{"total":121,"rows":[{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2103.08907","title":"BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation","created":"2021-03-16","cited_by_count":105,"area":null},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104,"area":null},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82,"area":"mllm"},{"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":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74,"area":null},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59,"area":null},{"id":"2212.03863","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","created":"2022-12-07","cited_by_count":49,"area":null},{"id":"2106.04054","title":"Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation","created":"2021-06-08","cited_by_count":47,"area":null},{"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":"2104.05606","title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","created":"2021-04-06","cited_by_count":42,"area":null},{"id":"2312.12198","title":"Mask Grounding for Referring Image Segmentation","created":"2023-12-19","cited_by_count":40,"area":null},{"id":"2402.15638","title":"Fair Resource Allocation in Multi-Task Learning","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2103.04570","title":"Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing","created":"2021-03-08","cited_by_count":31,"area":null},{"id":"2111.14562","title":"Instance-wise Occlusion and Depth Orders in Natural Scenes","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2105.02184","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2203.04074","title":"E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation","created":"2022-03-08","cited_by_count":27,"area":null},{"id":"2402.02009","title":"Robust Multi-Task Learning with Excess Risks","created":"2024-02-03","cited_by_count":24,"area":null},{"id":"2104.05367","title":"Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition","created":"2021-04-12","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":"2101.06720","title":"Deep Multi-Task Learning for Joint Localization, Perception, and Prediction","created":"2021-01-17","cited_by_count":22,"area":null},{"id":"2103.00429","title":"Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models","created":"2021-02-28","cited_by_count":22,"area":null},{"id":"2106.09748","title":"DeepLab2: A TensorFlow Library for Deep Labeling","created":"2021-06-17","cited_by_count":22,"area":null},{"id":"2207.04614","title":"Instance Shadow Detection with A Single-Stage Detector","created":"2022-07-11","cited_by_count":22,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21,"area":null},{"id":"2210.00911","title":"Learning Equivariant Segmentation with Instance-Unique Querying","created":"2022-10-03","cited_by_count":17,"area":null},{"id":"2411.10458","title":"Neural decoding from stereotactic EEG: accounting for electrode variability across subjects","created":"2024-11-01","cited_by_count":17,"area":null},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"id":"2103.17123","title":"Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite","created":"2021-03-31","cited_by_count":16,"area":null},{"id":"2212.03537","title":"Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning","created":"2022-12-07","cited_by_count":16,"area":null},{"id":"2105.03186","title":"A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2108.03581","title":"Visible Watermark Removal via Self-calibrated Localization and Background Refinement","created":"2021-08-08","cited_by_count":14,"area":null},{"id":"2301.03992","title":"Vision Transformers Are Good Mask Auto-Labelers","created":"2023-01-10","cited_by_count":14,"area":null},{"id":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2309.03130","title":"MyoDex: A Generalizable Prior for Dexterous Manipulation","created":"2023-09-06","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":"2103.11652","title":"Polarization Guided Specular Reflection Separation","created":"2021-03-22","cited_by_count":10,"area":null},{"id":"2204.05393","title":"Improving Few-Shot Part Segmentation using Coarse Supervision","created":"2022-04-11","cited_by_count":10,"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":"2108.05524","title":"Silhouette based View embeddings for Gait Recognition under Multiple Views","created":"2021-08-12","cited_by_count":9,"area":null},{"id":"2301.08898","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","created":"2023-01-21","cited_by_count":9,"area":null},{"id":"2101.02196","title":"Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos","created":"2021-01-06","cited_by_count":8,"area":null},{"id":"2101.06545","title":"VideoClick: Video Object Segmentation with a Single Click","created":"2021-01-16","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":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2105.11168","title":"Human-centric Relation Segmentation: Dataset and Solution","created":"2021-05-24","cited_by_count":7,"area":null},{"id":"2106.15707","title":"Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectives","created":"2021-06-28","cited_by_count":7,"area":null},{"id":"2204.05864","title":"Semantic keypoint-based pose estimation from single RGB frames","created":"2022-04-12","cited_by_count":7,"area":null},{"id":"2211.05120","title":"Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2308.06868","title":"Camera Based mmWave Beam Prediction: Towards Multi-Candidate Real-World Scenarios","created":"2023-08-14","cited_by_count":7,"area":null},{"id":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6,"area":null},{"id":"2101.10620","title":"Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer","created":"2021-01-26","cited_by_count":5,"area":null},{"id":"2105.00234","title":"JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets","created":"2021-05-01","cited_by_count":5,"area":null},{"id":"2109.08963","title":"SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2110.00470","title":"Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance Segmentation","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5,"area":null},{"id":"2404.08271","title":"Transfer Learning Study of Motion Transformer-based Trajectory Predictions","created":"2024-04-12","cited_by_count":5,"area":null},{"id":"2109.06148","title":"DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2208.09023","title":"Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2210.07239","title":"Composite Learning for Robust and Effective Dense Predictions","created":"2022-10-13","cited_by_count":4,"area":null},{"id":"2307.08238","title":"Unified Open-Vocabulary Dense Visual Prediction","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2412.00153","title":"ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model","created":"2024-11-29","cited_by_count":4,"area":"mllm"},{"id":"2507.07485","title":"Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning","created":"2025-07-10","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":"2107.07464","title":"Amodal segmentation just like doing a jigsaw","created":"2021-07-15","cited_by_count":3,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2109.08218","title":"SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2109.08912","title":"Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer","created":"2021-09-18","cited_by_count":3,"area":null},{"id":"2109.11874","title":"Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2204.02890","title":"DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2206.02903","title":"Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2403.01156","title":"Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation","created":"2024-03-02","cited_by_count":3,"area":null},{"id":"2405.18299","title":"Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2409.06716","title":"Detailed delineation of the fetal brain in diffusion MRI via multi-task learning","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2101.06371","title":"NNStreamer: Efficient and Agile Development of On-Device AI Systems","created":"2021-01-16","cited_by_count":2,"area":null},{"id":"2103.13565","title":"Jointly Modeling Heterogeneous Student Behaviors and Interactions Among Multiple Prediction Tasks","created":"2021-03-25","cited_by_count":2,"area":null},{"id":"2108.06185","title":"CNN-based Two-Stage Parking Slot Detection Using Region-Specific Multi-Scale Feature Extraction","created":"2021-08-13","cited_by_count":2,"area":null},{"id":"2202.10983","title":"Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2304.13216","title":"Exploiting CNNs for Semantic Segmentation with Pascal VOC","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2404.13443","title":"FisheyeDetNet: 360{\\deg} Surround view Fisheye Camera based Object Detection System for Autonomous Driving","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2508.10432","title":"CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2508.13979","title":"AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2105.13531","title":"Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task","created":"2021-05-28","cited_by_count":1,"area":null},{"id":"2108.12817","title":"Airplane Detection Based on Mask Region Convolution Neural Network","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2112.06121","title":"Magnifying Networks for Images with Billions of Pixels","created":"2021-12-12","cited_by_count":1,"area":null},{"id":"2203.06421","title":"One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out","created":"2022-03-12","cited_by_count":1,"area":null},{"id":"2303.01219","title":"A Coarse to Fine Framework for Object Detection in High Resolution Image","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2307.01401","title":"Multi-Task Learning Improves Performance In Deep Argument Mining Models","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2307.04013","title":"BPNet: B\\'ezier Primitive Segmentation on 3D Point Clouds","created":"2023-07-08","cited_by_count":1,"area":null},{"id":"2310.03472","title":"Ammonia-Net: A Multi-task Joint Learning Model for Multi-class Segmentation and Classification in Tooth-marked Tongue Diagnosis","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2401.12729","title":"Enhancing Object Detection Performance for Small Objects through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2402.02474","title":"Deep Spectral Improvement for Unsupervised Image Instance Segmentation","created":"2024-02-04","cited_by_count":1,"area":null}],"next_cursor":"100"}