{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1712.06080","title":"Spatial As Deep: Spatial CNN for Traffic Scene Understanding","created":"2017-12-17","cited_by_count":187},{"id":"1908.00821","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","created":"2019-08-02","cited_by_count":162},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151},{"id":"1904.08918","title":"Attentive Single-Tasking of Multiple Tasks","created":"2019-04-18","cited_by_count":148},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"1612.07695","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","created":"2016-12-22","cited_by_count":90},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89},{"id":"2108.11250","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","created":"2021-08-25","cited_by_count":82},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62},{"id":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58},{"id":"2007.06889","title":"Knowledge Distillation for Multi-task Learning","created":"2020-07-14","cited_by_count":51},{"id":"2104.10753","title":"Multi-task Learning with Attention for End-to-end Autonomous Driving","created":"2021-04-21","cited_by_count":49},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45},{"id":"2307.13933","title":"AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception","created":"2023-07-26","cited_by_count":39},{"id":"1912.08077","title":"Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition","created":"2019-12-15","cited_by_count":35},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34},{"id":"1911.05034","title":"Learning Sparse Sharing Architectures for Multiple Tasks","created":"2019-11-12","cited_by_count":31},{"id":"2106.03180","title":"Vision Transformers with Hierarchical Attention","created":"2021-06-06","cited_by_count":31},{"id":"2203.09035","title":"HybridNets: End-to-End Perception Network","created":"2022-03-17","cited_by_count":30},{"id":"2209.08953","title":"Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving","created":"2022-09-19","cited_by_count":30},{"id":"2301.03461","title":"DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction","created":"2023-01-09","cited_by_count":27},{"id":"2208.11434","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","created":"2022-08-24","cited_by_count":26},{"id":"2306.04842","title":"InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding","created":"2023-06-08","cited_by_count":22},{"id":"2407.02228","title":"MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders","created":"2024-07-02","cited_by_count":22},{"id":"1802.00066","title":"Dynamics of Driver's Gaze: Explorations in Behavior Modeling & Maneuver Prediction","created":"2018-01-31","cited_by_count":15},{"id":"2303.07666","title":"Relational Multi-Task Learning: Modeling Relations between Data and Tasks","created":"2023-03-14","cited_by_count":15},{"id":"2311.03427","title":"TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding","created":"2023-11-06","cited_by_count":12},{"id":"2311.15157","title":"Advancing Vision Transformers with Group-Mix Attention","created":"2023-11-26","cited_by_count":11},{"id":"2408.15101","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders","created":"2024-08-27","cited_by_count":10},{"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},{"id":"2005.09910","title":"Multitask Learning with Single Gradient Step Update for Task Balancing","created":"2020-05-20","cited_by_count":9},{"id":"2411.05881","title":"MIPD: A Multi-sensory Interactive Perception Dataset for Embodied Intelligent Driving","created":"2024-11-08","cited_by_count":5},{"id":"2111.14122","title":"Cross-Task Consistency Learning Framework for Multi-Task Learning","created":"2021-11-28","cited_by_count":3},{"id":"2506.18084","title":"TEM^3-Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive Driving","created":"2025-06-22","cited_by_count":3},{"id":"2101.12431","title":"Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs","created":"2021-01-29","cited_by_count":2}],"next_cursor":null}