{"list":"other","total":59,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"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":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"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":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2103.14006","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","created":"2021-03-25","cited_by_count":529},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2307.12348","title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","created":"2023-07-23","cited_by_count":365},{"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":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2205.07680","title":"BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models","created":"2022-05-16","cited_by_count":225},{"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":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"2303.07601","title":"V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception","created":"2023-03-14","cited_by_count":155},{"id":"2303.06840","title":"DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion","created":"2023-03-13","cited_by_count":153},{"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":"2305.15086","title":"Unpaired Image-to-Image Translation via Neural Schr\\\"odinger Bridge","created":"2023-05-24","cited_by_count":96},{"id":"2304.05172","title":"LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images","created":"2023-04-11","cited_by_count":87},{"id":"2210.01427","title":"Accurate Image Restoration with Attention Retractable Transformer","created":"2022-10-04","cited_by_count":85},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"1806.02311","title":"Unsupervised Attention-guided Image to Image Translation","created":"2018-06-06","cited_by_count":58},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","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":"2208.01166","title":"Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions","created":"2022-08-01","cited_by_count":48},{"id":"2407.05878","title":"HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution","created":"2024-07-08","cited_by_count":42},{"id":"1901.03281","title":"Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net","created":"2019-01-10","cited_by_count":35},{"id":"2307.06505","title":"WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces","created":"2023-07-13","cited_by_count":35},{"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":"2312.04861","title":"Exploring Radar Data Representations in Autonomous Driving: A Comprehensive Review","created":"2023-12-08","cited_by_count":22},{"id":"2503.01187","title":"DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution","created":"2025-03-03","cited_by_count":22},{"id":"2409.19589","title":"Effective Diffusion Transformer Architecture for Image Super-Resolution","created":"2024-09-29","cited_by_count":21},{"id":"2406.09383","title":"Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset","created":"2024-06-13","cited_by_count":18},{"id":"2405.12944","title":"AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection","created":"2024-05-21","cited_by_count":15},{"id":"2307.15800","title":"Why are thermal images blurry","created":"2023-07-28","cited_by_count":12},{"id":"2309.15751","title":"InfraParis: A multi-modal and multi-task autonomous driving dataset","created":"2023-09-27","cited_by_count":12},{"id":"2311.14459","title":"IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather","created":"2023-11-24","cited_by_count":12},{"id":"2304.07969","title":"Learning to \"Segment Anything\" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIR","created":"2023-04-17","cited_by_count":11},{"id":"2403.09359","title":"D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection","created":"2024-03-14","cited_by_count":9},{"id":"2405.16038","title":"Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection","created":"2024-05-25","cited_by_count":9},{"id":"1911.06975","title":"Long Range 3D with Quadocular Thermal (LWIR) Camera","created":"2019-11-16","cited_by_count":1}],"next_cursor":null}