{"total":108,"rows":[{"id":"2103.11624","title":"Multimodal Motion Prediction with Stacked Transformers","created":"2021-03-22","cited_by_count":208,"area":null},{"id":"2102.05034","title":"SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks","created":"2021-02-09","cited_by_count":110,"area":null},{"id":"2110.01401","title":"MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction","created":"2021-09-30","cited_by_count":48,"area":null},{"id":"2403.01786","title":"Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection","created":"2024-03-04","cited_by_count":47,"area":null},{"id":"2203.06801","title":"MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks","created":"2022-03-14","cited_by_count":34,"area":null},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30,"area":null},{"id":"2402.18922","title":"A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection","created":"2024-02-29","cited_by_count":23,"area":null},{"id":"2308.08942","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","created":"2023-08-17","cited_by_count":20,"area":null},{"id":"2306.02790","title":"Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers","created":"2023-06-05","cited_by_count":18,"area":null},{"id":"2309.16772","title":"XVO: Generalized Visual Odometry via Cross-Modal Self-Training","created":"2023-09-28","cited_by_count":18,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2505.08740","title":"Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential Equations","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2201.10353","title":"A Multi-modal Fusion Framework Based on Multi-task Correlation Learning for Cancer Prognosis Prediction","created":"2022-01-22","cited_by_count":11,"area":null},{"id":"2302.02928","title":"Generating Evidential BEV Maps in Continuous Driving Space","created":"2023-02-06","cited_by_count":10,"area":null},{"id":"2402.03366","title":"Uncertainty-Aware Explainable Recommendation with Large Language Models","created":"2024-01-31","cited_by_count":10,"area":null},{"id":"2104.06485","title":"Machine-learned 3D Building Vectorization from Satellite Imagery","created":"2021-04-13","cited_by_count":9,"area":null},{"id":"2202.03487","title":"Targeted-BEHRT: Deep learning for observational causal inference on longitudinal electronic health records","created":"2022-02-07","cited_by_count":9,"area":null},{"id":"2510.15868","title":"LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal","created":"2025-10-17","cited_by_count":9,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2211.08903","title":"Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks","created":"2022-11-16","cited_by_count":7,"area":null},{"id":"2305.19228","title":"Unsupervised Melody-to-Lyric Generation","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2307.03544","title":"Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note-wise Features","created":"2023-07-07","cited_by_count":7,"area":null},{"id":"2204.08649","title":"LitMC-BERT: transformer-based multi-label classification of biomedical literature with an application on COVID-19 literature curation","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2307.14382","title":"When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2308.11983","title":"Multi-Modal Multi-Task (3MT) Road Segmentation","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2607.13429","title":"Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment","created":"2026-07-15","cited_by_count":6,"area":"mllm"},{"id":"2203.05294","title":"Domain Generalisation for Object Detection under Covariate and Concept Shift","created":"2022-03-10","cited_by_count":5,"area":null},{"id":"2209.00381","title":"SemSegDepth: A Combined Model for Semantic Segmentation and Depth Completion","created":"2022-09-01","cited_by_count":5,"area":null},{"id":"2306.13661","title":"Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learning","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2406.16279","title":"SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2408.15114","title":"Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2412.16361","title":"Toward Robust Neural Reconstruction from Sparse Point Sets","created":"2024-12-20","cited_by_count":5,"area":null},{"id":"2505.10930","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2507.07778","title":"Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2202.04136","title":"Generative multitask learning mitigates target-causing confounding","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2202.07107","title":"Gaze-Guided Class Activation Mapping: Leveraging Human Attention for Network Attention in Chest X-rays Classification","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2202.07118","title":"Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2603.03505","title":"PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation","created":"2026-03-03","cited_by_count":4,"area":null},{"id":"2107.05445","title":"Disentangling Transfer and Interference in Multi-Domain Learning","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2110.02564","title":"MTCD: Cataract Detection via Near Infrared Eye Images","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2111.07846","title":"Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder","created":"2021-11-15","cited_by_count":3,"area":null},{"id":"2201.05782","title":"A Novel Multi-Task Learning Method for Symbolic Music Emotion Recognition","created":"2022-01-15","cited_by_count":3,"area":null},{"id":"2305.00385","title":"Cross-Shaped Windows Transformer with Self-supervised Pretraining for Clinically Significant Prostate Cancer Detection in Bi-parametric MRI","created":"2023-04-30","cited_by_count":3,"area":null},{"id":"2410.13332","title":"Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2504.07976","title":"EquiNO: A Physics-Informed Neural Operator for Multiscale Simulations","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2206.11049","title":"Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression","created":"2022-06-22","cited_by_count":2,"area":null},{"id":"2208.00919","title":"Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression","created":"2022-08-01","cited_by_count":2,"area":null},{"id":"2209.09199","title":"AutoPET Challenge 2022: Step-by-Step Lesion Segmentation in Whole-body FDG-PET/CT","created":"2022-09-04","cited_by_count":2,"area":null},{"id":"2210.15563","title":"Multimodal Transformer Distillation for Audio-Visual Synchronization","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2212.14180","title":"PanDepth: Joint Panoptic Segmentation and Depth Completion","created":"2022-12-29","cited_by_count":2,"area":null},{"id":"2303.07278","title":"Adaptive Weight Assignment Scheme For Multi-task Learning","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2401.14754","title":"VJT: A Video Transformer on Joint Tasks of Deblurring, Low-light Enhancement and Denoising","created":"2024-01-26","cited_by_count":2,"area":null},{"id":"2411.11871","title":"MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System","created":"2024-11-03","cited_by_count":2,"area":null},{"id":"2503.03270","title":"Reduced Spatial Dependency for More General Video-level Deepfake Detection","created":"2025-03-05","cited_by_count":2,"area":null},{"id":"2509.06654","title":"AnalysisGNN: Unified Music Analysis with Graph Neural Networks","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.16345","title":"Estimating Clinical Lab Test Result Trajectories from PPG using Physiological Foundation Model and Patient-Aware State Space Model -- a UNIPHY+ Approach","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2109.04561","title":"Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility","created":"2021-09-09","cited_by_count":1,"area":null},{"id":"2209.07384","title":"Self-Supervised Attention Networks and Uncertainty Loss Weighting for Multi-Task Emotion Recognition on Vocal Bursts","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2211.16753","title":"VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2311.01928","title":"Constructing Temporal Dynamic Knowledge Graphs from Interactive Text-based Games","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2401.07729","title":"SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2401.13998","title":"WAL-Net: Weakly supervised auxiliary task learning network for carotid plaques classification","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2401.16299","title":"Enhancing Molecular Property Prediction with Auxiliary Learning and Task-Specific Adaptation","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2404.01673","title":"A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2405.05695","title":"Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2405.15928","title":"PatchProt: Hydrophobic patch prediction using protein foundation models","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2409.01781","title":"Dual Advancement of Representation Learning and Clustering for Sparse and Noisy Images","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2412.11553","title":"Training Strategies for Isolated Sign Language Recognition","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2412.19547","title":"Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective","created":"2024-12-27","cited_by_count":1,"area":null},{"id":"2501.01114","title":"Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2502.00042","title":"LSU-Net: Lightweight Automatic Organs Segmentation Network For Medical Images","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2505.16756","title":"Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.17867","title":"Multi-task Learning For Joint Action and Gesture Recognition","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.00909","title":"NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detection","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2106.11478","title":"Fourier Transform Approximation as an Auxiliary Task for Image Classification","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2201.01806","title":"Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2301.09058","title":"Leveraging Speaker Embeddings with Adversarial Multi-task Learning for Age Group Classification","created":"2023-01-22","cited_by_count":0,"area":null},{"id":"2303.06807","title":"Vessel-Promoted OCT to OCTA Image Translation by Heuristic Contextual Constraints","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2303.15656","title":"Predicting Adverse Neonatal Outcomes for Preterm Neonates with Multi-Task Learning","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2305.13447","title":"Regularization Through Simultaneous Learning: A Case Study on Plant Classification","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2306.17646","title":"Feature Representation Learning for NL2SQL Generation Based on Coupling and Decoupling","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2310.09278","title":"Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning","created":"2023-10-13","cited_by_count":0,"area":null},{"id":"2404.03991","title":"Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2404.08028","title":"FedAuxHMTL: Federated Auxiliary Hard-Parameter Sharing Multi-Task Learning for Network Edge Traffic Classification","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2405.14195","title":"Enhanced Object Tracking by Self-Supervised Auxiliary Depth Estimation Learning","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2408.01526","title":"Recognizing and Reconstructing a Multi-Unit Floor Plan","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2409.19554","title":"Tri-Cam: Practical Eye Gaze Tracking via Camera Network","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2410.19639","title":"Planning-Aware Diffusion Networks for Enhanced Motion Forecasting in Autonomous Driving","created":"2024-10-25","cited_by_count":0,"area":null},{"id":"2501.12115","title":"Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2504.20800","title":"Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2505.02211","title":"Intelligent Diagnosis Using Dual-Branch Attention Network for Rare Thyroid Carcinoma Recognition with Ultrasound Imaging","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2506.07294","title":"Towards Generalized Source Tracing for Codec-Based Deepfake Speech","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2508.16927","title":"LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2509.13801","title":"Masked Representation Modeling for Domain-Adaptive Segmentation","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2510.22940","title":"Generating Auxiliary Tasks with Reinforcement Learning","created":"2025-10-27","cited_by_count":0,"area":"deeprl"},{"id":"2511.13197","title":"Fully Automatic Data Labeling for Ultrasound Screen Detection","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.02224","title":"Towards Unified Video Quality Assessment","created":"2025-12-01","cited_by_count":0,"area":"moe"},{"id":"2601.17080","title":"PC-MCL: Patient-Consistent Multi-Cycle Learning with multi-label bias correction for respiratory sound classification","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2602.05730","title":"Depth as Prior Knowledge for Object Detection","created":"2026-02-05","cited_by_count":0,"area":null}],"next_cursor":"100"}