{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1805.10421","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","created":"2018-05-26","cited_by_count":370},{"id":"1709.03410","title":"One-Shot Learning for Semantic Segmentation","created":"2017-09-11","cited_by_count":337},{"id":"2008.01449","title":"Prior Guided Feature Enrichment Network for Few-Shot Segmentation","created":"2020-08-04","cited_by_count":271},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1908.08297","title":"EGNet:Edge Guidance Network for Salient Object Detection","created":"2019-08-22","cited_by_count":237},{"id":"1903.02351","title":"CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning","created":"2019-03-06","cited_by_count":217},{"id":"1904.08739","title":"Cascaded Partial Decoder for Fast and Accurate Salient Object Detection","created":"2019-04-18","cited_by_count":216},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"2104.01893","title":"Adaptive Prototype Learning and Allocation for Few-Shot Segmentation","created":"2021-04-05","cited_by_count":207},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123},{"id":"2011.08612","title":"Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things","created":"2020-11-17","cited_by_count":111},{"id":"2003.13193","title":"Adversarial Feature Hallucination Networks for Few-Shot Learning","created":"2020-03-30","cited_by_count":110},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2003.05643","title":"Highly Efficient Salient Object Detection with 100K Parameters","created":"2020-03-12","cited_by_count":79},{"id":"1712.07576","title":"Learning to Act Properly: Predicting and Explaining Affordances from Images","created":"2017-12-20","cited_by_count":74},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"2007.03380","title":"Re-thinking Co-Salient Object Detection","created":"2020-07-07","cited_by_count":54},{"id":"1806.09266","title":"Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision","created":"2018-06-25","cited_by_count":52},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46},{"id":"1804.03080","title":"Binge Watching: Scaling Affordance Learning from Sitcoms","created":"2018-04-09","cited_by_count":41},{"id":"2106.14747","title":"One-Shot Affordance Detection","created":"2021-06-28","cited_by_count":32},{"id":"1808.09796","title":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","created":"2018-08-29","cited_by_count":30},{"id":"2008.02918","title":"Polysemy Deciphering Network for Robust Human-Object Interaction Detection","created":"2020-08-07","cited_by_count":25},{"id":"1907.10156","title":"DR Loss: Improving Object Detection by Distributional Ranking","created":"2019-07-23","cited_by_count":24},{"id":"1708.00945","title":"Predicting Human Activities Using Stochastic Grammar","created":"2017-08-02","cited_by_count":22},{"id":"1908.05641","title":"IoU-balanced Loss Functions for Single-stage Object Detection","created":"2019-08-15","cited_by_count":22},{"id":"2002.00537","title":"Towards High Performance Human Keypoint Detection","created":"2020-02-03","cited_by_count":20},{"id":"1704.02787","title":"Deep Affordance-grounded Sensorimotor Object Recognition","created":"2017-04-10","cited_by_count":17},{"id":"2004.05538","title":"Self-Supervised Tuning for Few-Shot Segmentation","created":"2020-04-12","cited_by_count":17},{"id":"1707.02850","title":"Adaptive Binarization for Weakly Supervised Affordance Segmentation","created":"2017-07-10","cited_by_count":16},{"id":"2012.11810","title":"Progressive One-shot Human Parsing","created":"2020-12-22","cited_by_count":12},{"id":"1905.06656","title":"One-Shot Texture Retrieval with Global Context Metric","created":"2019-05-16","cited_by_count":3},{"id":"1908.09075","title":"Residual Objectness for Imbalance Reduction","created":"2019-08-24","cited_by_count":3},{"id":"2104.14375","title":"MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization","created":"2021-04-29","cited_by_count":3},{"id":"2103.16549","title":"Deep Gaussian Processes for Few-Shot Segmentation","created":"2021-03-30","cited_by_count":1}],"next_cursor":null}