{"total":27,"rows":[{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90,"area":null},{"id":"2201.13100","title":"Adversarial Masking for Self-Supervised Learning","created":"2022-01-31","cited_by_count":78,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2401.14391","title":"Rethinking Patch Dependence for Masked Autoencoders","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27,"area":null},{"id":"2201.06268","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","created":"2022-01-17","cited_by_count":12,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2310.10700","title":"PELA: Learning Parameter-Efficient Models with Low-Rank Approximation","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2304.05350","title":"Astroformer: More Data Might not be all you need for Classification","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2310.07633","title":"Attention-Map Augmentation for Hypercomplex Breast Cancer Classification","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2603.02080","title":"From Pixels to Patches: Pooling Strategies for Earth Embeddings","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2212.12552","title":"A Close Look at Spatial Modeling: From Attention to Convolution","created":"2022-12-23","cited_by_count":3,"area":null},{"id":"2404.01524","title":"On Train-Test Class Overlap and Detection for Image Retrieval","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2402.19305","title":"HyenaPixel: Global Image Context with Convolutions","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2404.14996","title":"CA-Stream: Attention-based pooling for interpretable image recognition","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2411.15418","title":"Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2504.02797","title":"Spline-based Transformers","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2209.09930","title":"Deep Superpixel Generation and Clustering for Weakly Supervised Segmentation of Brain Tumors in MR Images","created":"2022-09-20","cited_by_count":1,"area":null},{"id":"2402.03843","title":"A new method for optical steel rope non-destructive damage detection","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2407.18673","title":"A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2409.01633","title":"SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2503.14929","title":"ACE: A Cardinality Estimator for Set-Valued Queries","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2509.14788","title":"Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2601.11262","title":"Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings","created":"2026-01-16","cited_by_count":0,"area":null}],"next_cursor":null}