{"total":132,"rows":[{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575,"area":null},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215,"area":null},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150,"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":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109,"area":null},{"id":"2111.12264","title":"Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes","created":"2021-11-24","cited_by_count":83,"area":null},{"id":"2107.11264","title":"Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation","created":"2021-07-23","cited_by_count":77,"area":null},{"id":"2108.08829","title":"Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2211.14512","title":"Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation","created":"2022-11-26","cited_by_count":55,"area":null},{"id":"2303.09875","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","created":"2023-03-17","cited_by_count":53,"area":null},{"id":"2203.16931","title":"Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond","created":"2022-03-31","cited_by_count":48,"area":null},{"id":"2207.02606","title":"DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition","created":"2022-07-06","cited_by_count":42,"area":null},{"id":"2102.02696","title":"Active Boundary Loss for Semantic Segmentation","created":"2021-02-04","cited_by_count":40,"area":null},{"id":"2302.14677","title":"Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger","created":"2023-02-28","cited_by_count":40,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2205.15361","title":"TubeFormer-DeepLab: Video Mask Transformer","created":"2022-05-30","cited_by_count":35,"area":null},{"id":"2305.16972","title":"Maskomaly:Zero-Shot Mask Anomaly Segmentation","created":"2023-05-26","cited_by_count":34,"area":null},{"id":"2110.12369","title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","created":"2021-10-24","cited_by_count":31,"area":null},{"id":"2206.13199","title":"MGNet: Monocular Geometric Scene Understanding for Autonomous Driving","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2207.10436","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","created":"2022-07-21","cited_by_count":25,"area":null},{"id":"2204.03330","title":"Learning Local and Global Temporal Contexts for Video Semantic Segmentation","created":"2022-04-07","cited_by_count":24,"area":null},{"id":"2304.04694","title":"Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation","created":"2023-04-10","cited_by_count":24,"area":null},{"id":"2104.00877","title":"S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation","created":"2021-04-02","cited_by_count":23,"area":null},{"id":"2104.06697","title":"Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction","created":"2021-04-14","cited_by_count":23,"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":"2204.05538","title":"NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night","created":"2022-04-12","cited_by_count":21,"area":null},{"id":"2207.06104","title":"Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification","created":"2022-07-13","cited_by_count":20,"area":null},{"id":"2210.00411","title":"Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem","created":"2022-10-02","cited_by_count":20,"area":null},{"id":"2102.06685","title":"Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance","created":"2021-02-11","cited_by_count":19,"area":null},{"id":"2107.13221","title":"Normalization Matters in Weakly Supervised Object Localization","created":"2021-07-28","cited_by_count":19,"area":null},{"id":"2108.00968","title":"Robust Semantic Segmentation with Superpixel-Mix","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2210.02074","title":"Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2112.06116","title":"Stereoscopic Universal Perturbations across Different Architectures and Datasets","created":"2021-12-12","cited_by_count":17,"area":null},{"id":"2312.15364","title":"WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments","created":"2023-12-23","cited_by_count":17,"area":null},{"id":"2104.09498","title":"Comparing Correspondences: Video Prediction with Correspondence-wise Losses","created":"2021-04-19","cited_by_count":16,"area":null},{"id":"2203.10730","title":"Semantic Segmentation with Active Semi-Supervised Learning","created":"2022-03-21","cited_by_count":16,"area":null},{"id":"2107.14209","title":"A Unified Efficient Pyramid Transformer for Semantic Segmentation","created":"2021-07-29","cited_by_count":14,"area":null},{"id":"2108.11224","title":"Multi-domain semantic segmentation with overlapping labels","created":"2021-08-25","cited_by_count":14,"area":null},{"id":"2107.09858","title":"Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation","created":"2021-07-21","cited_by_count":11,"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":"2207.02372","title":"Domain Adaptive Video Segmentation via Temporal Pseudo Supervision","created":"2022-07-06","cited_by_count":11,"area":null},{"id":"2212.07911","title":"Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2303.06920","title":"Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation","created":"2023-03-13","cited_by_count":11,"area":null},{"id":"2412.01646","title":"Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2112.12833","title":"Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data","created":"2021-12-23","cited_by_count":10,"area":null},{"id":"2203.05983","title":"PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2207.04415","title":"SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow","created":"2022-07-10","cited_by_count":10,"area":null},{"id":"2209.04471","title":"MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2022-09-09","cited_by_count":10,"area":null},{"id":"2407.21631","title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","created":"2024-07-31","cited_by_count":10,"area":null},{"id":"2106.03242","title":"Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs","created":"2021-06-06","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":"2107.13154","title":"Global Aggregation then Local Distribution for Scene Parsing","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2110.02549","title":"See Yourself in Others: Attending Multiple Tasks for Own Failure Detection","created":"2021-10-06","cited_by_count":8,"area":null},{"id":"2201.02260","title":"CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials","created":"2022-01-06","cited_by_count":8,"area":null},{"id":"2203.10528","title":"Stochastic Video Prediction with Structure and Motion","created":"2022-03-20","cited_by_count":8,"area":null},{"id":"2301.08555","title":"Hybrid Open-set Segmentation with Synthetic Negative Data","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2405.02608","title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","created":"2024-05-04","cited_by_count":8,"area":null},{"id":"2104.03962","title":"Panoptic Segmentation Forecasting","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2104.04606","title":"RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes","created":"2021-04-09","cited_by_count":7,"area":null},{"id":"2109.13432","title":"Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency","created":"2021-09-28","cited_by_count":7,"area":null},{"id":"2309.08020","title":"Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2401.15741","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","created":"2024-01-28","cited_by_count":7,"area":null},{"id":"2102.01586","title":"U-LanD: Uncertainty-Driven Video Landmark Detection","created":"2021-02-02","cited_by_count":6,"area":null},{"id":"2104.13602","title":"DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering","created":"2021-04-28","cited_by_count":6,"area":null},{"id":"2109.07245","title":"Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images","created":"2021-09-15","cited_by_count":6,"area":null},{"id":"2202.02002","title":"Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2105.00114","title":"Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames","created":"2021-04-30","cited_by_count":5,"area":null},{"id":"2105.11651","title":"Fast and Accurate Scene Parsing via Bi-direction Alignment Networks","created":"2021-05-25","cited_by_count":5,"area":null},{"id":"2112.05351","title":"Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","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":"2105.11668","title":"BoundarySqueeze: Image Segmentation as Boundary Squeezing","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2110.13996","title":"Controllable Data Augmentation Through Deep Relighting","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2111.00770","title":"Dense Prediction with Attentive Feature Aggregation","created":"2021-11-01","cited_by_count":4,"area":null},{"id":"2202.08700","title":"Detecting and Learning the Unknown in Semantic Segmentation","created":"2022-02-17","cited_by_count":4,"area":null},{"id":"2203.01087","title":"Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2207.06242","title":"SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2207.06351","title":"Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2412.09329","title":"Towards Open-Vocabulary Video Semantic Segmentation","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2512.01774","title":"Evaluating SAM2 for Video Semantic Segmentation","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2101.10777","title":"Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion","created":"2021-01-26","cited_by_count":3,"area":null},{"id":"2109.04991","title":"Detection of GAN-synthesized street videos","created":"2021-09-10","cited_by_count":3,"area":null},{"id":"2203.14481","title":"DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2206.13677","title":"Towards Global-Scale Crowd+AI Techniques to Map and Assess Sidewalks for People with Disabilities","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2304.08820","title":"Motion-state Alignment for Video Semantic Segmentation","created":"2023-04-18","cited_by_count":3,"area":null},{"id":"2405.16277","title":"Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2408.16504","title":"A Simple and Generalist Approach for Panoptic Segmentation","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2412.08671","title":"A Deep Semantic Segmentation Network with Semantic and Contextual Refinements","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2503.15676","title":"High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous Flight","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2103.11031","title":"Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation","created":"2021-03-19","cited_by_count":2,"area":null},{"id":"2104.05255","title":"Improving Online Performance Prediction for Semantic Segmentation","created":"2021-04-12","cited_by_count":2,"area":null},{"id":"2303.04315","title":"A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2309.01391","title":"SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2311.07578","title":"A Metacognitive Approach to Out-of-Distribution Detection for Segmentation","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2311.10883","title":"Labeling Indoor Scenes with Fusion of Out-of-the-Box Perception Models","created":"2023-11-17","cited_by_count":2,"area":null},{"id":"2506.13552","title":"A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2104.06957","title":"ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation","created":"2021-04-14","cited_by_count":1,"area":null},{"id":"2106.16000","title":"Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint","created":"2021-06-30","cited_by_count":1,"area":null}],"next_cursor":"100"}