{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"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":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"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":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"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":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"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":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173},{"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":"1510.05970","title":"Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches","created":"2015-10-20","cited_by_count":151},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"2403.00486","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","created":"2024-03-01","cited_by_count":99},{"id":"1811.01343","title":"Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset","created":"2018-11-04","cited_by_count":93},{"id":"1812.06264","title":"Hierarchical Discrete Distribution Decomposition for Match Density Estimation","created":"2018-12-15","cited_by_count":93},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87},{"id":"2402.05892","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","created":"2024-02-08","cited_by_count":84},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82},{"id":"2405.15364","title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","created":"2024-05-24","cited_by_count":79},{"id":"1409.4326","title":"Computing the Stereo Matching Cost with a Convolutional Neural Network","created":"2014-09-15","cited_by_count":74},{"id":"2006.12797","title":"PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching","created":"2020-06-23","cited_by_count":62},{"id":"2209.12699","title":"Accurate and Efficient Stereo Matching via Attention Concatenation Volume","created":"2022-09-23","cited_by_count":59},{"id":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54},{"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":"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":"1803.05196","title":"EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching","created":"2018-03-14","cited_by_count":32},{"id":"2312.12471","title":"Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion","created":"2023-12-19","cited_by_count":28},{"id":"2308.00728","title":"ELFNet: Evidential Local-global Fusion for Stereo Matching","created":"2023-08-01","cited_by_count":25},{"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":"2302.12772","title":"FLSea: Underwater Visual-Inertial and Stereo-Vision Forward-Looking Datasets","created":"2023-02-24","cited_by_count":21},{"id":"2312.14650","title":"Global Occlusion-Aware Transformer for Robust Stereo Matching","created":"2023-12-22","cited_by_count":19},{"id":"2203.04554","title":"ChiTransformer:Towards Reliable Stereo from Cues","created":"2022-03-09","cited_by_count":14},{"id":"2309.04183","title":"Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality","created":"2023-09-08","cited_by_count":14},{"id":"2402.19270","title":"Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching","created":"2024-02-29","cited_by_count":11},{"id":"2509.16415","title":"StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes","created":"2025-09-19","cited_by_count":9},{"id":"2309.00933","title":"Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation","created":"2023-09-02","cited_by_count":8},{"id":"2409.01782","title":"UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching","created":"2024-09-03","cited_by_count":7},{"id":"2103.07798","title":"ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images","created":"2021-03-13","cited_by_count":5},{"id":"2601.02760","title":"AnyDepth: Depth Estimation Made Easy","created":"2026-01-06","cited_by_count":5}],"next_cursor":null}