{"list":"other","total":53,"rows":[{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"1811.12039","title":"EV-SegNet: Semantic Segmentation for Event-based Cameras","created":"2018-11-29","cited_by_count":93},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79},{"id":"1807.06667","title":"Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video","created":"2018-07-17","cited_by_count":78},{"id":"2004.01800","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","created":"2020-04-03","cited_by_count":77},{"id":"1612.08871","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","created":"2016-12-28","cited_by_count":76},{"id":"1807.07429","title":"Semi-Dense 3D Reconstruction with a Stereo Event Camera","created":"2018-07-19","cited_by_count":67},{"id":"1708.03088","title":"Semantic Video CNNs through Representation Warping","created":"2017-08-10","cited_by_count":65},{"id":"2203.14956","title":"LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection","created":"2022-03-28","cited_by_count":55},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55},{"id":"1804.00931","title":"Dynamic Video Segmentation Network","created":"2018-04-03","cited_by_count":51},{"id":"2308.14419","title":"Graph-based Asynchronous Event Processing for Rapid Object Recognition","created":"2023-08-28","cited_by_count":51},{"id":"2102.08643","title":"Temporal Memory Attention for Video Semantic Segmentation","created":"2021-02-17","cited_by_count":50},{"id":"2111.12341","title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","created":"2021-11-24","cited_by_count":47},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"2003.06883","title":"Night-time Scene Parsing with a Large Real Dataset","created":"2020-03-15","cited_by_count":37},{"id":"2108.03694","title":"Event-driven Vision and Control for UAVs on a Neuromorphic Chip","created":"2021-08-08","cited_by_count":34},{"id":"2106.06908","title":"Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation","created":"2021-06-13","cited_by_count":33},{"id":"2403.08119","title":"CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast Maximization","created":"2024-03-12","cited_by_count":31},{"id":"2307.15942","title":"CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation","created":"2023-07-29","cited_by_count":30},{"id":"2305.08776","title":"Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models","created":"2023-05-15","cited_by_count":27},{"id":"2101.01715","title":"Local Memory Attention for Fast Video Semantic Segmentation","created":"2021-01-05","cited_by_count":25},{"id":"2203.07667","title":"SATS: Self-Attention Transfer for Continual Semantic Segmentation","created":"2022-03-15","cited_by_count":25},{"id":"2206.04511","title":"Efficient Human Pose Estimation via 3D Event Point Cloud","created":"2022-06-09","cited_by_count":25},{"id":"2207.10436","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","created":"2022-07-21","cited_by_count":25},{"id":"2211.10754","title":"HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities","created":"2022-11-19","cited_by_count":25},{"id":"2110.11601","title":"Multimodal Semi-Supervised Learning for 3D Objects","created":"2021-10-22","cited_by_count":24},{"id":"2301.04648","title":"Head-Free Lightweight Semantic Segmentation with Linear Transformer","created":"2023-01-11","cited_by_count":22},{"id":"2310.00400","title":"MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings","created":"2023-09-30","cited_by_count":22},{"id":"2404.01945","title":"Event-assisted Low-Light Video Object Segmentation","created":"2024-04-02","cited_by_count":22},{"id":"1912.11844","title":"Efficient Video Semantic Segmentation with Labels Propagation and Refinement","created":"2019-12-26","cited_by_count":18},{"id":"2304.07200","title":"EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks","created":"2023-04-14","cited_by_count":16},{"id":"2103.09097","title":"Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification","created":"2021-03-16","cited_by_count":15},{"id":"2401.14148","title":"LanDA: Language-Guided Multi-Source Domain Adaptation","created":"2024-01-25","cited_by_count":13},{"id":"2403.03063","title":"CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections","created":"2024-03-05","cited_by_count":12},{"id":"2103.08834","title":"GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video","created":"2021-03-16","cited_by_count":11},{"id":"2401.17509","title":"Anything in Any Scene: Photorealistic Video Object Insertion","created":"2024-01-30","cited_by_count":9},{"id":"2303.07224","title":"Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos","created":"2023-03-13","cited_by_count":8},{"id":"2404.06605","title":"RoadBEV: Road Surface Reconstruction in Bird's Eye View","created":"2024-04-09","cited_by_count":8},{"id":"2311.12651","title":"Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots","created":"2023-11-21","cited_by_count":5},{"id":"1708.09011","title":"Real-Time 6DOF Pose Relocalization for Event Cameras with Stacked Spatial LSTM Networks","created":"2017-08-22","cited_by_count":3},{"id":"2111.14094","title":"Topic Driven Adaptive Network for Cross-Domain Sentiment Classification","created":"2021-11-28","cited_by_count":3}],"next_cursor":null}