{"list":"other","total":51,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1703.00848","title":"Unsupervised Image-to-Image Translation Networks","created":"2017-03-02","cited_by_count":603},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"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":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163},{"id":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"1909.10980","title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","created":"2019-09-20","cited_by_count":85},{"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":"2303.15710","title":"Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks","created":"2023-03-28","cited_by_count":41},{"id":"2305.13608","title":"VDD: Varied Drone Dataset for Semantic Segmentation","created":"2023-05-23","cited_by_count":40},{"id":"1907.10303","title":"Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation","created":"2019-07-24","cited_by_count":36},{"id":"2204.03245","title":"HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection","created":"2022-04-07","cited_by_count":34},{"id":"2301.12689","title":"Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels","created":"2023-01-30","cited_by_count":30},{"id":"2303.17386","title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","created":"2023-03-30","cited_by_count":27},{"id":"2110.03143","title":"Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning","created":"2021-10-07","cited_by_count":25},{"id":"2310.19372","title":"RGB-X Object Detection via Scene-Specific Fusion Modules","created":"2023-10-30","cited_by_count":15},{"id":"2210.04367","title":"Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Network","created":"2022-10-09","cited_by_count":13},{"id":"2104.07196","title":"Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks","created":"2021-04-15","cited_by_count":12},{"id":"2012.03455","title":"TP-TIO: A Robust Thermal-Inertial Odometry with Deep ThermalPoint","created":"2020-12-07","cited_by_count":11},{"id":"1903.00798","title":"Keyframe-based Direct Thermal-Inertial Odometry","created":"2019-03-03","cited_by_count":8},{"id":"2209.04097","title":"MassMIND: Massachusetts Maritime INfrared Dataset","created":"2022-09-09","cited_by_count":8},{"id":"2307.09027","title":"Online Self-Supervised Thermal Water Segmentation for Aerial Vehicles","created":"2023-07-18","cited_by_count":6},{"id":"2402.02067","title":"RIDERS: Radar-Infrared Depth Estimation for Robust Sensing","created":"2024-02-03","cited_by_count":5},{"id":"2312.09159","title":"WIT-UAS: A Wildland-fire Infrared Thermal Dataset to Detect Crew Assets From Aerial Views","created":"2023-12-14","cited_by_count":4},{"id":"2304.07031","title":"Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery","created":"2023-04-14","cited_by_count":3}],"next_cursor":null}