{"total":307,"rows":[{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"area":"offlinerl"},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353,"area":null},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212,"area":null},{"id":"2110.14373","title":"Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition","created":"2021-10-27","cited_by_count":205,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2103.00783","title":"PENet: Towards Precise and Efficient Image Guided Depth Completion","created":"2021-03-01","cited_by_count":146,"area":null},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2206.04325","title":"CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization","created":"2022-06-09","cited_by_count":135,"area":null},{"id":"2105.10968","title":"HOME: Heatmap Output for future Motion Estimation","created":"2021-05-23","cited_by_count":122,"area":null},{"id":"2111.15490","title":"FENeRF: Face Editing in Neural Radiance Fields","created":"2021-11-30","cited_by_count":112,"area":null},{"id":"2110.01997","title":"Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images","created":"2021-10-05","cited_by_count":98,"area":null},{"id":"2209.03954","title":"Learning to Generate Realistic LiDAR Point Clouds","created":"2022-09-08","cited_by_count":93,"area":"wm"},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84,"area":null},{"id":"2301.09629","title":"LEGO-Net: Learning Regular Rearrangements of Objects in Rooms","created":"2023-01-23","cited_by_count":76,"area":null},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2107.14228","title":"Open-World Entity Segmentation","created":"2021-07-29","cited_by_count":74,"area":null},{"id":"2110.15678","title":"A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis","created":"2021-10-29","cited_by_count":72,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2104.06954","title":"Aligning Latent and Image Spaces to Connect the Unconnectable","created":"2021-04-14","cited_by_count":70,"area":null},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65,"area":null},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65,"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":"2104.03963","title":"InfinityGAN: Towards Infinite-Pixel Image Synthesis","created":"2021-04-08","cited_by_count":61,"area":null},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61,"area":null},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60,"area":null},{"id":"2102.07448","title":"OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving","created":"2021-02-15","cited_by_count":57,"area":null},{"id":"2103.17269","title":"CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields","created":"2021-03-31","cited_by_count":55,"area":null},{"id":"2112.11377","title":"Shape from Polarization for Complex Scenes in the Wild","created":"2021-12-21","cited_by_count":53,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2105.02467","title":"Body Meshes as Points","created":"2021-05-06","cited_by_count":45,"area":null},{"id":"2308.04583","title":"LATR: 3D Lane Detection from Monocular Images with Transformer","created":"2023-08-08","cited_by_count":44,"area":null},{"id":"2108.12178","title":"MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving","created":"2021-08-27","cited_by_count":41,"area":null},{"id":"2204.07178","title":"Relaxing Equivariance Constraints with Non-stationary Continuous Filters","created":"2022-04-14","cited_by_count":41,"area":null},{"id":"2209.01161","title":"Reconstructing editable prismatic CAD from rounded voxel models","created":"2022-09-02","cited_by_count":41,"area":null},{"id":"2303.05047","title":"Diversity-Measurable Anomaly Detection","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2203.15926","title":"Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images","created":"2022-03-29","cited_by_count":39,"area":null},{"id":"2206.07372","title":"MonoGround: Detecting Monocular 3D Objects from the Ground","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2303.05938","title":"ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction","created":"2023-03-10","cited_by_count":37,"area":null},{"id":"2203.15216","title":"Affine Medical Image Registration with Coarse-to-Fine Vision Transformer","created":"2022-03-29","cited_by_count":35,"area":null},{"id":"2209.02952","title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","created":"2022-09-07","cited_by_count":35,"area":null},{"id":"2103.10796","title":"CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization","created":"2021-03-19","cited_by_count":34,"area":null},{"id":"2105.14185","title":"FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions","created":"2021-05-29","cited_by_count":34,"area":null},{"id":"2109.05721","title":"ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment","created":"2021-09-13","cited_by_count":34,"area":null},{"id":"2301.13261","title":"Emergence of Maps in the Memories of Blind Navigation Agents","created":"2023-01-30","cited_by_count":33,"area":null},{"id":"2106.15947","title":"SOLO: A Simple Framework for Instance Segmentation","created":"2021-06-30","cited_by_count":32,"area":null},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31,"area":null},{"id":"2406.19464","title":"ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data","created":"2024-06-27","cited_by_count":31,"area":null},{"id":"2104.10419","title":"PP-YOLOv2: A Practical Object Detector","created":"2021-04-21","cited_by_count":30,"area":null},{"id":"2303.15288","title":"Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing","created":"2023-03-27","cited_by_count":30,"area":"diffusion"},{"id":"2206.13294","title":"LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation","created":"2022-06-27","cited_by_count":29,"area":null},{"id":"2212.01735","title":"Neural Fourier Filter Bank","created":"2022-12-04","cited_by_count":29,"area":null},{"id":"2306.15713","title":"Rethinking Closed-loop Training for Autonomous Driving","created":"2023-06-27","cited_by_count":29,"area":"driving"},{"id":"2405.04408","title":"DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks","created":"2024-05-07","cited_by_count":27,"area":null},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2404.14248","title":"NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results","created":"2024-04-22","cited_by_count":26,"area":null},{"id":"2104.04420","title":"SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras","created":"2021-04-09","cited_by_count":25,"area":null},{"id":"2103.13922","title":"ScanGAN360: A Generative Model of Realistic Scanpaths for 360$^{\\circ}$ Images","created":"2021-03-25","cited_by_count":23,"area":null},{"id":"2310.06131","title":"Learning Layer-wise Equivariances Automatically using Gradients","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2110.03396","title":"AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning","created":"2021-10-07","cited_by_count":21,"area":null},{"id":"2103.15233","title":"Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization","created":"2021-03-28","cited_by_count":20,"area":null},{"id":"2105.09936","title":"BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image","created":"2021-05-20","cited_by_count":20,"area":null},{"id":"2106.15944","title":"A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging","created":"2021-06-30","cited_by_count":20,"area":null},{"id":"2107.03021","title":"Bi-level Feature Alignment for Versatile Image Translation and Manipulation","created":"2021-07-07","cited_by_count":20,"area":null},{"id":"2101.10808","title":"Fast Facial Landmark Detection and Applications: A Survey","created":"2021-01-12","cited_by_count":18,"area":null},{"id":"2110.05132","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","created":"2021-10-11","cited_by_count":18,"area":null},{"id":"2211.11238","title":"RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments","created":"2022-11-21","cited_by_count":18,"area":null},{"id":"2311.15607","title":"Spatially Covariant Image Registration with Text Prompts","created":"2023-11-27","cited_by_count":18,"area":null},{"id":"2103.16086","title":"Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking","created":"2021-03-30","cited_by_count":17,"area":null},{"id":"2108.01285","title":"Toward Spatially Unbiased Generative Models","created":"2021-08-03","cited_by_count":17,"area":null},{"id":"2110.14118","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","created":"2021-10-27","cited_by_count":17,"area":"offlinerl"},{"id":"2203.06410","title":"Kernel Proposal Network for Arbitrary Shape Text Detection","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2104.10538","title":"Guided Table Structure Recognition through Anchor Optimization","created":"2021-04-21","cited_by_count":15,"area":null},{"id":"2207.12572","title":"Translating a Visual LEGO Manual to a Machine-Executable Plan","created":"2022-07-25","cited_by_count":15,"area":null},{"id":"2210.13604","title":"The Robustness Limits of SoTA Vision Models to Natural Variation","created":"2022-10-24","cited_by_count":15,"area":null},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2106.11160","title":"Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics","created":"2021-06-21","cited_by_count":14,"area":null},{"id":"2109.11798","title":"Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation","created":"2021-09-24","cited_by_count":14,"area":null},{"id":"2111.02360","title":"Subpixel Heatmap Regression for Facial Landmark Localization","created":"2021-11-03","cited_by_count":14,"area":null},{"id":"2209.07052","title":"MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14,"area":null},{"id":"2104.00613","title":"The surprising impact of mask-head architecture on novel class segmentation","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2201.09874","title":"CVAE-H: Conditionalizing Variational Autoencoders via Hypernetworks and Trajectory Forecasting for Autonomous Driving","created":"2022-01-24","cited_by_count":13,"area":null},{"id":"2105.12724","title":"Smile Like You Mean It: Driving Animatronic Robotic Face with Learned Models","created":"2021-05-26","cited_by_count":12,"area":null},{"id":"2108.07884","title":"Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs","created":"2021-08-17","cited_by_count":12,"area":null},{"id":"2202.12846","title":"An initial alignment between neural network and target is needed for gradient descent to learn","created":"2022-02-25","cited_by_count":12,"area":null},{"id":"2206.06100","title":"AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields","created":"2022-06-13","cited_by_count":12,"area":null},{"id":"2207.08951","title":"MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2307.16377","title":"JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery","created":"2023-07-31","cited_by_count":12,"area":null},{"id":"2110.01644","title":"Pixel-Level Bijective Matching for Video Object Segmentation","created":"2021-10-04","cited_by_count":11,"area":null},{"id":"2401.09252","title":"3D Scene Geometry Estimation from 360$^\\circ$ Imagery: A Survey","created":"2024-01-17","cited_by_count":11,"area":null},{"id":"2403.00729","title":"Can Transformers Capture Spatial Relations between Objects?","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2503.16067","title":"Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures","created":"2025-03-20","cited_by_count":11,"area":null},{"id":"2103.14572","title":"Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings","created":"2021-03-26","cited_by_count":10,"area":null},{"id":"2210.01559","title":"Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2301.07895","title":"Spatially Covariant Lesion Segmentation","created":"2023-01-19","cited_by_count":10,"area":null},{"id":"2305.00398","title":"SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification","created":"2023-04-30","cited_by_count":10,"area":null}],"next_cursor":"100"}