{"list":"other","total":114,"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":"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1907.07374","title":"A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI","created":"2019-07-17","cited_by_count":404},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"1701.07717","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","created":"2017-01-26","cited_by_count":281},{"id":"1708.02709","title":"Recent Trends in Deep Learning Based Natural Language Processing","created":"2017-08-09","cited_by_count":263},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178},{"id":"2105.01288","title":"Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis","created":"2021-05-04","cited_by_count":172},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"id":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131},{"id":"1810.05591","title":"PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention","created":"2018-10-12","cited_by_count":105},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104},{"id":"1811.01900","title":"Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs","created":"2018-11-05","cited_by_count":98},{"id":"1901.09006","title":"On the Limitations of Representing Functions on Sets","created":"2019-01-25","cited_by_count":90},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2103.15619","title":"SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data","created":"2021-03-29","cited_by_count":78},{"id":"2301.08739","title":"FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer","created":"2023-01-20","cited_by_count":73},{"id":"1906.06565","title":"Deep Set Prediction Networks","created":"2019-06-15","cited_by_count":71},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"1906.02795","title":"FSPool: Learning Set Representations with Featurewise Sort Pooling","created":"2019-06-06","cited_by_count":53},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46},{"id":"2111.00207","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","created":"2021-10-30","cited_by_count":43},{"id":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35},{"id":"1511.05263","title":"The Use of Machine Learning Algorithms in Recommender Systems: A Systematic Review","created":"2015-11-17","cited_by_count":27},{"id":"2209.00517","title":"The Neural Process Family: Survey, Applications and Perspectives","created":"2022-09-01","cited_by_count":23},{"id":"2010.03242","title":"Scalable Normalizing Flows for Permutation Invariant Densities","created":"2020-10-07","cited_by_count":22},{"id":"2111.12193","title":"Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation","created":"2021-11-23","cited_by_count":17},{"id":"2206.11925","title":"Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets","created":"2022-06-23","cited_by_count":17},{"id":"2301.13197","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","created":"2023-01-30","cited_by_count":16},{"id":"1903.07348","title":"On Deep Set Learning and the Choice of Aggregations","created":"2019-03-18","cited_by_count":13},{"id":"1807.11206","title":"Hard-Aware Point-to-Set Deep Metric for Person Re-identification","created":"2018-07-30","cited_by_count":12},{"id":"2010.04109","title":"Set Prediction without Imposing Structure as Conditional Density Estimation","created":"2020-10-08","cited_by_count":12},{"id":"2112.03568","title":"Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints","created":"2021-12-07","cited_by_count":11},{"id":"2203.01693","title":"Learning Neural Set Functions Under the Optimal Subset Oracle","created":"2022-03-03","cited_by_count":10},{"id":"2003.11794","title":"Compact Deep Aggregation for Set Retrieval","created":"2020-03-26","cited_by_count":8},{"id":"1707.09173","title":"Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding","created":"2017-07-28","cited_by_count":7}],"next_cursor":"100"}