{"total":25,"rows":[{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264,"area":null},{"id":"2308.03364","title":"Dual Aggregation Transformer for Image Super-Resolution","created":"2023-08-07","cited_by_count":124,"area":null},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103,"area":null},{"id":"2207.01077","title":"Can Language Understand Depth?","created":"2022-07-03","cited_by_count":69,"area":null},{"id":"2303.08129","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43,"area":null},{"id":"2112.14000","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","created":"2021-12-28","cited_by_count":36,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"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":"2106.03146","title":"Oriented Object Detection with Transformer","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2111.10332","title":"DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion","created":"2021-11-19","cited_by_count":17,"area":null},{"id":"2203.07373","title":"SATr: Slice Attention with Transformer for Universal Lesion Detection","created":"2022-03-13","cited_by_count":17,"area":null},{"id":"2108.12784","title":"TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting","created":"2021-08-29","cited_by_count":8,"area":null},{"id":"2208.03062","title":"Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection","created":"2022-08-05","cited_by_count":6,"area":null},{"id":"2411.19451","title":"Learning Visual Abstract Reasoning through Dual-Stream Networks","created":"2024-11-29","cited_by_count":4,"area":null},{"id":"2412.11540","title":"SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2109.08174","title":"TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network","created":"2021-09-16","cited_by_count":2,"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":"2209.01620","title":"MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition","created":"2022-08-31","cited_by_count":1,"area":null},{"id":"2211.13919","title":"Mutual Guidance and Residual Integration for Image Enhancement","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2302.06350","title":"VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2305.16342","title":"InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2106.06998","title":"XConv: Low-memory stochastic backpropagation for convolutional layers","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2301.11022","title":"Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2305.05132","title":"Dual flow fusion model for concrete surface crack segmentation","created":"2023-05-09","cited_by_count":0,"area":null}],"next_cursor":null}