{"total":105,"rows":[{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2108.06858","title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","created":"2021-08-16","cited_by_count":166,"area":null},{"id":"2107.13774","title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","created":"2021-07-29","cited_by_count":156,"area":null},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119,"area":null},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2102.08945","title":"Weakly Supervised Learning of Rigid 3D Scene Flow","created":"2021-02-17","cited_by_count":60,"area":null},{"id":"2112.11377","title":"Shape from Polarization for Complex Scenes in the Wild","created":"2021-12-21","cited_by_count":53,"area":null},{"id":"2210.09670","title":"Hierarchical Normalization for Robust Monocular Depth Estimation","created":"2022-10-18","cited_by_count":52,"area":null},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48,"area":null},{"id":"2110.10394","title":"Deep Learning for HDR Imaging: State-of-the-Art and Future Trends","created":"2021-10-20","cited_by_count":45,"area":null},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45,"area":"moe"},{"id":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44,"area":null},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42,"area":null},{"id":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37,"area":null},{"id":"2111.10493","title":"Discrete Representations Strengthen Vision Transformer Robustness","created":"2021-11-20","cited_by_count":35,"area":null},{"id":"2112.09081","title":"CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data","created":"2021-12-16","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":"2104.05107","title":"Towards a Collective Agenda on AI for Earth Science Data Analysis","created":"2021-04-11","cited_by_count":27,"area":null},{"id":"2206.13199","title":"MGNet: Monocular Geometric Scene Understanding for Autonomous Driving","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2103.10919","title":"Robustness via Cross-Domain Ensembles","created":"2021-03-19","cited_by_count":23,"area":null},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22,"area":null},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"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":"2403.15389","title":"DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data","created":"2024-03-22","cited_by_count":18,"area":"diffusion"},{"id":"2407.14032","title":"Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance","created":"2024-07-19","cited_by_count":17,"area":null},{"id":"2204.04836","title":"Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection","created":"2022-04-11","cited_by_count":16,"area":null},{"id":"2303.07666","title":"Relational Multi-Task Learning: Modeling Relations between Data and Tasks","created":"2023-03-14","cited_by_count":15,"area":null},{"id":"2106.13409","title":"Generative Modeling for Multi-task Visual Learning","created":"2021-06-25","cited_by_count":14,"area":null},{"id":"2112.07074","title":"Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text","created":"2021-12-14","cited_by_count":14,"area":"distill"},{"id":"2308.12372","title":"Vision Transformer Adapters for Generalizable Multitask Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2401.10222","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2102.02337","title":"Environment Predictive Coding for Embodied Agents","created":"2021-02-03","cited_by_count":12,"area":null},{"id":"2112.02252","title":"Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction","created":"2021-12-04","cited_by_count":11,"area":null},{"id":"2208.12462","title":"Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression","created":"2022-08-26","cited_by_count":11,"area":null},{"id":"2304.04140","title":"Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains","created":"2023-04-09","cited_by_count":11,"area":null},{"id":"2206.04669","title":"Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2212.11720","title":"GOOD: Exploring Geometric Cues for Detecting Objects in an Open World","created":"2022-12-22","cited_by_count":10,"area":null},{"id":"2309.15762","title":"Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback","created":"2023-09-27","cited_by_count":10,"area":null},{"id":"2310.03023","title":"Human-oriented Representation Learning for Robotic Manipulation","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2208.10056","title":"Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking","created":"2022-08-22","cited_by_count":9,"area":null},{"id":"2211.12417","title":"ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning","created":"2022-11-19","cited_by_count":9,"area":null},{"id":"2212.06079","title":"Robust Perception through Equivariance","created":"2022-12-12","cited_by_count":9,"area":null},{"id":"2110.02549","title":"See Yourself in Others: Attending Multiple Tasks for Own Failure Detection","created":"2021-10-06","cited_by_count":8,"area":null},{"id":"2110.11219","title":"PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image","created":"2021-10-21","cited_by_count":8,"area":null},{"id":"2303.09663","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2308.07615","title":"Self-supervised Hypergraphs for Learning Multiple World Interpretations","created":"2023-08-15","cited_by_count":8,"area":null},{"id":"2311.18664","title":"Multi-task learning with cross-task consistency for improved depth estimation in colonoscopy","created":"2023-11-30","cited_by_count":8,"area":null},{"id":"2403.15309","title":"Controlled Training Data Generation with Diffusion Models","created":"2024-03-22","cited_by_count":8,"area":"diffusion"},{"id":"2112.01767","title":"MT-TransUNet: Mediating Multi-Task Tokens in Transformers for Skin Lesion Segmentation and Classification","created":"2021-12-03","cited_by_count":7,"area":null},{"id":"2203.08764","title":"X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation","created":"2022-03-16","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":"2308.11021","title":"Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2309.09724","title":"Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering","created":"2023-09-18","cited_by_count":6,"area":null},{"id":"2310.02237","title":"Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2404.01976","title":"Joint-Task Regularization for Partially Labeled Multi-Task Learning","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2112.04212","title":"Do Pedestrians Pay Attention? Eye Contact Detection in the Wild","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2309.17450","title":"Multi-task View Synthesis with Neural Radiance Fields","created":"2023-09-29","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":"2103.14417","title":"Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift","created":"2021-03-26","cited_by_count":4,"area":null},{"id":"2202.04136","title":"Generative multitask learning mitigates target-causing confounding","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2206.03691","title":"Robust Deep Ensemble Method for Real-world Image Denoising","created":"2022-06-08","cited_by_count":4,"area":null},{"id":"2306.00118","title":"Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2411.18823","title":"Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2106.07822","title":"Canonical Face Embeddings","created":"2021-06-15","cited_by_count":3,"area":null},{"id":"2111.03039","title":"Towards Panoptic 3D Parsing for Single Image in the Wild","created":"2021-11-04","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":"2111.14122","title":"Cross-Task Consistency Learning Framework for Multi-Task Learning","created":"2021-11-28","cited_by_count":3,"area":null},{"id":"2302.03531","title":"Structured Generative Models for Scene Understanding","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2304.10671","title":"Point-supervised Single-cell Segmentation via Collaborative Knowledge Sharing","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2307.01425","title":"Consistent Multimodal Generation via A Unified GAN Framework","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2309.16646","title":"Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2311.04040","title":"Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data","created":"2023-11-07","cited_by_count":3,"area":"distill"},{"id":"2503.20748","title":"UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2509.23915","title":"Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2204.04544","title":"Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2301.11310","title":"Learning Good Features to Transfer Across Tasks and Domains","created":"2023-01-26","cited_by_count":2,"area":null},{"id":"2303.16133","title":"Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models","created":"2023-03-28","cited_by_count":2,"area":"mllm"},{"id":"2309.06288","title":"Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection","created":"2023-09-12","cited_by_count":2,"area":"distill"},{"id":"2403.10252","title":"Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2502.16748","title":"GS-TransUNet: Integrated 2D Gaussian Splatting and Transformer UNet for Accurate Skin Lesion Analysis","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2506.08013","title":"StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets","created":"2025-06-09","cited_by_count":2,"area":"diffusion"},{"id":"2202.03365","title":"Simple Control Baselines for Evaluating Transfer Learning","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2205.02979","title":"Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2210.05152","title":"TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2212.05040","title":"Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding","created":"2022-12-09","cited_by_count":1,"area":null},{"id":"2307.08071","title":"Dense Multitask Learning to Reconfigure Comics","created":"2023-07-16","cited_by_count":1,"area":null},{"id":"2307.12400","title":"TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2509.16959","title":"Graph Coloring for Multi-Task Learning","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2606.01557","title":"Everywhere Learning: Artificial Intelligence with Pointwise Constraints","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2101.07589","title":"Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets","created":"2021-01-19","cited_by_count":0,"area":null},{"id":"2110.12696","title":"Self-Supervised Knowledge Transfer via Loosely Supervised Auxiliary Tasks","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2210.05568","title":"Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2402.08035","title":"Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2402.13848","title":"Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2411.17536","title":"Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2501.06884","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","created":"2025-01-12","cited_by_count":0,"area":"moe"},{"id":"2508.19555","title":"MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery","created":"2025-08-27","cited_by_count":0,"area":null}],"next_cursor":"100"}