{"list":"other","total":59,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"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":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"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":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1805.10421","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","created":"2018-05-26","cited_by_count":370},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128},{"id":"2007.09183","title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation","created":"2020-07-17","cited_by_count":122},{"id":"2011.05005","title":"Deep Multimodal Fusion by Channel Exchanging","created":"2020-11-10","cited_by_count":118},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"1905.10089","title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","created":"2019-05-24","cited_by_count":107},{"id":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91},{"id":"2303.14816","title":"Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers","created":"2023-03-26","cited_by_count":87},{"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":"2203.11624","title":"High-resolution Iterative Feedback Network for Camouflaged Object Detection","created":"2022-03-22","cited_by_count":78},{"id":"2108.10528","title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","created":"2021-08-24","cited_by_count":77},{"id":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76},{"id":"2404.04256","title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","created":"2024-04-05","cited_by_count":71},{"id":"2212.05370","title":"Source-free Depth for Object Pop-out","created":"2022-12-10","cited_by_count":52},{"id":"2004.04534","title":"Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation","created":"2020-04-09","cited_by_count":48},{"id":"2112.02991","title":"Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery","created":"2021-12-06","cited_by_count":45},{"id":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44},{"id":"2210.14530","title":"RGB-T Semantic Segmentation with Location, Activation, and Sharpening","created":"2022-10-26","cited_by_count":39},{"id":"2301.07405","title":"HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness","created":"2023-01-18","cited_by_count":31},{"id":"2405.18014","title":"Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model","created":"2024-05-28","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":"2204.09848","title":"Weakly Aligned Feature Fusion for Multimodal Object Detection","created":"2022-04-21","cited_by_count":26},{"id":"2401.01624","title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","created":"2024-01-03","cited_by_count":21},{"id":"2403.09323","title":"E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection","created":"2024-03-14","cited_by_count":21},{"id":"2403.08997","title":"Caltech Aerial RGB-Thermal Dataset in the Wild","created":"2024-03-13","cited_by_count":19},{"id":"2112.02277","title":"BAANet: Learning Bi-directional Adaptive Attention Gates for Multispectral Pedestrian Detection","created":"2021-12-04","cited_by_count":13},{"id":"2302.11951","title":"Pixel Difference Convolutional Network for RGB-D Semantic Segmentation","created":"2023-02-23","cited_by_count":13},{"id":"2305.10469","title":"Object Segmentation by Mining Cross-Modal Semantics","created":"2023-05-17","cited_by_count":12},{"id":"2201.05761","title":"A Survey on RGB-D Datasets","created":"2022-01-15","cited_by_count":11},{"id":"2409.07715","title":"FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments","created":"2024-09-12","cited_by_count":8},{"id":"2309.15332","title":"Multimodal Dataset for Localization, Mapping and Crop Monitoring in Citrus Tree Farms","created":"2023-09-27","cited_by_count":6},{"id":"2309.05645","title":"CitDet: A Benchmark Dataset for Citrus Fruit Detection","created":"2023-09-11","cited_by_count":5},{"id":"2312.17505","title":"Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion","created":"2023-12-29","cited_by_count":3}],"next_cursor":null}