{"total":32,"rows":[{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184,"area":null},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108,"area":null},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105,"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":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83,"area":null},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74,"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":"2205.10063","title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","created":"2022-05-20","cited_by_count":57,"area":null},{"id":"2110.13083","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","created":"2021-10-25","cited_by_count":34,"area":null},{"id":"2109.03810","title":"Scaled ReLU Matters for Training Vision Transformers","created":"2021-09-08","cited_by_count":29,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2207.12795","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","created":"2022-07-26","cited_by_count":23,"area":null},{"id":"2207.03860","title":"Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain","created":"2022-07-08","cited_by_count":22,"area":null},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"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":"2303.05475","title":"Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking","created":"2023-03-09","cited_by_count":12,"area":null},{"id":"2308.00574","title":"PVG: Progressive Vision Graph for Vision Recognition","created":"2023-08-01","cited_by_count":10,"area":null},{"id":"2207.14741","title":"End-to-end View Synthesis via NeRF Attention","created":"2022-07-29","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":"2201.08996","title":"Linear Array Network for Low-light Image Enhancement","created":"2022-01-22","cited_by_count":2,"area":null},{"id":"2410.15360","title":"Improving 3D Medical Image Segmentation at Boundary Regions using Local Self-attention and Global Volume Mixing","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2210.03433","title":"PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search","created":"2022-10-07","cited_by_count":1,"area":null},{"id":"2302.06939","title":"Underwater target detection based on improved YOLOv7","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2305.14768","title":"Dual Path Transformer with Partition Attention","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2401.06827","title":"APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2507.00070","title":"An efficient plant disease detection using transfer learning approach","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2108.02404","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2201.02314","title":"RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images","created":"2022-01-07","cited_by_count":0,"area":null},{"id":"2207.05420","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2605.29260","title":"Deep Psychovisual Image Representations","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}