{"list":"other","total":98,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"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":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2005.00305","title":"Defocus Deblurring Using Dual-Pixel Data","created":"2020-05-01","cited_by_count":139},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"1909.05483","title":"3D Ken Burns Effect from a Single Image","created":"2019-09-12","cited_by_count":128},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"1810.08705","title":"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing","created":"2018-10-19","cited_by_count":106},{"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":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94},{"id":"2010.16188","title":"Bridging Composite and Real: Towards End-to-end Deep Image Matting","created":"2020-10-30","cited_by_count":89},{"id":"2403.13788","title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","created":"2024-03-20","cited_by_count":76},{"id":"1904.02028","title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","created":"2019-04-03","cited_by_count":75},{"id":"2403.07392","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","created":"2024-03-12","cited_by_count":66},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60},{"id":"1905.08598","title":"SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation","created":"2019-05-21","cited_by_count":59},{"id":"2105.09180","title":"PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency","created":"2021-05-19","cited_by_count":59},{"id":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48},{"id":"2206.12614","title":"BokehMe: When Neural Rendering Meets Classical Rendering","created":"2022-06-25","cited_by_count":48},{"id":"2211.11592","title":"Guided Depth Super-Resolution by Deep Anisotropic Diffusion","created":"2022-11-21","cited_by_count":46},{"id":"2312.02284","title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","created":"2023-12-04","cited_by_count":41},{"id":"2312.12176","title":"All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes","created":"2023-12-19","cited_by_count":41},{"id":"2002.12730","title":"Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields","created":"2020-02-28","cited_by_count":40},{"id":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33},{"id":"2011.04389","title":"EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes","created":"2020-11-09","cited_by_count":30},{"id":"2312.13252","title":"Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model","created":"2023-12-20","cited_by_count":29},{"id":"2302.09598","title":"Guided Depth Map Super-resolution: A Survey","created":"2023-02-19","cited_by_count":23},{"id":"2307.10713","title":"Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV","created":"2023-07-20","cited_by_count":21},{"id":"2208.01489","title":"Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter","created":"2022-08-02","cited_by_count":18},{"id":"2309.14291","title":"Tiled Multiplane Images for Practical 3D Photography","created":"2023-09-25","cited_by_count":14},{"id":"1912.09678","title":"IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation","created":"2019-12-20","cited_by_count":13},{"id":"2304.04672","title":"Deep Image Matting: A Comprehensive Survey","created":"2023-04-10","cited_by_count":12},{"id":"2204.10211","title":"SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis","created":"2022-04-21","cited_by_count":7},{"id":"2403.01569","title":"Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV","created":"2024-03-03","cited_by_count":7},{"id":"2309.09724","title":"Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering","created":"2023-09-18","cited_by_count":6}],"next_cursor":null}