{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"id":"2303.06615","title":"Iterative Geometry Encoding Volume for Stereo Matching","created":"2023-03-12","cited_by_count":190},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"2208.14201","title":"ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer","created":"2022-08-30","cited_by_count":171},{"id":"1911.12012","title":"Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness","created":"2019-11-27","cited_by_count":151},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113},{"id":"2008.07928","title":"Visibility-aware Multi-view Stereo Network","created":"2020-08-18","cited_by_count":98},{"id":"2201.01501","title":"Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation","created":"2022-01-05","cited_by_count":82},{"id":"2007.10872","title":"Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking","created":"2020-07-21","cited_by_count":81},{"id":"2108.03824","title":"AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network","created":"2021-08-09","cited_by_count":71},{"id":"1912.11746","title":"Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume","created":"2019-12-26","cited_by_count":59},{"id":"2208.02541","title":"MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth","created":"2022-08-04","cited_by_count":53},{"id":"2204.07346","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","created":"2022-04-15","cited_by_count":50},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45},{"id":"2303.08384","title":"Rethinking Optical Flow from Geometric Matching Consistent Perspective","created":"2023-03-15","cited_by_count":33},{"id":"2112.02338","title":"Generalized Binary Search Network for Highly-Efficient Multi-View Stereo","created":"2021-12-04","cited_by_count":32},{"id":"2205.14319","title":"WT-MVSNet: Window-based Transformers for Multi-view Stereo","created":"2022-05-28","cited_by_count":20},{"id":"2112.05999","title":"Curvature-guided dynamic scale networks for Multi-view Stereo","created":"2021-12-11","cited_by_count":17},{"id":"2205.03783","title":"Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo","created":"2022-05-08","cited_by_count":15},{"id":"2303.02885","title":"Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints","created":"2023-03-06","cited_by_count":15},{"id":"2307.10233","title":"RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo","created":"2023-07-16","cited_by_count":15},{"id":"2205.14320","title":"RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo","created":"2022-05-28","cited_by_count":12},{"id":"2305.10320","title":"CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo","created":"2023-05-17","cited_by_count":9},{"id":"2307.09160","title":"Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells","created":"2023-07-18","cited_by_count":8},{"id":"2308.09022","title":"ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval","created":"2023-08-17","cited_by_count":2}],"next_cursor":null}