{"total":188,"rows":[{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692,"area":null},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500,"area":null},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142,"area":null},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2103.09712","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","created":"2021-03-17","cited_by_count":94,"area":null},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91,"area":null},{"id":"2301.03028","title":"Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement","created":"2023-01-08","cited_by_count":90,"area":null},{"id":"2110.05266","title":"Chaos as an interpretable benchmark for forecasting and data-driven modelling","created":"2021-10-11","cited_by_count":88,"area":null},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68,"area":null},{"id":"2305.08989","title":"LoViT: Long Video Transformer for Surgical Phase Recognition","created":"2023-05-15","cited_by_count":56,"area":null},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","cited_by_count":56,"area":null},{"id":"2203.08321","title":"ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data","created":"2022-03-15","cited_by_count":45,"area":null},{"id":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","cited_by_count":43,"area":null},{"id":"2102.12218","title":"Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2302.06492","title":"Optical flow estimation from event-based cameras and spiking neural networks","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2401.13912","title":"A Survey of Deep Learning and Foundation Models for Time Series Forecasting","created":"2024-01-25","cited_by_count":33,"area":null},{"id":"2106.12271","title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2303.08011","title":"Model scale versus domain knowledge in statistical forecasting of chaotic systems","created":"2023-03-13","cited_by_count":27,"area":null},{"id":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","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":"2411.02796","title":"Specialized Foundation Models Struggle to Beat Supervised Baselines","created":"2024-11-05","cited_by_count":24,"area":null},{"id":"2102.00027","title":"Gesture Recognition in Robotic Surgery: a Review","created":"2021-01-29","cited_by_count":23,"area":null},{"id":"2303.08356","title":"Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognition","created":"2023-03-15","cited_by_count":20,"area":null},{"id":"2410.16928","title":"xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories","created":"2024-10-22","cited_by_count":19,"area":null},{"id":"2206.03305","title":"Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking","created":"2022-06-07","cited_by_count":18,"area":null},{"id":"2302.11974","title":"LightCTS: A Lightweight Framework for Correlated Time Series Forecasting","created":"2023-02-23","cited_by_count":18,"area":null},{"id":"2305.19591","title":"Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2309.09865","title":"Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight","created":"2023-09-18","cited_by_count":15,"area":null},{"id":"2203.14907","title":"Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices","created":"2022-03-24","cited_by_count":14,"area":null},{"id":"2303.06845","title":"Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals","created":"2023-03-13","cited_by_count":14,"area":null},{"id":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2402.17233","title":"Hybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response","created":"2024-02-27","cited_by_count":13,"area":null},{"id":"2212.01683","title":"Recognition and Prediction of Surgical Gestures and Trajectories Using Transformer Models in Robot-Assisted Surgery","created":"2022-12-03","cited_by_count":12,"area":null},{"id":"2410.01469","title":"TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2308.03805","title":"Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables","created":"2023-08-06","cited_by_count":10,"area":null},{"id":"2412.14435","title":"Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2601.20280","title":"The Forecast After the Forecast: A Post-Processing Shift in Time Series","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2107.05984","title":"Deep Autoregressive Models with Spectral Attention","created":"2021-07-13","cited_by_count":9,"area":null},{"id":"2206.05852","title":"ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths","created":"2022-06-12","cited_by_count":9,"area":null},{"id":"2302.06914","title":"Heterogeneous Anomaly Detection for Software Systems via Semi-supervised Cross-modal Attention","created":"2023-02-14","cited_by_count":9,"area":null},{"id":"2510.18310","title":"Towards Identifiability of Hierarchical Temporal Causal Representation Learning","created":"2025-10-21","cited_by_count":9,"area":null},{"id":"2111.02351","title":"Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators","created":"2021-11-03","cited_by_count":8,"area":null},{"id":"2203.04396","title":"Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring","created":"2022-03-01","cited_by_count":8,"area":null},{"id":"2404.00322","title":"Instrument-tissue Interaction Detection Framework for Surgical Video Understanding","created":"2024-03-30","cited_by_count":8,"area":null},{"id":"2506.06301","title":"Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2508.08551","title":"UQGNN: Uncertainty Quantification of Graph Neural Networks for Multivariate Spatiotemporal Prediction","created":"2025-08-12","cited_by_count":8,"area":null},{"id":"2305.11451","title":"SurgMAE: Masked Autoencoders for Long Surgical Video Analysis","created":"2023-05-19","cited_by_count":7,"area":null},{"id":"2404.11269","title":"DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2504.04495","title":"AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2203.16339","title":"Robust and Energy-efficient PPG-based Heart-Rate Monitoring","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2204.06439","title":"Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation","created":"2022-04-13","cited_by_count":6,"area":null},{"id":"2204.10670","title":"Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention","created":"2022-04-22","cited_by_count":6,"area":null},{"id":"2209.01148","title":"ARST: Auto-Regressive Surgical Transformer for Phase Recognition from Laparoscopic Videos","created":"2022-09-02","cited_by_count":6,"area":null},{"id":"2312.12250","title":"ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2402.03710","title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2403.11440","title":"Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2405.00980","title":"A Hong Kong Sign Language Corpus Collected from Sign-interpreted TV News","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2409.16145","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2501.11899","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","created":"2025-01-21","cited_by_count":6,"area":null},{"id":"2503.09929","title":"Emotion Recognition with CLIP and Sequential Learning","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2105.00460","title":"Surgical Gesture Recognition Based on Bidirectional Multi-Layer Independently RNN with Explainable Spatial Feature Extraction","created":"2021-05-02","cited_by_count":5,"area":null},{"id":"2203.00304","title":"Automatic Depression Detection via Learning and Fusing Features from Visual Cues","created":"2022-03-01","cited_by_count":5,"area":null},{"id":"2207.03348","title":"Human-Robot Commensality: Bite Timing Prediction for Robot-Assisted Feeding in Groups","created":"2022-07-07","cited_by_count":5,"area":null},{"id":"2209.14647","title":"Bounded Future MS-TCN++ for surgical gesture recognition","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2411.18018","title":"Neural Finite-State Machines for Surgical Phase Recognition","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2505.04419","title":"Recognizing Ornaments in Vocal Indian Art Music with Active Annotation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2507.09513","title":"Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining","created":"2025-07-13","cited_by_count":5,"area":null},{"id":"2508.07337","title":"KLASSify to Verify: Audio-Visual Deepfake Detection Using SSL-based Audio and Handcrafted Visual Features","created":"2025-08-10","cited_by_count":5,"area":null},{"id":"2109.00783","title":"Computer Vision Self-supervised Learning Methods on Time Series","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2110.04656","title":"Streaming on-device detection of device directed speech from voice and touch-based invocation","created":"2021-10-09","cited_by_count":4,"area":null},{"id":"2110.14317","title":"Ask \"Who\", Not \"What\": Bitcoin Volatility Forecasting with Twitter Data","created":"2021-10-27","cited_by_count":4,"area":null},{"id":"2203.00737","title":"Runtime Detection of Executional Errors in Robot-Assisted Surgery","created":"2022-03-01","cited_by_count":4,"area":null},{"id":"2203.12925","title":"TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2301.07923","title":"Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection","created":"2023-01-19","cited_by_count":4,"area":null},{"id":"2304.06059","title":"Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays","created":"2023-04-12","cited_by_count":4,"area":null},{"id":"2405.12179","title":"PLEIADES: Building Temporal Kernels with Orthogonal Polynomials","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2405.14002","title":"Animal Behavior Analysis Methods Using Deep Learning: A Survey","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2408.01334","title":"A Backbone for Long-Horizon Robot Task Understanding","created":"2024-08-02","cited_by_count":4,"area":null},{"id":"2503.17386","title":"A graph neural network surrogate model for mesh-based crashworthiness prediction of vehicle panel components","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2504.16315","title":"SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2506.13457","title":"Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2102.05234","title":"Driver2vec: Driver Identification from Automotive Data","created":"2021-02-10","cited_by_count":3,"area":null},{"id":"2106.07016","title":"WASE: Learning When to Attend for Speaker Extraction in Cocktail Party Environments","created":"2021-06-13","cited_by_count":3,"area":null},{"id":"2112.09293","title":"A Comparative Study of Detecting Anomalies in Time Series Data Using LSTM and TCN Models","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2201.01115","title":"Data Augmentation for Depression Detection Using Skeleton-Based Gait Information","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2201.02110","title":"Eye Know You Too: A DenseNet Architecture for End-to-end Eye Movement Biometrics","created":"2022-01-05","cited_by_count":3,"area":null},{"id":"2203.13817","title":"AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling","created":"2022-03-25","cited_by_count":3,"area":null},{"id":"2205.11648","title":"Deep Representations for Time-varying Brain Datasets","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2302.13074","title":"Temporal Segment Transformer for Action Segmentation","created":"2023-02-25","cited_by_count":3,"area":null},{"id":"2302.14237","title":"Towards Surgical Context Inference and Translation to Gestures","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2306.06960","title":"Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2405.13812","title":"Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2505.01766","title":"Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2102.01059","title":"Automatic Detection of B-lines in Lung Ultrasound Videos From Severe Dengue Patients","created":"2021-02-01","cited_by_count":2,"area":null}],"next_cursor":"100"}