{"total":224,"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":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327,"area":null},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286,"area":"diffusion"},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231,"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":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125,"area":null},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89,"area":null},{"id":"2104.13613","title":"Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","created":"2021-04-28","cited_by_count":80,"area":null},{"id":"2107.11787","title":"Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation","created":"2021-07-25","cited_by_count":77,"area":null},{"id":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2304.06334","title":"iDisc: Internal Discretization for Monocular Depth Estimation","created":"2023-04-13","cited_by_count":73,"area":null},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65,"area":null},{"id":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58,"area":"moe"},{"id":"2108.08829","title":"Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2104.02243","title":"3D-to-2D Distillation for Indoor Scene Parsing","created":"2021-04-06","cited_by_count":48,"area":null},{"id":"2111.12341","title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","created":"2021-11-24","cited_by_count":47,"area":"distill"},{"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":"2403.20320","title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","created":"2024-03-29","cited_by_count":44,"area":null},{"id":"2103.15483","title":"Adaptive Surface Normal Constraint for Depth Estimation","created":"2021-03-29","cited_by_count":43,"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":"2102.02696","title":"Active Boundary Loss for Semantic Segmentation","created":"2021-02-04","cited_by_count":40,"area":null},{"id":"2205.00858","title":"Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation","created":"2022-05-02","cited_by_count":40,"area":null},{"id":"2107.00782","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","created":"2021-07-02","cited_by_count":39,"area":null},{"id":"2102.10271","title":"Meta-Learning Dynamics Forecasting Using Task Inference","created":"2021-02-20","cited_by_count":38,"area":null},{"id":"2104.06456","title":"Single Image Depth Estimation: An Overview","created":"2021-04-13","cited_by_count":35,"area":null},{"id":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34,"area":null},{"id":"2101.07422","title":"SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images","created":"2021-01-19","cited_by_count":33,"area":null},{"id":"2105.07830","title":"Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation","created":"2021-05-17","cited_by_count":32,"area":null},{"id":"2109.01801","title":"Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation","created":"2021-09-04","cited_by_count":32,"area":null},{"id":"2103.12955","title":"Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2207.08224","title":"Learning with Recoverable Forgetting","created":"2022-07-17","cited_by_count":30,"area":null},{"id":"2208.00380","title":"Less is More: Consistent Video Depth Estimation with Masked Frames Modeling","created":"2022-07-31","cited_by_count":30,"area":null},{"id":"2307.11477","title":"SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection","created":"2023-07-21","cited_by_count":30,"area":null},{"id":"2303.02506","title":"Prismer: A Vision-Language Model with Multi-Task Experts","created":"2023-03-04","cited_by_count":28,"area":"mllm"},{"id":"2206.13199","title":"MGNet: Monocular Geometric Scene Understanding for Autonomous Driving","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2301.03461","title":"DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2302.06378","title":"Semantic Image Segmentation: Two Decades of Research","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2108.12545","title":"Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","created":"2021-08-28","cited_by_count":25,"area":null},{"id":"2206.08927","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","created":"2022-06-17","cited_by_count":25,"area":null},{"id":"2103.10919","title":"Robustness via Cross-Domain Ensembles","created":"2021-03-19","cited_by_count":23,"area":null},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23,"area":null},{"id":"2305.18691","title":"Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts","created":"2023-05-30","cited_by_count":23,"area":"moe"},{"id":"2110.07197","title":"Semi-supervised Multi-task Learning for Semantics and Depth","created":"2021-10-14","cited_by_count":22,"area":null},{"id":"2306.04842","title":"InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding","created":"2023-06-08","cited_by_count":22,"area":null},{"id":"2407.02228","title":"MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders","created":"2024-07-02","cited_by_count":22,"area":"ssm"},{"id":"2104.13395","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","created":"2021-04-27","cited_by_count":21,"area":null},{"id":"2301.00954","title":"PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation","created":"2023-01-03","cited_by_count":19,"area":null},{"id":"2501.02576","title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","created":"2025-01-05","cited_by_count":19,"area":"diffusion"},{"id":"2308.02066","title":"Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives","created":"2023-08-03","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":"2311.13250","title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2408.02198","title":"Synergistic Learning with Multi-Task DeepONet for Efficient PDE Problem Solving","created":"2024-08-05","cited_by_count":17,"area":null},{"id":"2501.13087","title":"Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation","created":"2025-01-22","cited_by_count":17,"area":"diffusion"},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"id":"2407.08187","title":"ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation","created":"2024-07-11","cited_by_count":15,"area":null},{"id":"2206.00468","title":"PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation","created":"2022-06-01","cited_by_count":14,"area":null},{"id":"2308.12372","title":"Vision Transformer Adapters for Generalizable Multitask Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2402.05869","title":"Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2307.15362","title":"Prompt Guided Transformer for Multi-Task Dense Prediction","created":"2023-07-28","cited_by_count":13,"area":null},{"id":"2307.16617","title":"FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration","created":"2023-07-31","cited_by_count":13,"area":null},{"id":"2403.10662","title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2408.16478","title":"MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2311.03427","title":"TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding","created":"2023-11-06","cited_by_count":12,"area":null},{"id":"2312.13514","title":"BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions","created":"2023-12-21","cited_by_count":12,"area":null},{"id":"2506.17206","title":"DreamCube: 3D Panorama Generation via Multi-plane Synchronization","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2309.01073","title":"Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding","created":"2023-09-03","cited_by_count":11,"area":null},{"id":"2403.16732","title":"Enabling Uncertainty Estimation in Iterative Neural Networks","created":"2024-03-25","cited_by_count":11,"area":null},{"id":"2406.02996","title":"Quantifying Task Priority for Multi-Task Optimization","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2210.04153","title":"Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing","created":"2022-10-09","cited_by_count":10,"area":null},{"id":"2408.15101","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders","created":"2024-08-27","cited_by_count":10,"area":"ssm"},{"id":"2504.02264","title":"MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception","created":"2025-04-03","cited_by_count":10,"area":null},{"id":"2106.08615","title":"EdgeConv with Attention Module for Monocular Depth Estimation","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2106.11401","title":"Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation","created":"2021-06-21","cited_by_count":9,"area":null},{"id":"2112.03695","title":"Safe Distillation Box","created":"2021-12-05","cited_by_count":9,"area":"distill"},{"id":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2306.01980","title":"Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning","created":"2023-06-03","cited_by_count":9,"area":null},{"id":"2311.12682","title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","created":"2023-11-21","cited_by_count":9,"area":null},{"id":"2407.20078","title":"Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2101.02843","title":"Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction","created":"2021-01-08","cited_by_count":8,"area":null},{"id":"2102.13258","title":"Boundary-induced and scene-aggregated network for monocular depth prediction","created":"2021-02-26","cited_by_count":8,"area":null},{"id":"2105.02195","title":"Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes","created":"2021-05-05","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":"2210.06989","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2303.01788","title":"Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving","created":"2023-03-03","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":"2307.07934","title":"Contrastive Multi-Task Dense Prediction","created":"2023-07-16","cited_by_count":8,"area":null},{"id":"2309.04422","title":"Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving","created":"2023-09-08","cited_by_count":8,"area":null},{"id":"2310.00986","title":"Multi-task Learning with 3D-Aware Regularization","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2311.00134","title":"Joint Depth Prediction and Semantic Segmentation with Multi-View SAM","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2108.04584","title":"UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2109.13432","title":"Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency","created":"2021-09-28","cited_by_count":7,"area":null},{"id":"2111.09692","title":"SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation","created":"2021-11-18","cited_by_count":7,"area":"distill"},{"id":"2304.03542","title":"Better \"CMOS\" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution","created":"2023-04-07","cited_by_count":7,"area":null}],"next_cursor":"100"}