{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"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":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"id":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275},{"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":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1711.07767","title":"Receptive Field Block Net for Accurate and Fast Object Detection","created":"2017-11-21","cited_by_count":141},{"id":"1803.06815","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","created":"2018-03-19","cited_by_count":133},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101},{"id":"1803.06791","title":"Depth-aware CNN for RGB-D Segmentation","created":"2018-03-19","cited_by_count":74},{"id":"1808.03833","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","created":"2018-08-11","cited_by_count":73},{"id":"2408.11104","title":"ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks","created":"2024-08-20","cited_by_count":46},{"id":"2403.20320","title":"MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning","created":"2024-03-29","cited_by_count":44},{"id":"1706.00906","title":"Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach","created":"2017-06-03","cited_by_count":43},{"id":"2304.08028","title":"MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning","created":"2023-04-17","cited_by_count":40},{"id":"2402.19422","title":"PEM: Prototype-based Efficient MaskFormer for Image Segmentation","created":"2024-02-29","cited_by_count":36},{"id":"2101.07422","title":"SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images","created":"2021-01-19","cited_by_count":33},{"id":"2207.04526","title":"Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments","created":"2022-07-10","cited_by_count":33},{"id":"2103.14431","title":"Multimodal Knowledge Expansion","created":"2021-03-26","cited_by_count":26},{"id":"2206.08927","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","created":"2022-06-17","cited_by_count":25},{"id":"2007.09365","title":"Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing","created":"2020-07-18","cited_by_count":24},{"id":"2308.01779","title":"Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport","created":"2023-08-03","cited_by_count":24},{"id":"2307.15362","title":"Prompt Guided Transformer for Multi-Task Dense Prediction","created":"2023-07-28","cited_by_count":13},{"id":"2311.01575","title":"On the Convergence of Encoder-only Shallow Transformers","created":"2023-11-02","cited_by_count":13},{"id":"2404.06486","title":"GO4Align: Group Optimization for Multi-Task Alignment","created":"2024-04-09","cited_by_count":11},{"id":"1905.08929","title":"Learning Fully Dense Neural Networks for Image Semantic Segmentation","created":"2019-05-22","cited_by_count":9},{"id":"2210.06989","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","created":"2022-10-13","cited_by_count":8},{"id":"2306.05242","title":"Efficient Multi-Task Scene Analysis with RGB-D Transformers","created":"2023-06-08","cited_by_count":7},{"id":"2206.03939","title":"Depth-Adapted CNNs for RGB-D Semantic Segmentation","created":"2022-06-08","cited_by_count":6},{"id":"2307.14786","title":"Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning","created":"2023-07-27","cited_by_count":6},{"id":"2210.00923","title":"Masked Supervised Learning for Semantic Segmentation","created":"2022-10-03","cited_by_count":4},{"id":"2308.06024","title":"Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation","created":"2023-08-11","cited_by_count":4},{"id":"2407.19666","title":"Take A Step Back: Rethinking the Two Stages in Visual Reasoning","created":"2024-07-29","cited_by_count":4},{"id":"2305.03640","title":"Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural Network","created":"2023-05-05","cited_by_count":3},{"id":"2307.12349","title":"ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer","created":"2023-07-23","cited_by_count":3},{"id":"2101.10837","title":"The Ikshana Hypothesis of Human Scene Understanding","created":"2021-01-21","cited_by_count":1},{"id":"2405.17004","title":"Efficient Visual Fault Detection for Freight Train via Neural Architecture Search with Data Volume Robustness","created":"2024-05-27","cited_by_count":1}],"next_cursor":null}