{"list":"other","total":66,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"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":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"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":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"1904.06587","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","created":"2019-04-13","cited_by_count":244},{"id":"1809.10790","title":"Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects","created":"2018-09-27","cited_by_count":241},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2004.09548","title":"AANet: Adaptive Aggregation Network for Efficient Stereo Matching","created":"2020-04-20","cited_by_count":202},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","cited_by_count":197},{"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":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"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":"2010.13501","title":"Hierarchical Neural Architecture Search for Deep Stereo Matching","created":"2020-10-26","cited_by_count":166},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"2104.04314","title":"CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching","created":"2021-04-09","cited_by_count":154},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2203.02146","title":"Attention Concatenation Volume for Accurate and Efficient Stereo Matching","created":"2022-03-04","cited_by_count":130},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"2206.10589","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","created":"2022-06-21","cited_by_count":121},{"id":"2007.12140","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","created":"2020-07-23","cited_by_count":120},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"1911.13287","title":"Domain-invariant Stereo Matching Networks","created":"2019-11-29","cited_by_count":109},{"id":"2403.00486","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","created":"2024-03-01","cited_by_count":99},{"id":"1804.06534","title":"Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation","created":"2018-04-18","cited_by_count":92},{"id":"2006.12797","title":"PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching","created":"2020-06-23","cited_by_count":62},{"id":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59},{"id":"2404.06842","title":"MoCha-Stereo: Motif Channel Attention Network for Stereo Matching","created":"2024-04-10","cited_by_count":48},{"id":"2108.05773","title":"Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation","created":"2021-08-12","cited_by_count":47},{"id":"2412.04472","title":"Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail","created":"2024-12-05","cited_by_count":47},{"id":"2204.00179","title":"GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature","created":"2022-04-01","cited_by_count":43},{"id":"2403.11193","title":"Neural Markov Random Field for Stereo Matching","created":"2024-03-17","cited_by_count":40},{"id":"2201.02263","title":"ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks","created":"2022-01-06","cited_by_count":39},{"id":"2210.11719","title":"Context-Enhanced Stereo Transformer","created":"2022-10-21","cited_by_count":37},{"id":"2307.14071","title":"Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching","created":"2023-07-26","cited_by_count":37},{"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":"2304.00152","title":"Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation","created":"2023-03-31","cited_by_count":23},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20},{"id":"2402.19270","title":"Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching","created":"2024-02-29","cited_by_count":11}],"next_cursor":null}