{"total":417,"rows":[{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351,"area":null},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713,"area":null},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"area":null},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652,"area":null},{"id":"2106.01226","title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","created":"2021-06-02","cited_by_count":463,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376,"area":null},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366,"area":null},{"id":"2111.12503","title":"Extracting Triangular 3D Models, Materials, and Lighting From Images","created":"2021-11-24","cited_by_count":366,"area":null},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344,"area":null},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293,"area":null},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197,"area":null},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192,"area":null},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188,"area":null},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188,"area":null},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181,"area":null},{"id":"2108.07845","title":"ARCH++: Animation-Ready Clothed Human Reconstruction Revisited","created":"2021-08-17","cited_by_count":174,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140,"area":null},{"id":"2211.05272","title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","created":"2022-11-10","cited_by_count":139,"area":null},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137,"area":null},{"id":"2110.07604","title":"NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild","created":"2021-10-14","cited_by_count":136,"area":null},{"id":"2302.11566","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","created":"2023-02-22","cited_by_count":134,"area":null},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133,"area":null},{"id":"2204.08906","title":"Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing","created":"2022-04-19","cited_by_count":126,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120,"area":null},{"id":"2311.08581","title":"Drivable 3D Gaussian Avatars","created":"2023-11-14","cited_by_count":120,"area":null},{"id":"2105.02976","title":"LASR: Learning Articulated Shape Reconstruction from a Monocular Video","created":"2021-05-06","cited_by_count":116,"area":null},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116,"area":null},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115,"area":null},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112,"area":null},{"id":"2207.05736","title":"Vision Transformer for NeRF-Based View Synthesis from a Single Input Image","created":"2022-07-12","cited_by_count":104,"area":null},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98,"area":null},{"id":"2209.12354","title":"InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction","created":"2022-09-26","cited_by_count":93,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87,"area":null},{"id":"2111.12698","title":"Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling","created":"2021-11-24","cited_by_count":84,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2104.06404","title":"Pointly-Supervised Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2105.10441","title":"Driving-Signal Aware Full-Body Avatars","created":"2021-05-21","cited_by_count":81,"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":"2104.04465","title":"Bootstrapping Semantic Segmentation with Regional Contrast","created":"2021-04-09","cited_by_count":80,"area":null},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78,"area":null},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75,"area":null},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75,"area":null},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74,"area":null},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","cited_by_count":71,"area":null},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70,"area":null},{"id":"2204.13983","title":"AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement","created":"2022-04-29","cited_by_count":70,"area":null},{"id":"2103.15537","title":"Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization","created":"2021-03-29","cited_by_count":69,"area":null},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68,"area":null},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66,"area":null},{"id":"2102.06195","title":"Shelf-Supervised Mesh Prediction in the Wild","created":"2021-02-11","cited_by_count":65,"area":null},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65,"area":null},{"id":"2204.02411","title":"Texturify: Generating Textures on 3D Shape Surfaces","created":"2022-04-05","cited_by_count":65,"area":null},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2107.10844","title":"DOVE: Learning Deformable 3D Objects by Watching Videos","created":"2021-07-22","cited_by_count":61,"area":null},{"id":"2101.06571","title":"S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling","created":"2021-01-17","cited_by_count":59,"area":null},{"id":"2401.02400","title":"Learning the 3D Fauna of the Web","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2108.07044","title":"Towards unconstrained joint hand-object reconstruction from RGB videos","created":"2021-08-16","cited_by_count":58,"area":null},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56,"area":null},{"id":"2212.04492","title":"Few-View Object Reconstruction with Unknown Categories and Camera Poses","created":"2022-12-08","cited_by_count":53,"area":null},{"id":"2303.00246","title":"ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution","created":"2023-03-01","cited_by_count":53,"area":null},{"id":"2103.15734","title":"Enhanced Boundary Learning for Glass-like Object Segmentation","created":"2021-03-29","cited_by_count":48,"area":null},{"id":"2110.00990","title":"Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild","created":"2021-10-03","cited_by_count":48,"area":null},{"id":"2102.07899","title":"A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction","created":"2021-02-16","cited_by_count":47,"area":null},{"id":"2104.08569","title":"RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features","created":"2021-04-17","cited_by_count":47,"area":null},{"id":"2305.06351","title":"Reconstructing Animatable Categories from Videos","created":"2023-05-10","cited_by_count":47,"area":null},{"id":"2101.03694","title":"Learning to Segment Rigid Motions from Two Frames","created":"2021-01-11","cited_by_count":46,"area":null},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46,"area":null},{"id":"2112.00169","title":"3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image","created":"2021-11-30","cited_by_count":45,"area":null},{"id":"2103.15627","title":"Learning Generative Models of Textured 3D Meshes from Real-World Images","created":"2021-03-29","cited_by_count":44,"area":null},{"id":"2109.01723","title":"Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction","created":"2021-09-03","cited_by_count":44,"area":null},{"id":"2104.05239","title":"Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation","created":"2021-04-12","cited_by_count":43,"area":null},{"id":"2104.09805","title":"CTNet: Context-based Tandem Network for Semantic Segmentation","created":"2021-04-20","cited_by_count":43,"area":null},{"id":"2104.05606","title":"Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation","created":"2021-04-06","cited_by_count":42,"area":null},{"id":"2301.03407","title":"On Advantages of Mask-level Recognition for Outlier-aware Segmentation","created":"2023-01-09","cited_by_count":42,"area":null},{"id":"2202.04639","title":"Point-Level Region Contrast for Object Detection Pre-Training","created":"2022-02-09","cited_by_count":41,"area":null},{"id":"2207.09055","title":"Box-supervised Instance Segmentation with Level Set Evolution","created":"2022-07-19","cited_by_count":41,"area":null},{"id":"2102.02696","title":"Active Boundary Loss for Semantic Segmentation","created":"2021-02-04","cited_by_count":40,"area":null},{"id":"2103.10978","title":"Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild","created":"2021-03-19","cited_by_count":40,"area":null},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39,"area":null},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39,"area":null},{"id":"2406.04875","title":"3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views","created":"2024-06-07","cited_by_count":39,"area":null},{"id":"2109.05885","title":"Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images","created":"2021-09-13","cited_by_count":38,"area":null},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36,"area":null},{"id":"2104.03778","title":"Progressive Semantic Segmentation","created":"2021-04-08","cited_by_count":35,"area":null},{"id":"2211.03568","title":"CASA: Category-agnostic Skeletal Animal Reconstruction","created":"2022-11-04","cited_by_count":35,"area":null},{"id":"2106.02022","title":"Single Image Depth Prediction with Wavelet Decomposition","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34,"area":null},{"id":"2305.00278","title":"Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected","created":"2023-04-29","cited_by_count":34,"area":null},{"id":"2301.02657","title":"TarViS: A Unified Approach for Target-based Video Segmentation","created":"2023-01-06","cited_by_count":33,"area":null},{"id":"2305.09664","title":"Understanding 3D Object Interaction from a Single Image","created":"2023-05-16","cited_by_count":33,"area":null},{"id":"2406.06039","title":"Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset","created":"2024-06-10","cited_by_count":33,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null}],"next_cursor":"100"}