{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-prediction/papers/3","list_of":"/task/video-prediction","task":"Video Prediction","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":394,"counts":{"archive_papers_tagged":394,"with_a_code_link":208,"where_syntology_ran_a_sample":62,"not_listed_spam_title":0,"listed":394,"listed_where_code_ran":62,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":58,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":58,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-prediction","prev":"/task/video-prediction/papers/2","next":"/task/video-prediction/papers/4","papers":[{"url":"/paper/prediction-under-uncertainty-with-error","slug":"prediction-under-uncertainty-with-error","title":"Prediction Under Uncertainty with Error-Encoding Networks","date":"2017-11-14","arxiv_id":"1711.04994","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-from-observation-learning-to","slug":"imitation-from-observation-learning-to","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","date":"2017-07-11","arxiv_id":"1707.03374","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-motion-and-content-for-natural","slug":"decomposing-motion-and-content-for-natural","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","date":"2017-06-25","arxiv_id":"1706.08033","repositories_listed":1,"syntology":null},{"url":"/paper/the-pose-knows-video-forecasting-by","slug":"the-pose-knows-video-forecasting-by","title":"The Pose Knows: Video Forecasting by Generating Pose Futures","date":"2017-04-28","arxiv_id":"1705.00053","repositories_listed":1,"syntology":null},{"url":"/paper/deep-visual-foresight-for-planning-robot","slug":"deep-visual-foresight-for-planning-robot","title":"Deep Visual Foresight for Planning Robot Motion","date":"2016-10-03","arxiv_id":"1610.00696","repositories_listed":1,"syntology":null},{"url":"/paper/video-pixel-networks","slug":"video-pixel-networks","title":"Video Pixel Networks","date":"2016-10-03","arxiv_id":"1610.00527","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-filter-networks","slug":"dynamic-filter-networks","title":"Dynamic Filter Networks","date":"2016-05-31","arxiv_id":"1605.09673","repositories_listed":1,"syntology":null},{"url":"/paper/action-conditional-video-prediction-using","slug":"action-conditional-video-prediction-using","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","date":"2015-07-31","arxiv_id":"1507.08750","repositories_listed":1,"syntology":null},{"url":null,"slug":"whole-body-conditioned-egocentric-video","title":"Whole-Body Conditioned Egocentric Video Prediction","date":"2025-06-26","arxiv_id":"2506.21552","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-unified-visual-imagination-and-control","title":"MinD: Unified Visual Imagination and Control via Hierarchical World Models","date":"2025-06-23","arxiv_id":"2506.18897","repositories_listed":0,"syntology":null},{"url":null,"slug":"amplify-actionless-motion-priors-for-robot","title":"AMPLIFY: Actionless Motion Priors for Robot Learning from Videos","date":"2025-06-17","arxiv_id":"2506.14198","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-generalizable-bimanual-foundation","title":"Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction","date":"2025-05-30","arxiv_id":"2505.24156","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistent-world-models-via-foresight","title":"Consistent World Models via Foresight Diffusion","date":"2025-05-22","arxiv_id":"2505.16474","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowdreamer-a-rgb-d-world-model-with-flow","title":"FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation","date":"2025-05-15","arxiv_id":"2505.10075","repositories_listed":0,"syntology":null},{"url":null,"slug":"egoexo-gen-ego-centric-video-prediction-by","title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","date":"2025-04-16","arxiv_id":"2504.11732","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-streaming-video-with-orthogonal","title":"Learning from Streaming Video with Orthogonal Gradients","date":"2025-04-02","arxiv_id":"2504.01961","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-video-prediction-with-fast-video","title":"Real-time Video Prediction With Fast Video Interpolation Model and Prediction Training","date":"2025-03-29","arxiv_id":"2503.23185","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracktention-leveraging-point-tracking-to","title":"Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better","date":"2025-03-25","arxiv_id":"2503.19904","repositories_listed":0,"syntology":null},{"url":null,"slug":"aether-geometric-aware-unified-world-modeling","title":"Aether: Geometric-Aware Unified World Modeling","date":"2025-03-24","arxiv_id":"2503.18945","repositories_listed":0,"syntology":null},{"url":null,"slug":"frame-wise-conditioning-adaptation-for-fine","title":"Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction","date":"2025-03-17","arxiv_id":"2503.12953","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangled-world-models-learning-to","title":"Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning","date":"2025-03-11","arxiv_id":"2503.08751","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-video-action-model","title":"Unified Video Action Model","date":"2025-02-28","arxiv_id":"2503.00200","repositories_listed":0,"syntology":null},{"url":null,"slug":"skillful-nowcasting-of-convective-clouds-with","title":"Skillful Nowcasting of Convective Clouds With a Cascade Diffusion Model","date":"2025-02-16","arxiv_id":"2502.10957","repositories_listed":0,"syntology":null},{"url":null,"slug":"maucell-an-adaptive-multi-attention-framework","title":"MAUCell: An Adaptive Multi-Attention Framework for Video Frame Prediction","date":"2025-01-28","arxiv_id":"2501.16997","repositories_listed":0,"syntology":null},{"url":null,"slug":"taming-teacher-forcing-for-masked","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","date":"2025-01-21","arxiv_id":"2501.12389","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-benefits-of-instance-decomposition-in","title":"On the Benefits of Instance Decomposition in Video Prediction Models","date":"2025-01-17","arxiv_id":"2501.10562","repositories_listed":0,"syntology":null},{"url":null,"slug":"stiv-scalable-text-and-image-conditioned","title":"STIV: Scalable Text and Image Conditioned Video Generation","date":"2024-12-10","arxiv_id":"2412.07730","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-continuous-video-flow-model-for","title":"Efficient Continuous Video Flow Model for Video Prediction","date":"2024-12-07","arxiv_id":"2412.05633","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-video-process-modeling-videos-as","title":"Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction","date":"2024-12-06","arxiv_id":"2412.04929","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-stochastic-video-prediction-via","title":"Lightweight Stochastic Video Prediction via Hybrid Warping","date":"2024-12-04","arxiv_id":"2412.03061","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-solar-generation-forecasting","title":"Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction","date":"2024-11-17","arxiv_id":"2411.10921","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-visual-dynamics-representations","title":"Pre-trained Visual Dynamics Representations for Efficient Policy Learning","date":"2024-11-05","arxiv_id":"2411.03169","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-prediction-using-score-based","title":"Video prediction using score-based conditional density estimation","date":"2024-10-30","arxiv_id":"2411.00842","repositories_listed":0,"syntology":null},{"url":null,"slug":"ghil-glue-hierarchical-control-with-filtered","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","date":"2024-10-26","arxiv_id":"2410.20018","repositories_listed":0,"syntology":null},{"url":"/paper/simpler-diffusion-sid2-1-5-fid-on-imagenet512","slug":"simpler-diffusion-sid2-1-5-fid-on-imagenet512","title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","date":"2024-10-25","arxiv_id":"2410.19324","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-3d-gaussian-tracking-for-graph-based","title":"Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling","date":"2024-10-24","arxiv_id":"2410.18912","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-temporal-consistency-via","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","date":"2024-10-21","arxiv_id":"2410.15728","repositories_listed":0,"syntology":null},{"url":null,"slug":"eva-an-embodied-world-model-for-future-video","title":"EVA: An Embodied World Model for Future Video Anticipation","date":"2024-10-20","arxiv_id":"2410.15461","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-uncertainty-aware-forecasting-of","title":"Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery","date":"2024-10-14","arxiv_id":"2410.19782","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-generative-priors-improve-world-models","title":"Masked Generative Priors Improve World Models Sequence Modelling Capabilities","date":"2024-10-10","arxiv_id":"2410.07836","repositories_listed":0,"syntology":null},{"url":null,"slug":"causalve-face-video-privacy-encryption-via","title":"CausalVE: Face Video Privacy Encryption via Causal Video Prediction","date":"2024-09-28","arxiv_id":"2409.19306","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen2act-human-video-generation-in-novel","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","date":"2024-09-24","arxiv_id":"2409.16283","repositories_listed":0,"syntology":null},{"url":null,"slug":"prospective-messaging-learning-in-networks","title":"Prospective Messaging: Learning in Networks with Communication Delays","date":"2024-07-07","arxiv_id":"2407.05494","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-video-prediction-with-explicit","title":"Guiding Video Prediction with Explicit Procedural Knowledge","date":"2024-06-26","arxiv_id":"2406.18220","repositories_listed":0,"syntology":null},{"url":null,"slug":"vipro-enabling-and-controlling-video","title":"ViPro: Enabling and Controlling Video Prediction for Complex Dynamical Scenarios using Procedural Knowledge","date":"2024-06-26","arxiv_id":"2407.09537","repositories_listed":0,"syntology":null},{"url":null,"slug":"financial-assets-dependency-prediction","title":"Financial Assets Dependency Prediction Utilizing Spatiotemporal Patterns","date":"2024-06-13","arxiv_id":"2406.11886","repositories_listed":0,"syntology":null},{"url":null,"slug":"aid-adapting-image2video-diffusion-models-for","title":"AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction","date":"2024-06-10","arxiv_id":"2406.06465","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussianprediction-dynamic-3d-gaussian","title":"GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis","date":"2024-05-30","arxiv_id":"2405.19745","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-prediction-models-as-general-visual","title":"Video Prediction Models as General Visual Encoders","date":"2024-05-25","arxiv_id":"2405.16382","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-spatiotemporal-prediction-using","title":"Enhanced Spatiotemporal Prediction Using Physical-guided And Frequency-enhanced Recurrent Neural Networks","date":"2024-05-23","arxiv_id":"2405.14504","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidu-a-highly-consistent-dynamic-and-skilled","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","date":"2024-05-07","arxiv_id":"2405.04233","repositories_listed":0,"syntology":null},{"url":null,"slug":"101-billion-arabic-words-dataset","title":"101 Billion Arabic Words Dataset","date":"2024-04-29","arxiv_id":"2405.01590","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-long-horizon-futures-by","title":"Predicting Long-horizon Futures by Conditioning on Geometry and Time","date":"2024-04-17","arxiv_id":"2404.11554","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-space-decomposition-model-for-video","title":"State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend","date":"2024-04-17","arxiv_id":"2404.11576","repositories_listed":0,"syntology":null},{"url":null,"slug":"taformer-a-unified-target-aware-transformer","title":"TAFormer: A Unified Target-Aware Transformer for Video and Motion Joint Prediction in Aerial Scenes","date":"2024-03-27","arxiv_id":"2403.18238","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-forecasting-with-stochastic","title":"Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes","date":"2024-03-20","arxiv_id":"2403.13724","repositories_listed":0,"syntology":null},{"url":null,"slug":"carbonnet-how-computer-vision-plays-a-role-in","title":"CarbonNet: How Computer Vision Plays a Role in Climate Change? Application: Learning Geomechanics from Subsurface Geometry of CCS to Mitigate Global Warming","date":"2024-03-09","arxiv_id":"2403.06025","repositories_listed":0,"syntology":null},{"url":null,"slug":"rolling-diffusion-models","title":"Rolling Diffusion Models","date":"2024-02-12","arxiv_id":"2402.09470","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-future-with-simple-world","title":"Simplifying Latent Dynamics with Softly State-Invariant World Models","date":"2024-01-31","arxiv_id":"2401.17835","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-video-prediction-from","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","date":"2024-01-26","arxiv_id":"2401.14718","repositories_listed":0,"syntology":null},{"url":null,"slug":"key-point-guided-deformable-image","title":"Key-point Guided Deformable Image Manipulation Using Diffusion Model","date":"2024-01-16","arxiv_id":"2401.08178","repositories_listed":0,"syntology":null},{"url":null,"slug":"extdm-distribution-extrapolation-diffusion","title":"ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"video-prediction-by-modeling-videos-as","title":"Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-3d-particle-based-simulators-from","title":"Learning 3D Particle-based Simulators from RGB-D Videos","date":"2023-12-08","arxiv_id":"2312.05359","repositories_listed":0,"syntology":null},{"url":null,"slug":"vip-mixer-a-convolutional-mixer-for-video","title":"SIAM: A Simple Alternating Mixer for Video Prediction","date":"2023-11-20","arxiv_id":"2311.11683","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-inference-for-sdes-driven-by","title":"Variational Inference for SDEs Driven by Fractional Noise","date":"2023-10-19","arxiv_id":"2310.12975","repositories_listed":0,"syntology":null},{"url":null,"slug":"future-video-prediction-from-a-single-frame","title":"Future Video Prediction from a Single Frame for Video Anomaly Detection","date":"2023-08-15","arxiv_id":"2308.07783","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-hr-vqvae-sequential-hierarchical-residual","title":"S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction","date":"2023-07-13","arxiv_id":"2307.06701","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-conditioned-deep-visual-prediction","title":"Action-conditioned Deep Visual Prediction with RoAM, a new Indoor Human Motion Dataset for Autonomous Robots","date":"2023-06-28","arxiv_id":"2306.15852","repositories_listed":0,"syntology":null},{"url":"/paper/physion-evaluating-physical-scene","slug":"physion-evaluating-physical-scene","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","date":"2023-06-27","arxiv_id":"2306.15668","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/physion-evaluating-physical-scene#ran","syntology_url":"https://syntology.ai/paper/2306.15668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15668"}},"official":null}},{"url":null,"slug":"slotdiffusion-object-centric-generative-1","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","date":"2023-05-18","arxiv_id":"2305.11281","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-vision-and-tactile-sensation-for","title":"Combining Vision and Tactile Sensation for Video Prediction","date":"2023-04-21","arxiv_id":"2304.11193","repositories_listed":0,"syntology":null},{"url":null,"slug":"ms-lstm-exploring-spatiotemporal-multiscale","title":"MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain","date":"2023-04-16","arxiv_id":"2304.07724","repositories_listed":0,"syntology":null},{"url":null,"slug":"tkn-transformer-based-keypoint-prediction","title":"TKN: Transformer-based Keypoint Prediction Network For Real-time Video Prediction","date":"2023-03-17","arxiv_id":"2303.09807","repositories_listed":0,"syntology":null},{"url":null,"slug":"allo-centric-occupancy-grid-prediction-for","title":"Allo-centric Occupancy Grid Prediction for Urban Traffic Scene Using Video Prediction Networks","date":"2023-01-11","arxiv_id":"2301.04454","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-horizon-video-prediction-using-a-dynamic","title":"Long-horizon video prediction using a dynamic latent hierarchy","date":"2022-12-29","arxiv_id":"2212.14376","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-and-context-aware-audio-visual","title":"Motion and Context-Aware Audio-Visual Conditioned Video Prediction","date":"2022-12-09","arxiv_id":"2212.04679","repositories_listed":0,"syntology":null},{"url":null,"slug":"randomized-conditional-flow-matching-for","title":"Efficient Video Prediction via Sparsely Conditioned Flow Matching","date":"2022-11-26","arxiv_id":"2211.14575","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-plan-predict-language-guided-cognitive","title":"See, Plan, Predict: Language-guided Cognitive Planning with Video Prediction","date":"2022-10-07","arxiv_id":"2210.03825","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-driven-video-prediction","title":"Text-driven Video Prediction","date":"2022-10-06","arxiv_id":"2210.02872","repositories_listed":0,"syntology":null},{"url":null,"slug":"harp-autoregressive-latent-video-prediction","title":"HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator","date":"2022-09-15","arxiv_id":"2209.07143","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-motion-planning-as-video-prediction-a","title":"Robot Motion Planning as Video Prediction: A Spatio-Temporal Neural Network-based Motion Planner","date":"2022-08-24","arxiv_id":"2208.11287","repositories_listed":0,"syntology":null},{"url":null,"slug":"wildfire-forecasting-with-satellite-images","title":"Wildfire Forecasting with Satellite Images and Deep Generative Model","date":"2022-08-19","arxiv_id":"2208.09411","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskvit-masked-visual-pre-training-for-video","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","date":"2022-06-23","arxiv_id":"2206.11894","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-spatio-temporal-forecasting","title":"Deep learning for spatio-temporal forecasting -- application to solar energy","date":"2022-05-07","arxiv_id":"2205.03571","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-extrapolationin-space-and-time","title":"Video Extrapolation in Space and Time","date":"2022-05-04","arxiv_id":"2205.02084","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-episode-few-shot-contrastive-predictive","title":"Zero-Episode Few-Shot Contrastive Predictive Coding: Solving intelligence tests without prior training","date":"2022-05-04","arxiv_id":"2205.01924","repositories_listed":0,"syntology":null},{"url":null,"slug":"stau-a-spatiotemporal-aware-unit-for-video","title":"STAU: A SpatioTemporal-Aware Unit for Video Prediction and Beyond","date":"2022-04-20","arxiv_id":"2204.09456","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-video-prediction-with-structure","title":"Stochastic Video Prediction with Structure and Motion","date":"2022-03-20","arxiv_id":"2203.10528","repositories_listed":0,"syntology":null},{"url":null,"slug":"filtered-cophy-unsupervised-learning-of-1","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","date":"2022-02-01","arxiv_id":"2202.00368","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-network-applications","title":"Generative Adversarial Network Applications in Creating a Meta-Universe","date":"2022-01-23","arxiv_id":"2201.09152","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-local-optimality-for-video","title":"Generalized Local Optimality for Video Steganalysis in Motion Vector Domain","date":"2021-12-22","arxiv_id":"2112.11729","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-visual-reasoning-on-rpms-with-an","title":"Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction","date":"2021-11-24","arxiv_id":"2111.12301","repositories_listed":0,"syntology":null},{"url":null,"slug":"wide-and-narrow-video-prediction-from-context","title":"Wide and Narrow: Video Prediction from Context and Motion","date":"2021-10-22","arxiv_id":"2110.11586","repositories_listed":0,"syntology":null},{"url":null,"slug":"fourier-based-video-prediction-through","title":"Fourier-based Video Prediction through Relational Object Motion","date":"2021-10-12","arxiv_id":"2110.05881","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-variational-neural-uncertainty-1","title":"A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction","date":"2021-10-06","arxiv_id":"2110.03446","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-latent-video-prediction-with","title":"Autoregressive Latent Video Prediction with High-Fidelity Image Generator","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cdnet-a-cascaded-decoupling-architecture-for","title":"CDNet: A cascaded decoupling architecture for video prediction","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fitvid-high-capacity-pixel-level-video","title":"FitVid: High-Capacity Pixel-Level Video Prediction","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"object-dynamics-distillation-for-scene","title":"OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"d42f72bc4cf124f1117f3ee7f369069543bbaba6b6b37e08fcfc2c0e1e88fd91","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}