{"total":22,"rows":[{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806,"area":null},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2106.06716","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","created":"2021-06-12","cited_by_count":126,"area":null},{"id":"2104.14726","title":"MOOD: Multi-level Out-of-distribution Detection","created":"2021-04-30","cited_by_count":94,"area":null},{"id":"2112.10074","title":"QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results","created":"2021-12-19","cited_by_count":28,"area":null},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19,"area":null},{"id":"2401.00926","title":"Accurate Leukocyte Detection Based on Deformable-DETR and Multi-Level Feature Fusion for Aiding Diagnosis of Blood Diseases","created":"2024-01-01","cited_by_count":15,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2303.01589","title":"AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2311.10807","title":"SENetV2: Aggregated dense layer for channelwise and global representations","created":"2023-11-17","cited_by_count":3,"area":null},{"id":"2312.05928","title":"AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer","created":"2023-12-10","cited_by_count":3,"area":null},{"id":"2103.15584","title":"Busy-Quiet Video Disentangling for Video Classification","created":"2021-03-29","cited_by_count":2,"area":null},{"id":"2308.03471","title":"Deepfake Detection: A Comparative Analysis","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2212.01790","title":"Kernel Inversed Pyramidal Resizing Network for Efficient Pavement Distress Recognition","created":"2022-12-04","cited_by_count":1,"area":null},{"id":"2407.06673","title":"CTRL-F: Pairing Convolution with Transformer for Image Classification via Multi-Level Feature Cross-Attention and Representation Learning Fusion","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2203.16767","title":"SpatioTemporal Focus for Skeleton-based Action Recognition","created":"2022-03-31","cited_by_count":0,"area":null},{"id":"2209.10327","title":"SDA-$x$Net: Selective Depth Attention Networks for Adaptive Multi-scale Feature Representation","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2308.13343","title":"Squeeze aggregated excitation network","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2403.10803","title":"Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion","created":"2024-03-16","cited_by_count":0,"area":null},{"id":"2404.00949","title":"Harnessing The Power of Attention For Patch-Based Biomedical Image Classification","created":"2024-04-01","cited_by_count":0,"area":null}],"next_cursor":null}