{"total":19,"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":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34,"area":null},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34,"area":null},{"id":"2303.08685","title":"Making Vision Transformers Efficient from A Token Sparsification View","created":"2023-03-15","cited_by_count":29,"area":null},{"id":"2307.05541","title":"High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition","created":"2023-07-08","cited_by_count":18,"area":null},{"id":"2409.07967","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","created":"2024-09-12","cited_by_count":11,"area":null},{"id":"2202.13808","title":"DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2304.04175","title":"Token Boosting for Robust Self-Supervised Visual Transformer Pre-training","created":"2023-04-09","cited_by_count":4,"area":null},{"id":"2303.13111","title":"Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2407.02934","title":"PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2304.08803","title":"MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition","created":"2023-04-18","cited_by_count":1,"area":null},{"id":"2404.00648","title":"SpiralMLP: A Lightweight Vision MLP Architecture","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2206.02997","title":"TadML: A fast temporal action detection with Mechanics-MLP","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2304.03917","title":"MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision","created":"2023-04-08","cited_by_count":0,"area":null},{"id":"2308.11204","title":"A Simple Framework for Multi-mode Spatial-Temporal Data Modeling","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2308.16018","title":"SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition","created":"2023-08-30","cited_by_count":0,"area":null},{"id":"2403.17607","title":"Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2511.20928","title":"Smooth regularization for efficient video recognition","created":"2025-11-25","cited_by_count":0,"area":null}],"next_cursor":null}