{"total":109,"rows":[{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"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":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2111.04734","title":"Mixed Transformer U-Net For Medical Image Segmentation","created":"2021-11-08","cited_by_count":95,"area":null},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75,"area":null},{"id":"2307.09323","title":"Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis","created":"2023-07-18","cited_by_count":72,"area":null},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"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":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61,"area":null},{"id":"2211.01784","title":"MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation","created":"2022-11-03","cited_by_count":59,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2109.05422","title":"Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?","created":"2021-09-12","cited_by_count":38,"area":null},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32,"area":null},{"id":"2210.07124","title":"RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer","created":"2022-10-13","cited_by_count":31,"area":null},{"id":"2105.11605","title":"TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields","created":"2021-05-25","cited_by_count":29,"area":null},{"id":"2207.06095","title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2407.03575","title":"DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification","created":"2024-07-04","cited_by_count":25,"area":null},{"id":"2108.01072","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2110.01775","title":"Deep Instance Segmentation with Automotive Radar Detection Points","created":"2021-10-05","cited_by_count":22,"area":null},{"id":"2312.17071","title":"SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation","created":"2023-12-28","cited_by_count":22,"area":null},{"id":"2409.20398","title":"AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2505.14361","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","created":"2025-05-20","cited_by_count":18,"area":"mllm"},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2106.14882","title":"Rethinking Token-Mixing MLP for MLP-based Vision Backbone","created":"2021-06-28","cited_by_count":15,"area":null},{"id":"2312.04606","title":"Urban Region Representation Learning with Attentive Fusion","created":"2023-12-07","cited_by_count":12,"area":null},{"id":"2303.09417","title":"All4One: Symbiotic Neighbour Contrastive Learning via Self-Attention and Redundancy Reduction","created":"2023-03-16","cited_by_count":11,"area":null},{"id":"2303.17778","title":"CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition","created":"2023-03-31","cited_by_count":10,"area":null},{"id":"2207.03341","title":"Softmax-free Linear Transformers","created":"2022-07-05","cited_by_count":9,"area":null},{"id":"2210.16584","title":"Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images","created":"2022-10-29","cited_by_count":8,"area":null},{"id":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2105.15078","title":"Can Attention Enable MLPs To Catch Up With CNNs?","created":"2021-05-31","cited_by_count":7,"area":null},{"id":"2206.12128","title":"Excavating RoI Attention for Underwater Object Detection","created":"2022-06-24","cited_by_count":7,"area":null},{"id":"2304.13349","title":"Discrepancy-Guided Reconstruction Learning for Image Forgery Detection","created":"2023-04-26","cited_by_count":7,"area":null},{"id":"2306.03594","title":"Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2401.15741","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","created":"2024-01-28","cited_by_count":7,"area":null},{"id":"2111.03420","title":"Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images","created":"2021-11-05","cited_by_count":6,"area":null},{"id":"2201.05739","title":"Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance","created":"2022-01-15","cited_by_count":6,"area":null},{"id":"2209.08490","title":"EMA-VIO: Deep Visual-Inertial Odometry with External Memory Attention","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2305.11392","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2403.07359","title":"FSC: Few-point Shape Completion","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2501.14413","title":"Context-CrackNet: A Context-Aware Framework for Precise Segmentation of Tiny Cracks in Pavement images","created":"2025-01-24","cited_by_count":6,"area":null},{"id":"2503.13946","title":"Is Discretization Fusion All You Need for Collaborative Perception?","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2110.02442","title":"PoNet: Pooling Network for Efficient Token Mixing in Long Sequences","created":"2021-10-06","cited_by_count":5,"area":null},{"id":"2301.00531","title":"Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification","created":"2023-01-02","cited_by_count":5,"area":null},{"id":"2311.06067","title":"Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2401.05752","title":"Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations","created":"2024-01-11","cited_by_count":5,"area":null},{"id":"2107.02174","title":"What Makes for Hierarchical Vision Transformer?","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2207.04293","title":"Attention and Self-Attention in Random Forests","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2303.01917","title":"Pyramid Pixel Context Adaption Network for Medical Image Classification with Supervised Contrastive Learning","created":"2023-03-03","cited_by_count":4,"area":null},{"id":"2303.13100","title":"PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds","created":"2023-03-23","cited_by_count":4,"area":null},{"id":"2410.19446","title":"Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2509.08205","title":"Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection","created":"2025-09-10","cited_by_count":4,"area":null},{"id":"2210.11822","title":"Valuing Vicinity: Memory attention framework for context-based semantic segmentation in histopathology","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2312.09743","title":"SLS4D: Sparse Latent Space for 4D Novel View Synthesis","created":"2023-12-15","cited_by_count":3,"area":null},{"id":"2405.21061","title":"Graph External Attention Enhanced Transformer","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2201.10753","title":"Interactive Image Inpainting Using Semantic Guidance","created":"2022-01-26","cited_by_count":2,"area":null},{"id":"2205.14477","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","created":"2022-05-28","cited_by_count":2,"area":null},{"id":"2211.10622","title":"Rethinking Batch Sample Relationships for Data Representation: A Batch-Graph Transformer based Approach","created":"2022-11-19","cited_by_count":2,"area":null},{"id":"2603.19290","title":"Neural Dynamics Self-Attention for Spiking Transformers","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2208.11108","title":"Efficient Attention-free Video Shift Transformers","created":"2022-08-23","cited_by_count":1,"area":null},{"id":"2308.07717","title":"Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2310.20305","title":"Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2408.13201","title":"EAViT: External Attention Vision Transformer for Audio Classification","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2508.21040","title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2206.01096","title":"A Dual-fusion Semantic Segmentation Framework With GAN For SAR Images","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2208.11056","title":"Enhancement Encoding: A Novel Imbalanced Classification Approach via Encoding the Training Labels","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2211.12746","title":"Completing point cloud from few points by Wasserstein GAN and Transformers","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2212.11278","title":"Decision-making and control with diffractive optical networks","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2301.06962","title":"Long Range Pooling for 3D Large-Scale Scene Understanding","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2302.03221","title":"Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2304.12596","title":"Detection of Pavement Cracks by Deep Learning Models of Transformer and UNet","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2305.15520","title":"Exploring Automatically Perturbed Natural Language Explanations in Relation Extraction","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2305.19787","title":"DeepMerge: Deep-Learning-Based Region-Merging for Image Segmentation","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2308.07110","title":"SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2309.06157","title":"Robust-MBDL: A Robust Multi-branch Deep Learning Based Model for Remaining Useful Life Prediction and Operational Condition Identification of Rotating Machines","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2309.06721","title":"Dynamic Spectrum Mixer for Visual Recognition","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2309.09196","title":"Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition","created":"2023-09-17","cited_by_count":0,"area":null},{"id":"2403.16130","title":"AKBR: Learning Adaptive Kernel-based Representations for Graph Classification","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2408.06021","title":"ClickAttention: Click Region Similarity Guided Interactive Segmentation","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2408.10517","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2024-08-20","cited_by_count":0,"area":"ssm"},{"id":"2410.12811","title":"Decoding Emotions: Unveiling Facial Expressions through Acoustic Sensing with Contrastive Attention","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2411.00169","title":"Aerial Flood Scene Classification Using Fine-Tuned Attention-based Architecture for Flood-Prone Countries in South Asia","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2501.07984","title":"Threshold Attention Network for Semantic Segmentation of Remote Sensing Images","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2502.15331","title":"Lightweight yet Efficient: An External Attentive Graph Convolutional Network with Positional Prompts for Sequential Recommendation","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2503.19002","title":"Quantum Complex-Valued Self-Attention Model","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2504.00759","title":"MSSFC-Net:Enhancing Building Interpretation with Multi-Scale Spatial-Spectral Feature Collaboration","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2506.07933","title":"Ensemble-Based Survival Models with the Self-Attended Beran Estimator Predictions","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2507.08307","title":"M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2508.10566","title":"HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2512.07275","title":"Effective Attention-Guided Multi-Scale Medical Network for Skin Lesion Segmentation","created":"2025-12-08","cited_by_count":0,"area":null}],"next_cursor":"100"}