{"total":169,"rows":[{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327,"area":null},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174,"area":null},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172,"area":null},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148,"area":null},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146,"area":null},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2105.01905","title":"4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface","created":"2021-05-05","cited_by_count":124,"area":null},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122,"area":null},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116,"area":"diffusion"},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102,"area":null},{"id":"2204.13683","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","created":"2022-04-28","cited_by_count":96,"area":"driving"},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82,"area":null},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","cited_by_count":81,"area":null},{"id":"2105.04619","title":"Enhancing Photorealism Enhancement","created":"2021-05-10","cited_by_count":74,"area":null},{"id":"2102.11859","title":"STEP: Segmenting and Tracking Every Pixel","created":"2021-02-23","cited_by_count":73,"area":null},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64,"area":null},{"id":"2506.07310","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","created":"2025-06-08","cited_by_count":58,"area":null},{"id":"2404.04808","title":"MemFlow: Optical Flow Estimation and Prediction with Memory","created":"2024-04-07","cited_by_count":55,"area":null},{"id":"2212.03863","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","created":"2022-12-07","cited_by_count":49,"area":null},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48,"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":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38,"area":null},{"id":"2302.01334","title":"STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation","created":"2023-02-02","cited_by_count":37,"area":null},{"id":"2211.03568","title":"CASA: Category-agnostic Skeletal Animal Reconstruction","created":"2022-11-04","cited_by_count":35,"area":null},{"id":"2506.21526","title":"WAFT: Warping-Alone Field Transforms for Optical Flow","created":"2025-06-26","cited_by_count":34,"area":null},{"id":"2108.05570","title":"LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation","created":"2021-08-12","cited_by_count":33,"area":null},{"id":"2203.05056","title":"SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving","created":"2022-03-09","cited_by_count":32,"area":null},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30,"area":null},{"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,"area":null},{"id":"2503.14880","title":"DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework","created":"2025-03-19","cited_by_count":30,"area":null},{"id":"2203.16895","title":"Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds","created":"2022-03-31","cited_by_count":28,"area":null},{"id":"2207.11368","title":"Neural-Sim: Learning to Generate Training Data with NeRF","created":"2022-07-22","cited_by_count":27,"area":null},{"id":"2103.03114","title":"Self-supervised Geometric Perception","created":"2021-03-04","cited_by_count":26,"area":null},{"id":"2106.09453","title":"Learning to Associate Every Segment for Video Panoptic Segmentation","created":"2021-06-17","cited_by_count":25,"area":null},{"id":"2108.12545","title":"Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation","created":"2021-08-28","cited_by_count":25,"area":null},{"id":"2103.12209","title":"Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision","created":"2021-03-22","cited_by_count":24,"area":null},{"id":"2110.04111","title":"Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation","created":"2021-10-08","cited_by_count":24,"area":null},{"id":"2112.08949","title":"Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation","created":"2021-12-16","cited_by_count":24,"area":null},{"id":"2104.13395","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","created":"2021-04-27","cited_by_count":21,"area":null},{"id":"2107.11004","title":"Domain Adaptive Video Segmentation via Temporal Consistency Regularization","created":"2021-07-23","cited_by_count":21,"area":null},{"id":"2111.04418","title":"A Survey of Human Activity Recognition in Smart Homes Based on IoT Sensors Algorithms: Taxonomies, Challenges, and Opportunities with Deep Learning","created":"2021-10-18","cited_by_count":21,"area":null},{"id":"2404.16484","title":"Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey","created":"2024-04-25","cited_by_count":19,"area":null},{"id":"2309.16217","title":"GAFlow: Incorporating Gaussian Attention into Optical Flow","created":"2023-09-28","cited_by_count":18,"area":null},{"id":"2406.00934","title":"LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2107.05617","title":"Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games","created":"2021-07-12","cited_by_count":17,"area":null},{"id":"2206.09592","title":"DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection","created":"2022-06-20","cited_by_count":17,"area":"diffusion"},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16,"area":null},{"id":"2207.05025","title":"PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models","created":"2022-07-11","cited_by_count":15,"area":null},{"id":"2304.03526","title":"Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field","created":"2023-04-07","cited_by_count":15,"area":null},{"id":"2311.02661","title":"CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning","created":"2023-11-05","cited_by_count":15,"area":null},{"id":"2412.00683","title":"DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement","created":"2024-12-01","cited_by_count":15,"area":null},{"id":"2108.11224","title":"Multi-domain semantic segmentation with overlapping labels","created":"2021-08-25","cited_by_count":14,"area":null},{"id":"2110.06685","title":"Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-10-13","cited_by_count":13,"area":null},{"id":"2408.16478","title":"MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2111.06934","title":"Contrastive Feature Loss for Image Prediction","created":"2021-11-12","cited_by_count":12,"area":null},{"id":"2210.16900","title":"High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)","created":"2022-10-30","cited_by_count":12,"area":null},{"id":"2211.10412","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2304.07051","title":"The Second Monocular Depth Estimation Challenge","created":"2023-04-14","cited_by_count":12,"area":null},{"id":"2503.16801","title":"Auto-Regressive Diffusion for Generating 3D Human-Object Interactions","created":"2025-03-21","cited_by_count":12,"area":null},{"id":"2112.09290","title":"PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision","created":"2021-12-17","cited_by_count":11,"area":null},{"id":"2207.02372","title":"Domain Adaptive Video Segmentation via Temporal Pseudo Supervision","created":"2022-07-06","cited_by_count":11,"area":null},{"id":"2211.05709","title":"AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies","created":"2022-11-10","cited_by_count":11,"area":null},{"id":"2409.05688","title":"LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow","created":"2024-09-09","cited_by_count":11,"area":null},{"id":"2212.01762","title":"Self-supervised AutoFlow","created":"2022-12-04","cited_by_count":10,"area":null},{"id":"2303.14361","title":"Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation","created":"2023-03-25","cited_by_count":10,"area":null},{"id":"2309.05956","title":"Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation","created":"2023-09-12","cited_by_count":10,"area":"diffusion"},{"id":"2309.12172","title":"SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2402.03830","title":"OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving","created":"2024-02-06","cited_by_count":10,"area":"driving"},{"id":"2508.21824","title":"DriveQA: Passing the Driving Knowledge Test","created":"2025-08-29","cited_by_count":10,"area":"driving"},{"id":"2509.05297","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2107.11052","title":"Unsupervised Domain Adaptation for Video Semantic Segmentation","created":"2021-07-23","cited_by_count":9,"area":null},{"id":"2210.04708","title":"GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal","created":"2022-10-10","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":"2008.12969","title":"Driving Through Ghosts: Behavioral Cloning with False Positives","created":"2020-08-29","cited_by_count":8,"area":"offlinerl"},{"id":"2206.15083","title":"UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration","created":"2022-06-30","cited_by_count":8,"area":null},{"id":"2311.07761","title":"Amodal Optical Flow","created":"2023-11-13","cited_by_count":8,"area":null},{"id":"2401.04942","title":"Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic Dataset and New Metrics","created":"2024-01-10","cited_by_count":8,"area":null},{"id":"2412.00730","title":"SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2505.09368","title":"RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2506.23151","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","created":"2025-06-29","cited_by_count":7,"area":null},{"id":"2104.13617","title":"End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning","created":"2021-04-28","cited_by_count":6,"area":null},{"id":"2111.13681","title":"ManiFest: Manifold Deformation for Few-shot Image Translation","created":"2021-11-26","cited_by_count":6,"area":null},{"id":"2306.17302","title":"Robust Roadside Perception: an Automated Data Synthesis Pipeline Minimizing Human Annotation","created":"2023-06-29","cited_by_count":6,"area":null},{"id":"2308.07537","title":"AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes","created":"2023-08-15","cited_by_count":6,"area":null},{"id":"2311.13254","title":"Unified Domain Adaptive Semantic Segmentation","created":"2023-11-22","cited_by_count":6,"area":null},{"id":"2408.13175","title":"Identifying Crucial Objects in Blind and Low-Vision Individuals' Navigation","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2201.05723","title":"Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow","created":"2022-01-15","cited_by_count":5,"area":null},{"id":"2205.11888","title":"Mind The Gap: Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2206.14372","title":"Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logic","created":"2022-06-29","cited_by_count":5,"area":null},{"id":"2211.16234","title":"SimCS: Simulation for Domain Incremental Online Continual Segmentation","created":"2022-11-29","cited_by_count":5,"area":null},{"id":"2212.10340","title":"Weakly supervised training of universal visual concepts for multi-domain semantic segmentation","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2312.00694","title":"Object Detector Differences when using Synthetic and Real Training Data","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2406.10891","title":"Noisy Annotations in Semantic Segmentation","created":"2024-06-16","cited_by_count":5,"area":null}],"next_cursor":"100"}