupervised Keypoints for Real-Time Fall Detection: Comparative Analysis Under Real-world Conditions with Predictive Bandwidth Reduction","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.19463","title":"ParticleSplat: Self-supervised Object-centric Latent Particle Splatting","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}