{"list":"other","total":81,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"1905.07553","title":"Which Tasks Should Be Learned Together in Multi-task Learning?","created":"2019-05-18","cited_by_count":375},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2104.02395","title":"Ensemble deep learning: A review","created":"2021-04-06","cited_by_count":284},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2002.12186","title":"University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization","created":"2020-02-27","cited_by_count":157},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146},{"id":"2011.11156","title":"Better Aggregation in Test-Time Augmentation","created":"2020-11-23","cited_by_count":122},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"2405.02771","title":"MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning","created":"2024-05-04","cited_by_count":77},{"id":"2411.03687","title":"Beyond Model Adaptation at Test Time: A Survey","created":"2024-11-06","cited_by_count":59},{"id":"2001.11737","title":"AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance","created":"2020-01-31","cited_by_count":56},{"id":"2010.11422","title":"Learning Loss for Test-Time Augmentation","created":"2020-10-22","cited_by_count":56},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40},{"id":"2307.06505","title":"WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces","created":"2023-07-13","cited_by_count":35},{"id":"2309.14949","title":"Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization","created":"2023-09-26","cited_by_count":34},{"id":"2308.10491","title":"SynDrone -- Multi-modal UAV Dataset for Urban Scenarios","created":"2023-08-21","cited_by_count":28},{"id":"2402.03706","title":"MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats","created":"2024-02-06","cited_by_count":18},{"id":"2406.09383","title":"Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset","created":"2024-06-13","cited_by_count":18},{"id":"2212.04408","title":"OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models","created":"2022-12-08","cited_by_count":17},{"id":"2410.11125","title":"UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles","created":"2024-10-14","cited_by_count":16},{"id":"1808.04593","title":"Unsupervised learning of foreground object detection","created":"2018-08-14","cited_by_count":15},{"id":"2010.01910","title":"Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation","created":"2020-10-02","cited_by_count":15},{"id":"1905.09788","title":"Multi-Sample Dropout for Accelerated Training and Better Generalization","created":"2019-05-23","cited_by_count":14},{"id":"2303.07126","title":"Mirror U-Net: Marrying Multimodal Fission with Multi-task Learning for Semantic Segmentation in Medical Imaging","created":"2023-03-13","cited_by_count":14},{"id":"2502.05086","title":"REASSEMBLE: A Multimodal Dataset for Contact-rich Robotic Assembly and Disassembly","created":"2025-02-07","cited_by_count":14},{"id":"2504.11172","title":"TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data","created":"2025-04-15","cited_by_count":14},{"id":"2506.19283","title":"AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration","created":"2025-06-24","cited_by_count":11},{"id":"2304.04959","title":"AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations","created":"2023-04-11","cited_by_count":10},{"id":"2312.12494","title":"DDOS: The Drone Depth and Obstacle Segmentation Dataset","created":"2023-12-19","cited_by_count":10},{"id":"2010.01086","title":"Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus","created":"2020-10-02","cited_by_count":8},{"id":"2308.07615","title":"Self-supervised Hypergraphs for Learning Multiple World Interpretations","created":"2023-08-15","cited_by_count":8},{"id":"2412.18256","title":"Robust Semi-Supervised Learning in Open Environments","created":"2024-12-24","cited_by_count":8},{"id":"2010.14731","title":"MultiMix: Sparingly Supervised, Extreme Multitask Learning From Medical Images","created":"2020-10-28","cited_by_count":6},{"id":"2308.11021","title":"Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations","created":"2023-08-21","cited_by_count":6},{"id":"2406.04230","title":"M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and Multispectral Data","created":"2024-06-06","cited_by_count":6},{"id":"2103.14417","title":"Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift","created":"2021-03-26","cited_by_count":4},{"id":"2406.06230","title":"UEMM-Air: Make Unmanned Aerial Vehicles Perform More Multi-modal Tasks","created":"2024-06-10","cited_by_count":4},{"id":"2407.08460","title":"Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer","created":"2024-07-11","cited_by_count":4},{"id":"2408.16703","title":"RoboMNIST: A Multimodal Dataset for Multi-Robot Activity Recognition Using WiFi Sensing, Video, and Audio","created":"2024-08-29","cited_by_count":3},{"id":"2412.05313","title":"{\\lambda}: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics","created":"2024-11-28","cited_by_count":3},{"id":"2506.16319","title":"RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving","created":"2025-06-19","cited_by_count":3},{"id":"2411.19913","title":"Quantifying the synthetic and real domain gap in aerial scene understanding","created":"2024-11-29","cited_by_count":2},{"id":"2412.08096","title":"THUD++: Large-Scale Dynamic Indoor Scene Dataset and Benchmark for Mobile Robots","created":"2024-12-11","cited_by_count":1}],"next_cursor":null}