{"list":"other","total":62,"rows":[{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"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":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2308.02097","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","created":"2023-08-04","cited_by_count":129},{"id":"1805.08982","title":"RGB-T Object Tracking:Benchmark and Baseline","created":"2018-05-23","cited_by_count":121},{"id":"2203.12719","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","created":"2022-03-23","cited_by_count":118},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"id":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","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":"1909.10980","title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","created":"2019-09-20","cited_by_count":85},{"id":"2009.12664","title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","created":"2020-09-26","cited_by_count":85},{"id":"2008.03043","title":"Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems","created":"2020-08-07","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":"2406.11519","title":"HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model","created":"2024-06-17","cited_by_count":73},{"id":"2007.03262","title":"RGBT Salient Object Detection: A Large-scale Dataset and Benchmark","created":"2020-07-07","cited_by_count":69},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68},{"id":"2008.12134","title":"Siamese Network for RGB-D Salient Object Detection and Beyond","created":"2020-08-26","cited_by_count":67},{"id":"1905.06741","title":"RGB-T Image Saliency Detection via Collaborative Graph Learning","created":"2019-05-16","cited_by_count":58},{"id":"2306.16175","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","created":"2023-06-28","cited_by_count":58},{"id":"1802.09972","title":"Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection","created":"2018-02-27","cited_by_count":57},{"id":"2304.05919","title":"Hard Patches Mining for Masked Image Modeling","created":"2023-04-12","cited_by_count":57},{"id":"2012.04529","title":"Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting","created":"2020-12-08","cited_by_count":52},{"id":"1701.02829","title":"A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach","created":"2017-01-11","cited_by_count":51},{"id":"2209.13801","title":"Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection","created":"2022-09-28","cited_by_count":50},{"id":"1808.04818","title":"Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation","created":"2018-08-14","cited_by_count":49},{"id":"1611.05842","title":"Video Processing from Electro-optical Sensors for Object Detection and Tracking in Maritime Environment: A Survey","created":"2016-11-17","cited_by_count":47},{"id":"2110.08988","title":"FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation","created":"2021-10-18","cited_by_count":45},{"id":"2112.05144","title":"Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing","created":"2021-12-09","cited_by_count":45},{"id":"2005.02315","title":"Multi-interactive Dual-decoder for RGB-thermal Salient Object Detection","created":"2020-05-05","cited_by_count":44},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44},{"id":"2003.04645","title":"HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images","created":"2020-03-10","cited_by_count":41},{"id":"1801.05944","title":"PTB-TIR: A Thermal Infrared Pedestrian Tracking Benchmark","created":"2018-01-18","cited_by_count":34},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27},{"id":"2204.05453","title":"Glass Segmentation with RGB-Thermal Image Pairs","created":"2022-04-12","cited_by_count":26},{"id":"2205.07439","title":"ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning","created":"2022-05-16","cited_by_count":26},{"id":"2008.00836","title":"LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark","created":"2020-08-03","cited_by_count":25},{"id":"2101.01715","title":"Local Memory Attention for Fast Video Semantic Segmentation","created":"2021-01-05","cited_by_count":25},{"id":"2312.00360","title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","created":"2023-12-01","cited_by_count":25},{"id":"2405.05237","title":"EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning","created":"2024-05-08","cited_by_count":25},{"id":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25},{"id":"1810.12574","title":"Rain Removal in Traffic Surveillance: Does it Matter?","created":"2018-10-30","cited_by_count":15},{"id":"2205.14338","title":"Object-wise Masked Autoencoders for Fast Pre-training","created":"2022-05-28","cited_by_count":15},{"id":"2405.12944","title":"AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection","created":"2024-05-21","cited_by_count":15},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13},{"id":"2408.00969","title":"Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach","created":"2024-08-02","cited_by_count":13},{"id":"2108.00913","title":"I2V-GAN: Unpaired Infrared-to-Visible Video Translation","created":"2021-08-02","cited_by_count":10},{"id":"2007.00622","title":"A Multi-spectral Dataset for Evaluating Motion Estimation Systems","created":"2020-07-01","cited_by_count":8},{"id":"2206.11459","title":"Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline","created":"2022-06-23","cited_by_count":2}],"next_cursor":null}