{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"2009.11732","title":"A Unifying Review of Deep and Shallow Anomaly Detection","created":"2020-09-24","cited_by_count":425},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168},{"id":"1506.07285","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","created":"2015-06-24","cited_by_count":117},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93},{"id":"2208.14743","title":"SimpleRecon: 3D Reconstruction Without 3D Convolutions","created":"2022-08-31","cited_by_count":83},{"id":"2211.13319","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","created":"2022-11-23","cited_by_count":76},{"id":"2001.02613","title":"Don't Forget The Past: Recurrent Depth Estimation from Monocular Video","created":"2020-01-08","cited_by_count":71},{"id":"1901.02571","title":"Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera","created":"2019-01-09","cited_by_count":69},{"id":"1908.03706","title":"Exploiting temporal consistency for real-time video depth estimation","created":"2019-08-10","cited_by_count":61},{"id":"2011.13118","title":"Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks","created":"2020-11-26","cited_by_count":59},{"id":"1901.04713","title":"Global-to-local Memory Pointer Networks for Task-Oriented Dialogue","created":"2019-01-15","cited_by_count":47},{"id":"2003.13246","title":"Memory Aggregation Networks for Efficient Interactive Video Object Segmentation","created":"2020-03-30","cited_by_count":40},{"id":"2204.05289","title":"Towards Online Domain Adaptive Object Detection","created":"2022-04-11","cited_by_count":36},{"id":"1704.06485","title":"Attend to You: Personalized Image Captioning with Context Sequence Memory Networks","created":"2017-04-21","cited_by_count":35},{"id":"1808.00529","title":"Open Category Detection with PAC Guarantees","created":"2018-08-01","cited_by_count":35},{"id":"1906.11888","title":"Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks","created":"2019-06-09","cited_by_count":32},{"id":"2208.00380","title":"Less is More: Consistent Video Depth Estimation with Masked Frames Modeling","created":"2022-07-31","cited_by_count":30},{"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":"2204.07262","title":"Imposing Consistency for Optical Flow Estimation","created":"2022-04-14","cited_by_count":24},{"id":"1912.12874","title":"Video Depth Estimation by Fusing Flow-to-Depth Proposals","created":"2019-12-30","cited_by_count":23},{"id":"2207.04535","title":"Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion","created":"2022-07-10","cited_by_count":21},{"id":"2302.08149","title":"URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation","created":"2023-02-16","cited_by_count":16},{"id":"2303.16891","title":"Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations","created":"2023-03-29","cited_by_count":16},{"id":"2304.03369","title":"EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation","created":"2023-04-06","cited_by_count":16},{"id":"2303.14078","title":"DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling","created":"2023-03-24","cited_by_count":14},{"id":"2110.12516","title":"X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation","created":"2021-10-24","cited_by_count":12},{"id":"1909.07074","title":"Temporally Consistent Depth Prediction with Flow-Guided Memory Units","created":"2019-09-16","cited_by_count":10},{"id":"2204.05370","title":"Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation","created":"2022-04-11","cited_by_count":9},{"id":"2303.01573","title":"DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction","created":"2023-03-02","cited_by_count":9},{"id":"2306.05691","title":"DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow","created":"2023-06-09","cited_by_count":7},{"id":"2302.14611","title":"TransAdapt: A Transformative Framework for Online Test Time Adaptive Semantic Segmentation","created":"2023-02-24","cited_by_count":6},{"id":"2209.11350","title":"Oracle Analysis of Representations for Deep Open Set Detection","created":"2022-09-22","cited_by_count":3}],"next_cursor":null}