{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61},{"id":"2208.00406","title":"Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AI","created":"2022-07-31","cited_by_count":58},{"id":"2110.11822","title":"Unraveling the Hidden Environmental Impacts of AI Solutions for Environment","created":"2021-10-22","cited_by_count":32},{"id":"1902.00267","title":"ColorNet: Investigating the importance of color spaces for image classification","created":"2019-02-01","cited_by_count":31},{"id":"2305.03123","title":"ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review","created":"2023-04-13","cited_by_count":28},{"id":"2203.02202","title":"Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis","created":"2022-03-04","cited_by_count":18},{"id":"2303.13972","title":"Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI","created":"2023-03-24","cited_by_count":16},{"id":"2102.07887","title":"VA-RED$^2$: Video Adaptive Redundancy Reduction","created":"2021-02-15","cited_by_count":15},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14},{"id":"2201.10394","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","created":"2022-01-25","cited_by_count":10},{"id":"2304.00897","title":"Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models","created":"2023-04-03","cited_by_count":9},{"id":"2306.04822","title":"Optimizing ViViT Training: Time and Memory Reduction for Action Recognition","created":"2023-06-07","cited_by_count":4}],"next_cursor":null}