{"total":304,"rows":[{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764,"area":null},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303,"area":null},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212,"area":null},{"id":"2103.14635","title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","created":"2021-03-26","cited_by_count":211,"area":null},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184,"area":null},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182,"area":null},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176,"area":null},{"id":"2101.06742","title":"Deep Parametric Continuous Convolutional Neural Networks","created":"2021-01-17","cited_by_count":161,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2308.09244","title":"SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos","created":"2023-08-18","cited_by_count":150,"area":null},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128,"area":null},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2105.05003","title":"CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution","created":"2021-05-11","cited_by_count":95,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2105.10422","title":"LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond","created":"2021-05-21","cited_by_count":88,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","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":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2107.00358","title":"Cross-domain Few-shot Learning with Task-specific Adapters","created":"2021-07-01","cited_by_count":80,"area":null},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79,"area":null},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74,"area":null},{"id":"2202.09769","title":"Dynamic Spatial Propagation Network for Depth Completion","created":"2022-02-20","cited_by_count":71,"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":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68,"area":null},{"id":"2312.17118","title":"Fully Sparse 3D Occupancy Prediction","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","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":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61,"area":null},{"id":"2108.08035","title":"Adaptive Graph Convolution for Point Cloud Analysis","created":"2021-08-18","cited_by_count":60,"area":null},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60,"area":null},{"id":"2203.15737","title":"Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version","created":"2022-03-29","cited_by_count":59,"area":null},{"id":"2308.15085","title":"Learning to Upsample by Learning to Sample","created":"2023-08-29","cited_by_count":57,"area":null},{"id":"2209.07947","title":"Omni-Dimensional Dynamic Convolution","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2103.02243","title":"MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions","created":"2021-03-03","cited_by_count":54,"area":null},{"id":"2104.00032","title":"Convolutional Dynamic Alignment Networks for Interpretable Classifications","created":"2021-03-31","cited_by_count":54,"area":null},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53,"area":null},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51,"area":null},{"id":"2207.08351","title":"SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement","created":"2022-07-18","cited_by_count":50,"area":null},{"id":"2310.08956","title":"LRRU: Long-short Range Recurrent Updating Networks for Depth Completion","created":"2023-10-13","cited_by_count":49,"area":null},{"id":"2204.00367","title":"Learning to Deblur using Light Field Generated and Real Defocus Images","created":"2022-04-01","cited_by_count":46,"area":null},{"id":"2109.07053","title":"Image Synthesis via Semantic Composition","created":"2021-09-15","cited_by_count":45,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44,"area":null},{"id":"2403.14418","title":"OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation","created":"2024-03-21","cited_by_count":44,"area":null},{"id":"2204.10638","title":"Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation","created":"2022-04-22","cited_by_count":43,"area":null},{"id":"2103.13582","title":"Learning Dynamic Alignment via Meta-filter for Few-shot Learning","created":"2021-03-25","cited_by_count":41,"area":null},{"id":"2307.14187","title":"ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation","created":"2023-07-26","cited_by_count":41,"area":null},{"id":"2201.03808","title":"MobileFaceSwap: A Lightweight Framework for Video Face Swapping","created":"2022-01-11","cited_by_count":39,"area":null},{"id":"2305.06382","title":"HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks","created":"2023-05-10","cited_by_count":37,"area":null},{"id":"2110.06178","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","created":"2021-10-12","cited_by_count":36,"area":null},{"id":"2207.07372","title":"3D Instances as 1D Kernels","created":"2022-07-15","cited_by_count":36,"area":null},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35,"area":null},{"id":"2210.06323","title":"AISFormer: Amodal Instance Segmentation with Transformer","created":"2022-10-12","cited_by_count":35,"area":null},{"id":"2306.04652","title":"Language Adaptive Weight Generation for Multi-task Visual Grounding","created":"2023-06-06","cited_by_count":35,"area":null},{"id":"2104.06624","title":"Device-Cloud Collaborative Learning for Recommendation","created":"2021-04-14","cited_by_count":34,"area":null},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34,"area":null},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34,"area":null},{"id":"2203.01853","title":"Efficient Video Instance Segmentation via Tracklet Query and Proposal","created":"2022-03-03","cited_by_count":33,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null},{"id":"2107.10433","title":"MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking","created":"2021-07-22","cited_by_count":32,"area":null},{"id":"2108.02760","title":"SLAMP: Stochastic Latent Appearance and Motion Prediction","created":"2021-08-05","cited_by_count":32,"area":null},{"id":"2308.09891","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","created":"2023-08-19","cited_by_count":32,"area":null},{"id":"2104.09556","title":"Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network","created":"2021-04-19","cited_by_count":31,"area":null},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31,"area":null},{"id":"2109.06548","title":"Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging","created":"2021-09-14","cited_by_count":31,"area":null},{"id":"2103.16748","title":"Dual Contrastive Loss and Attention for GANs","created":"2021-03-31","cited_by_count":30,"area":null},{"id":"2208.02879","title":"PointConvFormer: Revenge of the Point-based Convolution","created":"2022-08-04","cited_by_count":30,"area":null},{"id":"2211.12051","title":"Adaptive Dynamic Filtering Network for Image Denoising","created":"2022-11-22","cited_by_count":28,"area":null},{"id":"2401.03707","title":"FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring","created":"2024-01-08","cited_by_count":28,"area":null},{"id":"2104.10325","title":"SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation","created":"2021-04-21","cited_by_count":27,"area":null},{"id":"2112.06988","title":"Event-guided Deblurring of Unknown Exposure Time Videos","created":"2021-12-13","cited_by_count":26,"area":null},{"id":"2110.00338","title":"Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2110.14961","title":"Roto-translated Local Coordinate Frames For Interacting Dynamical Systems","created":"2021-10-28","cited_by_count":24,"area":null},{"id":"2206.02850","title":"GLF-CR: SAR-Enhanced Cloud Removal with Global-Local Fusion","created":"2022-06-06","cited_by_count":24,"area":null},{"id":"2308.01265","title":"Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives","created":"2023-07-18","cited_by_count":24,"area":null},{"id":"2103.02433","title":"Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms","created":"2021-03-03","cited_by_count":23,"area":null},{"id":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2104.09762","title":"Learning Semantic-Aware Dynamics for Video Prediction","created":"2021-04-20","cited_by_count":21,"area":null},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2203.14949","title":"Controllable Dynamic Multi-Task Architectures","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2210.15461","title":"LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20,"area":null},{"id":"2112.03740","title":"Dilated convolution with learnable spacings","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2204.11448","title":"High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation","created":"2022-04-25","cited_by_count":20,"area":null},{"id":"2404.07543","title":"Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2102.03026","title":"Instance and Panoptic Segmentation Using Conditional Convolutions","created":"2021-02-05","cited_by_count":19,"area":null},{"id":"2211.11679","title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","created":"2022-11-21","cited_by_count":19,"area":null}],"next_cursor":"100"}