{"total":294,"rows":[{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172,"area":null},{"id":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167,"area":null},{"id":"2211.12499","title":"Instant Volumetric Head Avatars","created":"2022-11-22","cited_by_count":159,"area":null},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124,"area":null},{"id":"2312.02214","title":"FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding","created":"2023-12-03","cited_by_count":108,"area":null},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2101.06085","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","created":"2021-01-15","cited_by_count":89,"area":null},{"id":"2206.02066","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","created":"2022-06-04","cited_by_count":84,"area":null},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81,"area":null},{"id":"2201.08361","title":"Stitch it in Time: GAN-Based Facial Editing of Real Videos","created":"2022-01-20","cited_by_count":68,"area":null},{"id":"2303.08600","title":"MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving","created":"2023-03-15","cited_by_count":68,"area":null},{"id":"2211.14068","title":"Fine-Grained Face Swapping via Regional GAN Inversion","created":"2022-11-25","cited_by_count":67,"area":null},{"id":"2312.02902","title":"HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting","created":"2023-12-05","cited_by_count":60,"area":null},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59,"area":null},{"id":"2103.04233","title":"GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments","created":"2021-03-07","cited_by_count":51,"area":null},{"id":"2202.13670","title":"FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving","created":"2022-02-28","cited_by_count":41,"area":null},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41,"area":null},{"id":"2303.14651","title":"You Only Segment Once: Towards Real-Time Panoptic Segmentation","created":"2023-03-26","cited_by_count":40,"area":null},{"id":"2212.02802","title":"Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding","created":"2022-12-06","cited_by_count":39,"area":null},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37,"area":null},{"id":"2402.19422","title":"PEM: Prototype-based Efficient MaskFormer for Image Segmentation","created":"2024-02-29","cited_by_count":36,"area":null},{"id":"2101.06175","title":"PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation","created":"2021-01-15","cited_by_count":35,"area":null},{"id":"2312.03029","title":"HHAvatar: Gaussian Head Avatar with Dynamic Hairs","created":"2023-12-05","cited_by_count":35,"area":null},{"id":"2403.05369","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","created":"2024-03-08","cited_by_count":34,"area":null},{"id":"2204.02681","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","created":"2022-04-06","cited_by_count":33,"area":null},{"id":"2210.07124","title":"RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer","created":"2022-10-13","cited_by_count":31,"area":null},{"id":"2204.03648","title":"SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage","created":"2022-04-07","cited_by_count":30,"area":null},{"id":"2404.05680","title":"SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation","created":"2024-04-08","cited_by_count":30,"area":null},{"id":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29,"area":null},{"id":"2304.06700","title":"Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images","created":"2023-04-13","cited_by_count":27,"area":"diffusion"},{"id":"2410.14987","title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","created":"2024-10-19","cited_by_count":27,"area":null},{"id":"2401.00027","title":"Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring","created":"2023-12-29","cited_by_count":24,"area":null},{"id":"2102.02531","title":"ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images","created":"2021-02-04","cited_by_count":22,"area":null},{"id":"2201.06889","title":"Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation","created":"2022-01-18","cited_by_count":22,"area":null},{"id":"2305.10899","title":"Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark","created":"2023-05-18","cited_by_count":22,"area":null},{"id":"2312.17071","title":"SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation","created":"2023-12-28","cited_by_count":22,"area":null},{"id":"2103.12417","title":"OFFSEG: A Semantic Segmentation Framework For Off-Road Driving","created":"2021-03-23","cited_by_count":20,"area":null},{"id":"2303.11686","title":"Learning a 3D Morphable Face Reflectance Model from Low-cost Data","created":"2023-03-21","cited_by_count":20,"area":null},{"id":"2308.09618","title":"LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark","created":"2023-08-18","cited_by_count":19,"area":null},{"id":"2301.13156","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2406.19369","title":"Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model","created":"2024-06-27","cited_by_count":18,"area":"ssm"},{"id":"2409.20398","title":"AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2503.18445","title":"Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness","created":"2025-03-24","cited_by_count":18,"area":null},{"id":"2109.00699","title":"FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation","created":"2021-09-02","cited_by_count":17,"area":null},{"id":"2203.08881","title":"Hyperbolic Uncertainty Aware Semantic Segmentation","created":"2022-03-16","cited_by_count":17,"area":null},{"id":"2309.14065","title":"AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation","created":"2023-09-25","cited_by_count":17,"area":null},{"id":"2205.13278","title":"Semantic Segmentation for Thermal Images: A Comparative Survey","created":"2022-05-26","cited_by_count":16,"area":null},{"id":"2211.08352","title":"Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview","created":"2022-11-13","cited_by_count":16,"area":null},{"id":"2310.17316","title":"Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics","created":"2023-10-26","cited_by_count":16,"area":null},{"id":"2203.04031","title":"Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes","created":"2022-03-08","cited_by_count":15,"area":null},{"id":"2207.06799","title":"MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation","created":"2022-07-14","cited_by_count":15,"area":null},{"id":"2209.07774","title":"Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning","created":"2022-09-16","cited_by_count":15,"area":null},{"id":"2401.11414","title":"S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving","created":"2024-01-21","cited_by_count":15,"area":null},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15,"area":null},{"id":"2103.05930","title":"AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing","created":"2021-03-10","cited_by_count":14,"area":null},{"id":"2208.14143","title":"FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation","created":"2022-08-30","cited_by_count":14,"area":"distill"},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2402.15351","title":"AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks","created":"2024-02-23","cited_by_count":14,"area":null},{"id":"2403.17217","title":"DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment","created":"2024-03-25","cited_by_count":14,"area":"diffusion"},{"id":"2302.10484","title":"Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN","created":"2023-02-21","cited_by_count":12,"area":null},{"id":"2111.09957","title":"Rethinking Dilated Convolution for Real-time Semantic Segmentation","created":"2021-11-18","cited_by_count":11,"area":null},{"id":"2404.13640","title":"Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer","created":"2024-04-21","cited_by_count":11,"area":null},{"id":"2203.09594","title":"Delta Distillation for Efficient Video Processing","created":"2022-03-17","cited_by_count":10,"area":"distill"},{"id":"2207.04415","title":"SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow","created":"2022-07-10","cited_by_count":10,"area":null},{"id":"2211.15595","title":"FsaNet: Frequency Self-attention for Semantic Segmentation","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2306.10364","title":"Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation","created":"2023-06-17","cited_by_count":10,"area":null},{"id":"2307.00270","title":"Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation","created":"2023-07-01","cited_by_count":10,"area":null},{"id":"2309.03535","title":"Feature Enhancer Segmentation Network (FES-Net) for Vessel Segmentation","created":"2023-09-07","cited_by_count":10,"area":null},{"id":"2503.06700","title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","created":"2025-03-09","cited_by_count":10,"area":null},{"id":"2507.01182","title":"Rapid Salient Object Detection with Difference Convolutional Neural Networks","created":"2025-07-01","cited_by_count":10,"area":null},{"id":"2112.07146","title":"PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9,"area":null},{"id":"2303.06209","title":"SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2408.00296","title":"Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360{\\deg}","created":"2024-08-01","cited_by_count":9,"area":null},{"id":"2411.09387","title":"Instruction-Driven Fusion of Infrared-Visible Images: Tailoring for Diverse Downstream Tasks","created":"2024-11-14","cited_by_count":9,"area":null},{"id":"2303.07224","title":"Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos","created":"2023-03-13","cited_by_count":8,"area":null},{"id":"2310.15081","title":"E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2409.19560","title":"Fast-Convergent and Communication-Alleviated Heterogeneous Hierarchical Federated Learning in Autonomous Driving","created":"2024-09-29","cited_by_count":8,"area":null},{"id":"2108.11105","title":"Lightweight Monocular Depth with a Novel Neural Architecture Search Method","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2108.11128","title":"Semantic Scene Segmentation for Robotics Applications","created":"2021-08-25","cited_by_count":7,"area":null},{"id":"2206.08605","title":"On Efficient Real-Time Semantic Segmentation: A Survey","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2207.12939","title":"Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability","created":"2022-07-26","cited_by_count":7,"area":null},{"id":"2301.05526","title":"Self-Training Guided Disentangled Adaptation for Cross-Domain Remote Sensing Image Semantic Segmentation","created":"2023-01-13","cited_by_count":7,"area":null},{"id":"2304.09463","title":"HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks","created":"2023-04-19","cited_by_count":7,"area":null},{"id":"2311.14762","title":"The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024","created":"2023-11-23","cited_by_count":7,"area":null},{"id":"2412.07739","title":"GASP: Gaussian Avatars with Synthetic Priors","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2501.02260","title":"MagicFace: High-Fidelity Facial Expression Editing with Action-Unit Control","created":"2025-01-04","cited_by_count":7,"area":"diffusion"},{"id":"2108.08516","title":"Retrieval and Localization with Observation Constraints","created":"2021-08-19","cited_by_count":6,"area":null},{"id":"2210.10335","title":"WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2302.09486","title":"LC-NeRF: Local Controllable Face Generation in Neural Randiance Field","created":"2023-02-19","cited_by_count":6,"area":null},{"id":"2307.10267","title":"On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2401.07579","title":"PMFSNet: Polarized Multi-scale Feature Self-attention Network For Lightweight Medical Image Segmentation","created":"2024-01-15","cited_by_count":6,"area":null},{"id":"2401.10228","title":"RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2401.15647","title":"UP-CrackNet: Unsupervised Pixel-Wise Road Crack Detection via Adversarial Image Restoration","created":"2024-01-28","cited_by_count":6,"area":null},{"id":"2403.03468","title":"Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2404.17159","title":"Phase-aggregated Dual-branch Network for Efficient Fingerprint Dense Registration","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2406.16289","title":"Crowd-Sourced NeRF: Collecting Data from Production Vehicles for 3D Street View Reconstruction","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.05577","title":"Audio-driven High-resolution Seamless Talking Head Video Editing via StyleGAN","created":"2024-07-08","cited_by_count":6,"area":null}],"next_cursor":"100"}