{"total":1355,"rows":[{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2203.10638","title":"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer","created":"2022-03-20","cited_by_count":320,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2203.08414","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","created":"2022-03-16","cited_by_count":241,"area":null},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2207.02202","title":"CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers","created":"2022-07-05","cited_by_count":227,"area":null},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203,"area":null},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183,"area":null},{"id":"2106.07286","title":"TimeLens: Event-based Video Frame Interpolation","created":"2021-06-14","cited_by_count":151,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140,"area":null},{"id":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136,"area":null},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2207.07361","title":"Registration based Few-Shot Anomaly Detection","created":"2022-07-15","cited_by_count":133,"area":null},{"id":"2104.00670","title":"Unconstrained Scene Generation with Locally Conditioned Radiance Fields","created":"2021-04-01","cited_by_count":130,"area":null},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128,"area":null},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2304.03608","title":"ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation","created":"2023-04-07","cited_by_count":121,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2104.02300","title":"Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression","created":"2021-04-06","cited_by_count":112,"area":null},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","cited_by_count":111,"area":null},{"id":"2203.17191","title":"Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion","created":"2022-03-31","cited_by_count":111,"area":null},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2103.16050","title":"Progressive Domain Expansion Network for Single Domain Generalization","created":"2021-03-30","cited_by_count":97,"area":null},{"id":"2207.11770","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","created":"2022-07-24","cited_by_count":97,"area":null},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96,"area":null},{"id":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90,"area":null},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90,"area":null},{"id":"2104.06468","title":"ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration","created":"2021-04-13","cited_by_count":87,"area":null},{"id":"2108.13610","title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","created":"2021-08-31","cited_by_count":86,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2205.11876","title":"Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration","created":"2022-05-24","cited_by_count":80,"area":null},{"id":"2209.08290","title":"Changer: Feature Interaction is What You Need for Change Detection","created":"2022-09-17","cited_by_count":79,"area":null},{"id":"2210.04142","title":"Deep Clustering: A Comprehensive Survey","created":"2022-10-09","cited_by_count":78,"area":null},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75,"area":null},{"id":"2406.09624","title":"DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks","created":"2024-06-13","cited_by_count":75,"area":null},{"id":"2303.03988","title":"DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video","created":"2023-03-07","cited_by_count":74,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2112.08122","title":"Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue","created":"2021-12-15","cited_by_count":72,"area":null},{"id":"2105.14804","title":"Scene-aware Generative Network for Human Motion Synthesis","created":"2021-05-31","cited_by_count":70,"area":null},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70,"area":null},{"id":"2304.10628","title":"HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer","created":"2023-04-20","cited_by_count":70,"area":null},{"id":"2103.15537","title":"Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization","created":"2021-03-29","cited_by_count":69,"area":null},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2203.02910","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","created":"2022-03-06","cited_by_count":68,"area":null},{"id":"2302.02515","title":"Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2209.15179","title":"Physical Adversarial Attack meets Computer Vision: A Decade Survey","created":"2022-09-30","cited_by_count":67,"area":null},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65,"area":null},{"id":"2206.13295","title":"Diffusion Deformable Model for 4D Temporal Medical Image Generation","created":"2022-06-27","cited_by_count":65,"area":null},{"id":"2207.09161","title":"Single Stage Virtual Try-on via Deformable Attention Flows","created":"2022-07-19","cited_by_count":65,"area":null},{"id":"2303.05970","title":"Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception","created":"2023-03-10","cited_by_count":65,"area":null},{"id":"2103.04400","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","created":"2021-03-07","cited_by_count":63,"area":null},{"id":"2106.14490","title":"Making Images Real Again: A Comprehensive Survey on Deep Image Composition","created":"2021-06-28","cited_by_count":63,"area":null},{"id":"2112.13047","title":"Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation","created":"2021-12-24","cited_by_count":63,"area":null},{"id":"2103.09479","title":"Disentangled Cycle Consistency for Highly-realistic Virtual Try-On","created":"2021-03-17","cited_by_count":62,"area":null},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62,"area":null},{"id":"2301.03505","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","created":"2023-01-09","cited_by_count":62,"area":null},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61,"area":null},{"id":"2104.07434","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2107.05274","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","created":"2021-07-12","cited_by_count":60,"area":null},{"id":"2203.14675","title":"Part-based Pseudo Label Refinement for Unsupervised Person Re-identification","created":"2022-03-28","cited_by_count":59,"area":null},{"id":"2102.02629","title":"Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency","created":"2021-02-04","cited_by_count":58,"area":null},{"id":"2108.03830","title":"Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark","created":"2021-08-09","cited_by_count":58,"area":null},{"id":"2410.06245","title":"HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction","created":"2024-10-08","cited_by_count":57,"area":null},{"id":"2108.08829","title":"Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2209.07947","title":"Omni-Dimensional Dynamic Convolution","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2307.15615","title":"A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond","created":"2023-07-28","cited_by_count":55,"area":null},{"id":"2301.10941","title":"GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency","created":"2023-01-26","cited_by_count":54,"area":null},{"id":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54,"area":null},{"id":"2112.15093","title":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","created":"2021-12-30","cited_by_count":53,"area":null},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"area":null},{"id":"2409.12753","title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","created":"2024-09-19","cited_by_count":53,"area":null},{"id":"2102.03725","title":"I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modeling","created":"2021-02-07","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50,"area":null},{"id":"2205.13129","title":"Wireless Deep Video Semantic Transmission","created":"2022-05-26","cited_by_count":50,"area":null},{"id":"2106.12859","title":"Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images","created":"2021-06-24","cited_by_count":49,"area":null},{"id":"2103.15982","title":"TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations","created":"2021-03-29","cited_by_count":48,"area":null},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48,"area":null},{"id":"2103.14943","title":"HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset","created":"2021-03-27","cited_by_count":45,"area":null},{"id":"2104.00337","title":"Wide-Depth-Range 6D Object Pose Estimation in Space","created":"2021-04-01","cited_by_count":45,"area":null},{"id":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45,"area":null}],"next_cursor":"100"}