{"total":271,"rows":[{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152,"area":null},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75,"area":"offlinerl"},{"id":"2102.06828","title":"Domain Adaptation for Time Series Forecasting via Attention Sharing","created":"2021-02-13","cited_by_count":68,"area":null},{"id":"2206.03287","title":"NeMF: Neural Motion Fields for Kinematic Animation","created":"2022-06-04","cited_by_count":68,"area":null},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2306.09368","title":"Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Series","created":"2023-06-14","cited_by_count":55,"area":null},{"id":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48,"area":null},{"id":"2306.01439","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2510.23672","title":"DBLoss: Decomposition-based Loss Function for Time Series Forecasting","created":"2025-10-27","cited_by_count":45,"area":null},{"id":"2105.05217","title":"Representation Learning via Global Temporal Alignment and Cycle-Consistency","created":"2021-05-11","cited_by_count":44,"area":null},{"id":"2108.11996","title":"Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers","created":"2021-08-26","cited_by_count":39,"area":null},{"id":"2102.06555","title":"Online Graph Dictionary Learning","created":"2021-02-12","cited_by_count":37,"area":null},{"id":"2304.13265","title":"StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos","created":"2023-04-26","cited_by_count":37,"area":null},{"id":"2503.00877","title":"Patch-wise Structural Loss for Time Series Forecasting","created":"2025-03-02","cited_by_count":35,"area":null},{"id":"2401.16702","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","created":"2024-01-30","cited_by_count":34,"area":null},{"id":"2203.16800","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","created":"2022-03-31","cited_by_count":33,"area":null},{"id":"2303.05095","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","created":"2023-03-09","cited_by_count":26,"area":null},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2203.16784","title":"Video-Text Representation Learning via Differentiable Weak Temporal Alignment","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2103.09458","title":"Learning Discriminative Prototypes with Dynamic Time Warping","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2103.13922","title":"ScanGAN360: A Generative Model of Realistic Scanpaths for 360$^{\\circ}$ Images","created":"2021-03-25","cited_by_count":23,"area":null},{"id":"2207.10785","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2410.01506","title":"Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22,"area":null},{"id":"2505.17847","title":"Time-o1: Time-Series Forecasting Needs Transformed Label Alignment","created":"2025-05-23","cited_by_count":22,"area":null},{"id":"2110.05651","title":"Learning with Algorithmic Supervision via Continuous Relaxations","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2211.00005","title":"Uncertainty-DTW for Time Series and Sequences","created":"2022-10-30","cited_by_count":21,"area":null},{"id":"2406.09794","title":"SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis","created":"2024-06-14","cited_by_count":19,"area":null},{"id":"2106.10272","title":"Riemannian Convex Potential Maps","created":"2021-06-18","cited_by_count":17,"area":null},{"id":"2108.06090","title":"SVC-onGoing: Signature Verification Competition","created":"2021-08-13","cited_by_count":17,"area":null},{"id":"2411.00304","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","created":"2024-11-01","cited_by_count":15,"area":"mllm"},{"id":"2202.11485","title":"Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences","created":"2022-02-17","cited_by_count":14,"area":null},{"id":"2305.16358","title":"Differentiable Clustering with Perturbed Spanning Forests","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2104.02577","title":"Learnable Dynamic Temporal Pooling for Time Series Classification","created":"2021-04-02","cited_by_count":13,"area":null},{"id":"2201.01413","title":"Towards Similarity-Aware Time-Series Classification","created":"2022-01-05","cited_by_count":13,"area":null},{"id":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2505.13820","title":"Structured Agent Distillation for Large Language Model","created":"2025-05-20","cited_by_count":13,"area":"agents"},{"id":"2510.24574","title":"DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2307.00928","title":"Learning Differentiable Logic Programs for Abstract Visual Reasoning","created":"2023-07-03","cited_by_count":12,"area":"lr"},{"id":"2102.07005","title":"Clustering Interval-Censored Time-Series for Disease Phenotyping","created":"2021-02-13","cited_by_count":11,"area":null},{"id":"2204.12223","title":"Context-Aware Sequence Alignment using 4D Skeletal Augmentation","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2208.03257","title":"3D Pose Based Feedback for Physical Exercises","created":"2022-08-05","cited_by_count":11,"area":null},{"id":"2503.16832","title":"Joint Self-Supervised Video Alignment and Action Segmentation","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2104.04610","title":"Deep Time Series Forecasting with Shape and Temporal Criteria","created":"2021-04-09","cited_by_count":10,"area":null},{"id":"2112.12668","title":"3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na\\\"ive","created":"2021-12-23","cited_by_count":10,"area":null},{"id":"2402.04599","title":"Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment","created":"2024-02-07","cited_by_count":10,"area":null},{"id":"2508.04045","title":"FeDaL: Federated Dataset Learning for General Time Series Foundation Models","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2511.00053","title":"Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models","created":"2025-10-28","cited_by_count":10,"area":null},{"id":"2210.15879","title":"Complex Handwriting Trajectory Recovery: Evaluation Metrics and Algorithm","created":"2022-10-28","cited_by_count":9,"area":null},{"id":"2211.16049","title":"Evaluating and reducing the distance between synthetic and real speech distributions","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2402.12035","title":"Class-incremental Learning for Time Series: Benchmark and Evaluation","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2502.14676","title":"BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2106.00739","title":"ICDAR 2021 Competition on On-Line Signature Verification","created":"2021-06-01","cited_by_count":8,"area":null},{"id":"2201.11941","title":"Unifying Pairwise Interactions in Complex Dynamics","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2210.15050","title":"TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecasting","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2303.12533","title":"Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach","created":"2023-03-22","cited_by_count":8,"area":null},{"id":"2312.03998","title":"Series2Vec: Similarity-based Self-supervised Representation Learning for Time Series Classification","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2510.25207","title":"Selective Learning for Deep Time Series Forecasting","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2601.02994","title":"Learning to Act Robustly with View-Invariant Latent Actions","created":"2026-01-06","cited_by_count":8,"area":null},{"id":"2108.06816","title":"Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping","created":"2021-08-15","cited_by_count":7,"area":null},{"id":"2206.08107","title":"Closed-Form Diffeomorphic Transformations for Time Series Alignment","created":"2022-06-16","cited_by_count":7,"area":null},{"id":"2305.06114","title":"Few-shot Action Recognition via Intra- and Inter-Video Information Maximization","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2407.01622","title":"Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2110.05728","title":"Rethinking the Spatial Route Prior in Vision-and-Language Navigation","created":"2021-10-12","cited_by_count":6,"area":null},{"id":"2211.10420","title":"Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2309.16353","title":"ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2506.22837","title":"xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection","created":"2025-06-28","cited_by_count":6,"area":null},{"id":"2511.00033","title":"STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization","created":"2025-10-27","cited_by_count":6,"area":null},{"id":"2204.08822","title":"A Convolutional-Attentional Neural Framework for Structure-Aware Performance-Score Synchronization","created":"2022-04-19","cited_by_count":5,"area":null},{"id":"2206.02956","title":"Robust Time Series Dissimilarity Measure for Outlier Detection and Periodicity Detection","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2207.04308","title":"Dynamic Time Warping based Adversarial Framework for Time-Series Domain","created":"2022-07-09","cited_by_count":5,"area":null},{"id":"2302.04856","title":"One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation","created":"2023-02-09","cited_by_count":5,"area":null},{"id":"2303.10778","title":"Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths","created":"2023-03-19","cited_by_count":5,"area":null},{"id":"2308.06443","title":"Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2311.11285","title":"TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2412.07544","title":"Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery","created":"2024-12-10","cited_by_count":5,"area":"offlinerl"},{"id":"2602.21669","title":"DWA-KD: Dual-Space Weighting and Time-Warped Alignment for Cross-Tokenizer Knowledge Distillation","created":"2026-02-25","cited_by_count":5,"area":"distill"},{"id":"2106.11911","title":"Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment","created":"2021-06-22","cited_by_count":4,"area":null},{"id":"2210.03382","title":"Temporal Feature Alignment in Contrastive Self-Supervised Learning for Human Activity Recognition","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2210.04996","title":"Graph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization","created":"2022-10-10","cited_by_count":4,"area":null},{"id":"2211.11650","title":"Neural Meta-Symbolic Reasoning and Learning","created":"2022-11-21","cited_by_count":4,"area":"lr"},{"id":"2304.05032","title":"Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2310.08841","title":"Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments","created":"2023-10-13","cited_by_count":4,"area":"offlinerl"},{"id":"2311.04770","title":"Vital Sign Forecasting for Sepsis Patients in ICUs","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2410.08125","title":"Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2412.00486","title":"Automatic Differentiation-based Full Waveform Inversion with Flexible Workflows","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2507.15540","title":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2608.01857","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","created":"2026-08-03","cited_by_count":4,"area":null},{"id":"2104.00705","title":"Multi-rate attention architecture for fast streamable Text-to-speech spectrum modeling","created":"2021-04-01","cited_by_count":3,"area":null},{"id":"2301.04525","title":"Clustering disease trajectories in contrastive feature space for biomarker discovery in age-related macular degeneration","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2302.04064","title":"Weakly-supervised Representation Learning for Video Alignment and Analysis","created":"2023-02-08","cited_by_count":3,"area":null},{"id":"2305.19480","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2307.03461","title":"A Deep Active Contour Model for Delineating Glacier Calving Fronts","created":"2023-07-07","cited_by_count":3,"area":null},{"id":"2311.05144","title":"Counter-Empirical Attacking based on Adversarial Reinforcement Learning for Time-Relevant Scoring System","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2312.17330","title":"Count What You Want: Exemplar Identification and Few-shot Counting of Human Actions in the Wild","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2403.06260","title":"SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations","created":"2024-03-10","cited_by_count":3,"area":null},{"id":"2409.01448","title":"FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition","created":"2024-09-02","cited_by_count":3,"area":null}],"next_cursor":"100"}