{"total":58,"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":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"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":"2506.03143","title":"GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents","created":"2025-06-03","cited_by_count":95,"area":"agents"},{"id":"2104.04329","title":"Learning Position and Target Consistency for Memory-based Video Object Segmentation","created":"2021-04-09","cited_by_count":63,"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":"2112.02363","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","created":"2021-12-04","cited_by_count":47,"area":null},{"id":"2102.12152","title":"Dual-Awareness Attention for Few-Shot Object Detection","created":"2021-02-24","cited_by_count":29,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2207.12659","title":"Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds","created":"2022-07-26","cited_by_count":17,"area":null},{"id":"2107.14209","title":"A Unified Efficient Pyramid Transformer for Semantic Segmentation","created":"2021-07-29","cited_by_count":14,"area":null},{"id":"2111.11057","title":"Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images","created":"2021-11-22","cited_by_count":12,"area":null},{"id":"2207.04044","title":"kMaX-DeepLab: k-means Mask Transformer","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2103.03768","title":"VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2021-03-05","cited_by_count":11,"area":null},{"id":"2108.00150","title":"Deep Image-based Illumination Harmonization","created":"2021-07-31","cited_by_count":11,"area":null},{"id":"2204.10482","title":"Recurrent Affine Transformation for Text-to-image Synthesis","created":"2022-04-22","cited_by_count":11,"area":null},{"id":"2101.12346","title":"Deep Triplet Hashing Network for Case-based Medical Image Retrieval","created":"2021-01-29","cited_by_count":8,"area":null},{"id":"2403.12891","title":"Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types","created":"2024-03-19","cited_by_count":8,"area":"offlinerl"},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2108.03920","title":"FA-GAN: Fused Attentive Generative Adversarial Networks for MRI Image Super-Resolution","created":"2021-08-09","cited_by_count":7,"area":null},{"id":"2203.05122","title":"DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting","created":"2022-03-10","cited_by_count":7,"area":null},{"id":"2305.02722","title":"Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty","created":"2023-05-04","cited_by_count":7,"area":"distill"},{"id":"2503.20268","title":"EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation","created":"2025-03-26","cited_by_count":6,"area":"diffusion"},{"id":"2604.18348","title":"AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation","created":"2026-04-20","cited_by_count":6,"area":"diffusion"},{"id":"2109.05265","title":"Advancing Autonomous Driving: DepthSense with Radar and Spatial Attention","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2112.09569","title":"CPPE-5: Medical Personal Protective Equipment Dataset","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2308.02213","title":"Balanced Classification: A Unified Framework for Long-Tailed Object Detection","created":"2023-08-04","cited_by_count":5,"area":null},{"id":"2406.04589","title":"MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancement","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2406.16928","title":"A Multi-Resolution Mutual Learning Network for Multi-Label ECG Classification","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2501.02749","title":"Intelligent logistics management robot path planning algorithm integrating transformer and GCN network","created":"2025-01-06","cited_by_count":4,"area":null},{"id":"2302.14557","title":"GRAN: Ghost Residual Attention Network for Single Image Super Resolution","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2606.04032","title":"Do Transformers Need Three Projections? Systematic Study of QKV Variants","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2212.14742","title":"DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation","created":"2022-12-30","cited_by_count":2,"area":null},{"id":"2304.06345","title":"ASR: Attention-alike Structural Re-parameterization","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2306.14269","title":"Weakly Supervised Scene Text Generation for Low-resource Languages","created":"2023-06-25","cited_by_count":2,"area":null},{"id":"2106.04996","title":"Salient Positions based Attention Network for Image Classification","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2112.03205","title":"Simultaneously Predicting Multiple Plant Traits from Multiple Sensors via Deformable CNN Regression","created":"2021-12-06","cited_by_count":1,"area":null},{"id":"2205.02125","title":"Engineering deep learning methods on automatic detection of damage in infrastructure due to extreme events","created":"2022-05-01","cited_by_count":1,"area":null},{"id":"2109.01915","title":"Sparse Spatial Attention Network for Semantic Segmentation","created":"2021-09-04","cited_by_count":0,"area":null},{"id":"2203.06318","title":"Deformable VisTR: Spatio temporal deformable attention for video instance segmentation","created":"2022-03-12","cited_by_count":0,"area":null},{"id":"2206.13383","title":"Mushroom image recognition and distance generation based on attention-mechanism model and genetic information","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2207.00188","title":"Rethinking Query-Key Pairwise Interactions in Vision Transformers","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2210.10998","title":"Semi-supervised object detection based on single-stage detector for thighbone fracture localization","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2402.10752","title":"STF: Spatio-Temporal Fusion Module for Improving Video Object Detection","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2403.04478","title":"Improved Focus on Hard Samples for Lung Nodule Detection","created":"2024-03-07","cited_by_count":0,"area":null},{"id":"2406.18313","title":"Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learning","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2410.08794","title":"M$^3$-Impute: Mask-guided Representation Learning for Missing Value Imputation","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2502.01445","title":"SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2502.16762","title":"A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image Recognition","created":"2025-02-24","cited_by_count":0,"area":"distill"},{"id":"2506.08612","title":"Data-Efficient Challenges in Visual Inductive Priors: A Retrospective","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2511.20800","title":"Intriguing Properties of Dynamic Sampling Networks","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.00189","title":"LPIPS-AttnWav2Lip: Generic Audio-Driven lip synchronization for Talking Head Generation in the Wild","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.17222","title":"Region-Affinity Attention for Whole-Slide Breast Cancer Classification in Deep Ultraviolet Imaging","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2606.15118","title":"Multi-view feature High-order Fusion for Space Weak Object Detection and Segmentation","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.00057","title":"Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}