{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"1901.06523","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","created":"2019-01-19","cited_by_count":368},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2203.16220","title":"Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection","created":"2022-03-30","cited_by_count":317},{"id":"1905.12784","title":"Intrinsic dimension of data representations in deep neural networks","created":"2019-05-29","cited_by_count":282},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2211.14461","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","created":"2022-11-26","cited_by_count":223},{"id":"1903.05987","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","created":"2019-03-14","cited_by_count":167},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"2305.11443","title":"Equivariant Multi-Modality Image Fusion","created":"2023-05-19","cited_by_count":99},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86},{"id":"2312.04265","title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-07","cited_by_count":83},{"id":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76},{"id":"2007.03262","title":"RGBT Salient Object Detection: A Large-scale Dataset and Benchmark","created":"2020-07-07","cited_by_count":69},{"id":"2211.10960","title":"CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion","created":"2022-11-20","cited_by_count":63},{"id":"2204.05585","title":"SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection","created":"2022-04-12","cited_by_count":59},{"id":"1905.06741","title":"RGB-T Image Saliency Detection via Collaborative Graph Learning","created":"2019-05-16","cited_by_count":58},{"id":"2403.01439","title":"Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis","created":"2024-03-03","cited_by_count":53},{"id":"2112.02363","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","created":"2021-12-04","cited_by_count":47},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44},{"id":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44},{"id":"2303.15710","title":"Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks","created":"2023-03-28","cited_by_count":41},{"id":"2210.14530","title":"RGB-T Semantic Segmentation with Location, Activation, and Sharpening","created":"2022-10-26","cited_by_count":39},{"id":"2303.07336","title":"MP-Former: Mask-Piloted Transformer for Image Segmentation","created":"2023-03-13","cited_by_count":39},{"id":"2408.08345","title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks","created":"2024-08-15","cited_by_count":34},{"id":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31},{"id":"2403.00326","title":"DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion","created":"2024-03-01","cited_by_count":28},{"id":"2401.01624","title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","created":"2024-01-03","cited_by_count":21},{"id":"2311.15010","title":"Adapter is All You Need for Tuning Visual Tasks","created":"2023-11-25","cited_by_count":19},{"id":"2406.00917","title":"Alignment-Free RGBT Salient Object Detection: Semantics-guided Asymmetric Correlation Network and A Unified Benchmark","created":"2024-06-03","cited_by_count":19},{"id":"2312.10376","title":"STA-VPT: SpatioTemporally Aligned Visual Prompt Tuning","created":"2023-12-16","cited_by_count":17},{"id":"2310.19372","title":"RGB-X Object Detection via Scene-Specific Fusion Modules","created":"2023-10-30","cited_by_count":15},{"id":"2406.03051","title":"Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision","created":"2024-06-05","cited_by_count":13},{"id":"2305.10469","title":"Object Segmentation by Mining Cross-Modal Semantics","created":"2023-05-17","cited_by_count":12},{"id":"2312.17116","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","created":"2023-12-28","cited_by_count":12},{"id":"2402.00407","title":"InfMAE: A Foundation Model in the Infrared Modality","created":"2024-02-01","cited_by_count":11},{"id":"2306.10364","title":"Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation","created":"2023-06-17","cited_by_count":10},{"id":"2303.08692","title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","created":"2023-03-15","cited_by_count":7}],"next_cursor":null}