{"list":"other","total":68,"rows":[{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231},{"id":"2104.02409","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","created":"2021-04-06","cited_by_count":224},{"id":"2008.08290","title":"Attribute Prototype Network for Zero-Shot Learning","created":"2020-08-19","cited_by_count":160},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"2001.03343","title":"RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving","created":"2020-01-10","cited_by_count":150},{"id":"1904.09117","title":"SelFlow: Self-Supervised Learning of Optical Flow","created":"2019-04-19","cited_by_count":128},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"2006.04902","title":"What Matters in Unsupervised Optical Flow","created":"2020-06-08","cited_by_count":124},{"id":"1805.03438","title":"Robust Classification with Convolutional Prototype Learning","created":"2018-05-09","cited_by_count":123},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107},{"id":"2105.14021","title":"Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging","created":"2021-05-28","cited_by_count":104},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","cited_by_count":98},{"id":"2208.02245","title":"MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training","created":"2022-08-03","cited_by_count":94},{"id":"2103.12605","title":"MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation","created":"2021-03-23","cited_by_count":82},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80},{"id":"1803.11029","title":"Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation","created":"2018-03-29","cited_by_count":78},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"1811.10742","title":"Joint Monocular 3D Vehicle Detection and Tracking","created":"2018-11-26","cited_by_count":77},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64},{"id":"2204.07616","title":"Multi-Frame Self-Supervised Depth with Transformers","created":"2022-04-15","cited_by_count":64},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57},{"id":"2207.04718","title":"Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches","created":"2022-07-11","cited_by_count":57},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56},{"id":"1808.04699","title":"Improving Generalization via Scalable Neighborhood Component Analysis","created":"2018-08-14","cited_by_count":53},{"id":"1705.08182","title":"Unmasking the abnormal events in video","created":"2017-05-23","cited_by_count":48},{"id":"2204.00330","title":"DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow","created":"2022-04-01","cited_by_count":40},{"id":"2202.03857","title":"Learning Optical Flow with Adaptive Graph Reasoning","created":"2022-02-08","cited_by_count":33},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33},{"id":"2303.08384","title":"Rethinking Optical Flow from Geometric Matching Consistent Perspective","created":"2023-03-15","cited_by_count":33},{"id":"2112.00202","title":"3DVNet: Multi-View Depth Prediction and Volumetric Refinement","created":"2021-12-01","cited_by_count":21},{"id":"2208.09686","title":"YOLOV: Making Still Image Object Detectors Great at Video Object Detection","created":"2022-08-20","cited_by_count":18},{"id":"1512.01192","title":"Prototypical Priors: From Improving Classification to Zero-Shot Learning","created":"2015-12-03","cited_by_count":14},{"id":"2311.00987","title":"CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","created":"2023-11-02","cited_by_count":9}],"next_cursor":null}