{"list":"other","total":59,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"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":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1711.07837","title":"UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss","created":"2017-11-21","cited_by_count":202},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"1712.02616","title":"In-Place Activated BatchNorm for Memory-Optimized Training of DNNs","created":"2017-12-07","cited_by_count":81},{"id":"1904.11112","title":"Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes","created":"2019-04-25","cited_by_count":73},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69},{"id":"2002.11433","title":"Efficient Semantic Video Segmentation with Per-frame Inference","created":"2020-02-26","cited_by_count":63},{"id":"1908.03706","title":"Exploiting temporal consistency for real-time video depth estimation","created":"2019-08-10","cited_by_count":61},{"id":"2001.00987","title":"DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling","created":"2019-12-24","cited_by_count":60},{"id":"2108.01166","title":"Consistent Depth of Moving Objects in Video","created":"2021-08-02","cited_by_count":56},{"id":"2211.03660","title":"SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes","created":"2022-11-07","cited_by_count":52},{"id":"2102.08643","title":"Temporal Memory Attention for Video Semantic Segmentation","created":"2021-02-17","cited_by_count":50},{"id":"2206.12614","title":"BokehMe: When Neural Rendering Meets Classical Rendering","created":"2022-06-25","cited_by_count":48},{"id":"2006.02708","title":"Auto-Rectify Network for Unsupervised Indoor Depth Estimation","created":"2020-06-04","cited_by_count":39},{"id":"2104.00556","title":"Deep Two-View Structure-from-Motion Revisited","created":"2021-04-01","cited_by_count":39},{"id":"2011.10185","title":"ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis","created":"2020-11-20","cited_by_count":34},{"id":"2208.00380","title":"Less is More: Consistent Video Depth Estimation with Masked Frames Modeling","created":"2022-07-31","cited_by_count":30},{"id":"1905.06326","title":"Synthetic Defocus and Look-Ahead Autofocus for Casual Videography","created":"2019-05-15","cited_by_count":28},{"id":"2110.08192","title":"Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation","created":"2021-10-15","cited_by_count":27},{"id":"2303.08120","title":"Blind Video Deflickering by Neural Filtering with a Flawed Atlas","created":"2023-03-14","cited_by_count":27},{"id":"2111.09337","title":"Temporally Consistent Online Depth Estimation in Dynamic Scenes","created":"2021-11-17","cited_by_count":26},{"id":"2207.10436","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","created":"2022-07-21","cited_by_count":25},{"id":"2303.05724","title":"3D Cinemagraphy from a Single Image","created":"2023-03-10","cited_by_count":24},{"id":"2201.11632","title":"Deep Video Prior for Video Consistency and Propagation","created":"2022-01-27","cited_by_count":18},{"id":"2209.14819","title":"SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis","created":"2022-09-29","cited_by_count":13},{"id":"2304.07435","title":"Temporally Consistent Online Depth Estimation Using Point-Based Fusion","created":"2023-04-15","cited_by_count":12}],"next_cursor":null}