{"list":"other","total":54,"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"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":"1807.02547","title":"3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data","created":"2018-07-06","cited_by_count":354},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"1902.04615","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","created":"2019-02-11","cited_by_count":267},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264},{"id":"2002.12880","title":"Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data","created":"2020-02-25","cited_by_count":248},{"id":"1811.02017","title":"A General Theory of Equivariant CNNs on Homogeneous Spaces","created":"2018-11-05","cited_by_count":228},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2306.12059","title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","created":"2023-06-21","cited_by_count":204},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"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":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2207.10662","title":"Generalizable Patch-Based Neural Rendering","created":"2022-07-21","cited_by_count":122},{"id":"1905.00538","title":"DPSNet: End-to-end Deep Plane Sweep Stereo","created":"2019-05-02","cited_by_count":115},{"id":"1709.01889","title":"Polar Transformer Networks","created":"2017-09-06","cited_by_count":81},{"id":"2103.14147","title":"Equivariant Point Network for 3D Point Cloud Analysis","created":"2021-03-25","cited_by_count":81},{"id":"2002.03830","title":"Attentive Group Equivariant Convolutional Networks","created":"2020-02-07","cited_by_count":63},{"id":"2010.00977","title":"Group Equivariant Stand-Alone Self-Attention For Vision","created":"2020-10-02","cited_by_count":63},{"id":"2206.08321","title":"Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning","created":"2022-06-16","cited_by_count":56},{"id":"2006.10731","title":"Spin-Weighted Spherical CNNs","created":"2020-06-18","cited_by_count":50},{"id":"1911.10444","title":"Normal Assisted Stereo Depth Estimation","created":"2019-11-24","cited_by_count":49},{"id":"1904.00993","title":"Equivariant Multi-View Networks","created":"2019-04-01","cited_by_count":45},{"id":"2302.11556","title":"Equivariant Polynomials for Graph Neural Networks","created":"2023-02-22","cited_by_count":38},{"id":"2303.12410","title":"EDGI: Equivariant Diffusion for Planning with Embodied Agents","created":"2023-03-22","cited_by_count":36},{"id":"2211.00191","title":"Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection","created":"2022-10-31","cited_by_count":35},{"id":"2112.03243","title":"Input-level Inductive Biases for 3D Reconstruction","created":"2021-12-06","cited_by_count":31},{"id":"2010.11661","title":"Efficient Generalized Spherical CNNs","created":"2020-10-09","cited_by_count":29},{"id":"2206.04176","title":"VN-Transformer: Rotation-Equivariant Attention for Vector Neurons","created":"2022-06-08","cited_by_count":27},{"id":"2111.08251","title":"Enabling equivariance for arbitrary Lie groups","created":"2021-11-16","cited_by_count":22},{"id":"2306.05420","title":"Scaling Spherical CNNs","created":"2023-06-08","cited_by_count":21},{"id":"2206.08362","title":"Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces","created":"2022-06-16","cited_by_count":20},{"id":"2203.17178","title":"3D Equivariant Graph Implicit Functions","created":"2022-03-31","cited_by_count":18},{"id":"2303.14548","title":"Viewpoint Equivariance for Multi-View 3D Object Detection","created":"2023-03-25","cited_by_count":18},{"id":"2206.05398","title":"E2PN: Efficient SE(3)-Equivariant Point Network","created":"2022-06-11","cited_by_count":17},{"id":"2207.14287","title":"Depth Field Networks for Generalizable Multi-view Scene Representation","created":"2022-07-28","cited_by_count":17},{"id":"2311.02922","title":"Truly Scale-Equivariant Deep Nets with Fourier Layers","created":"2023-11-06","cited_by_count":16},{"id":"2304.00947","title":"RePAST: Relative Pose Attention Scene Representation Transformer","created":"2023-04-03","cited_by_count":8}],"next_cursor":null}