{"list":"other","total":102,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1812.06499","title":"HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images","created":"2018-12-16","cited_by_count":388},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"1605.09782","title":"Adversarial Feature Learning","created":"2016-05-31","cited_by_count":350},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"1805.06561","title":"DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images","created":"2018-05-17","cited_by_count":277},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1503.01817","title":"YFCC100M: The New Data in Multimedia Research","created":"2015-03-05","cited_by_count":235},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2002.12416","title":"Learning in the Frequency Domain","created":"2020-02-27","cited_by_count":198},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1808.01050","title":"Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds","created":"2018-08-02","cited_by_count":186},{"id":"2012.07810","title":"Real-Time High-Resolution Background Matting","created":"2020-12-14","cited_by_count":173},{"id":"2107.05407","title":"PonderNet: Learning to Ponder","created":"2021-07-12","cited_by_count":168},{"id":"1912.12378","title":"Deep neural network models for computational histopathology: A survey","created":"2019-12-28","cited_by_count":165},{"id":"2001.03360","title":"NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization","created":"2020-01-10","cited_by_count":151},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"1803.06815","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","created":"2018-03-19","cited_by_count":133},{"id":"1808.04277","title":"BACH: Grand Challenge on Breast Cancer Histology Images","created":"2018-08-13","cited_by_count":131},{"id":"1810.05331","title":"Dynamic Channel Pruning: Feature Boosting and Suppression","created":"2018-10-12","cited_by_count":129},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"id":"1511.04136","title":"UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking","created":"2015-11-13","cited_by_count":98},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"2004.05993","title":"A Survey of Single-Scene Video Anomaly Detection","created":"2020-04-13","cited_by_count":88},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88},{"id":"1607.07155","title":"A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection","created":"2016-07-25","cited_by_count":83},{"id":"2005.01094","title":"Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities","created":"2020-05-03","cited_by_count":71},{"id":"2004.12814","title":"Why should we add early exits to neural networks?","created":"2020-04-27","cited_by_count":70},{"id":"1811.02840","title":"Neural Image Compression for Gigapixel Histopathology Image Analysis","created":"2018-11-07","cited_by_count":65},{"id":"1807.08284","title":"Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge","created":"2018-07-22","cited_by_count":61},{"id":"1809.03355","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","created":"2018-09-10","cited_by_count":56},{"id":"1703.02442","title":"Detecting Cancer Metastases on Gigapixel Pathology Images","created":"2017-03-03","cited_by_count":52},{"id":"1910.11097","title":"Deep Learning for Whole Slide Image Analysis: An Overview","created":"2019-10-18","cited_by_count":51},{"id":"2003.04852","title":"PANDA: A Gigapixel-level Human-centric Video Dataset","created":"2020-03-10","cited_by_count":45},{"id":"2003.00425","title":"Learning When and Where to Zoom with Deep Reinforcement Learning","created":"2020-03-01","cited_by_count":43},{"id":"2003.12783","title":"CNN-based Density Estimation and Crowd Counting: A Survey","created":"2020-03-28","cited_by_count":43},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42},{"id":"2103.15726","title":"Slimmable Compressive Autoencoders for Practical Neural Image Compression","created":"2021-03-29","cited_by_count":39},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39},{"id":"1811.11057","title":"Fast Object Detection in Compressed Video","created":"2018-11-27","cited_by_count":33},{"id":"1907.07156","title":"Efficient Segmentation: Learning Downsampling Near Semantic Boundaries","created":"2019-07-16","cited_by_count":33},{"id":"1907.12428","title":"Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting","created":"2019-07-29","cited_by_count":32},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32},{"id":"1808.05264","title":"DeepDownscale: a Deep Learning Strategy for High-Resolution Weather Forecast","created":"2018-08-15","cited_by_count":28},{"id":"2106.15183","title":"Multi-Exit Vision Transformer for Dynamic Inference","created":"2021-06-29","cited_by_count":28},{"id":"1805.09512","title":"You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery","created":"2018-05-24","cited_by_count":27},{"id":"2106.15754","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","created":"2021-06-29","cited_by_count":27},{"id":"2105.09121","title":"Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead","created":"2021-05-19","cited_by_count":26},{"id":"1711.05187","title":"Dynamic Zoom-in Network for Fast Object Detection in Large Images","created":"2017-11-14","cited_by_count":23},{"id":"1910.13042","title":"Deep Multi-Magnification Networks for Multi-Class Breast Cancer Image Segmentation","created":"2019-10-29","cited_by_count":22},{"id":"2109.11071","title":"Learning to Downsample for Segmentation of Ultra-High Resolution Images","created":"2021-09-22","cited_by_count":19},{"id":"2205.11269","title":"Dynamic Split Computing for Efficient Deep Edge Intelligence","created":"2022-05-23","cited_by_count":18},{"id":"2002.12256","title":"ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images","created":"2020-02-27","cited_by_count":17},{"id":"1806.03863","title":"Massively Parallel Video Networks","created":"2018-06-11","cited_by_count":16},{"id":"2005.07097","title":"Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions","created":"2020-05-14","cited_by_count":13},{"id":"2201.06268","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","created":"2022-01-17","cited_by_count":12},{"id":"2204.02397","title":"SALISA: Saliency-based Input Sampling for Efficient Video Object Detection","created":"2022-04-05","cited_by_count":12},{"id":"1807.11113","title":"Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-slide Images","created":"2018-07-29","cited_by_count":11},{"id":"1906.04445","title":"Bag of Color Features For Color Constancy","created":"2019-06-11","cited_by_count":11},{"id":"2104.10461","title":"Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning","created":"2021-04-21","cited_by_count":9},{"id":"2106.00050","title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","created":"2021-05-31","cited_by_count":9},{"id":"1709.09902","title":"Improving Efficiency in Convolutional Neural Network with Multilinear Filters","created":"2017-09-28","cited_by_count":8},{"id":"1912.07517","title":"Zoom in to where it matters: a hierarchical graph based model for mammogram analysis","created":"2019-12-16","cited_by_count":8},{"id":"2011.02018","title":"Single Image Human Proxemics Estimation for Visual Social Distancing","created":"2020-11-03","cited_by_count":8},{"id":"2204.03418","title":"Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch","created":"2022-04-07","cited_by_count":8},{"id":"2105.15078","title":"Can Attention Enable MLPs To Catch Up With CNNs?","created":"2021-05-31","cited_by_count":7}],"next_cursor":"100"}