{"list":"other","total":89,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"1910.04851","title":"Addressing Failure Prediction by Learning Model Confidence","created":"2019-10-01","cited_by_count":186},{"id":"2405.17429","title":"GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction","created":"2024-05-27","cited_by_count":157},{"id":"1811.12709","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","created":"2018-11-30","cited_by_count":143},{"id":"1904.07595","title":"Detecting the Unexpected via Image Resynthesis","created":"2019-04-16","cited_by_count":137},{"id":"2012.06575","title":"Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation","created":"2020-12-09","cited_by_count":133},{"id":"2203.04050","title":"BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs","created":"2022-03-08","cited_by_count":123},{"id":"2003.08440","title":"Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation","created":"2020-03-18","cited_by_count":96},{"id":"2312.01919","title":"COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction","created":"2023-12-04","cited_by_count":96},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90},{"id":"2309.14616","title":"NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space","created":"2023-09-26","cited_by_count":90},{"id":"2412.04384","title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","created":"2024-12-05","cited_by_count":86},{"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},{"id":"2108.09770","title":"MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching","created":"2021-08-22","cited_by_count":82},{"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},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2510.26125","title":"WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios","created":"2025-10-30","cited_by_count":62},{"id":"2410.10429","title":"DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model","created":"2024-10-14","cited_by_count":61},{"id":"2407.00959","title":"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving","created":"2024-07-01","cited_by_count":56},{"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},{"id":"2204.07965","title":"Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint","created":"2022-04-17","cited_by_count":53},{"id":"2401.09413","title":"POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images","created":"2024-01-17","cited_by_count":52},{"id":"2108.04562","title":"Deep Metric Learning for Open World Semantic Segmentation","created":"2021-08-10","cited_by_count":51},{"id":"2405.13675","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","created":"2024-05-22","cited_by_count":50},{"id":"2107.12628","title":"Energy-Based Open-World Uncertainty Modeling for Confidence Calibration","created":"2021-07-27","cited_by_count":46},{"id":"2404.11958","title":"Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation","created":"2024-04-18","cited_by_count":43},{"id":"2301.03407","title":"On Advantages of Mask-level Recognition for Outlier-aware Segmentation","created":"2023-01-09","cited_by_count":42},{"id":"2510.04333","title":"RAP: 3D Rasterization Augmented End-to-End Planning","created":"2025-10-05","cited_by_count":41},{"id":"2211.08691","title":"Towards Long-Tailed 3D Detection","created":"2022-11-16","cited_by_count":40},{"id":"2312.05752","title":"Camera-based 3D Semantic Scene Completion with Sparse Guidance Network","created":"2023-12-10","cited_by_count":40},{"id":"2402.15374","title":"Outlier detection by ensembling uncertainty with negative objectness","created":"2024-02-23","cited_by_count":34},{"id":"2408.09859","title":"OccMamba: Semantic Occupancy Prediction with State Space Models","created":"2024-08-19","cited_by_count":30},{"id":"2502.07309","title":"Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving","created":"2025-02-11","cited_by_count":29},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27},{"id":"2305.16133","title":"OVO: Open-Vocabulary Occupancy","created":"2023-05-25","cited_by_count":24},{"id":"2504.06994","title":"RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration","created":"2025-04-09","cited_by_count":23},{"id":"2403.09412","title":"OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments","created":"2024-03-14","cited_by_count":22},{"id":"2411.07725","title":"ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions","created":"2024-11-12","cited_by_count":20},{"id":"2210.08375","title":"Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining","created":"2022-10-15","cited_by_count":19},{"id":"2309.04573","title":"Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation","created":"2023-09-08","cited_by_count":18},{"id":"2209.14435","title":"Out-of-Distribution Detection for LiDAR-based 3D Object Detection","created":"2022-09-28","cited_by_count":17},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17},{"id":"2412.08774","title":"ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder","created":"2024-12-11","cited_by_count":17},{"id":"1909.00676","title":"This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity","created":"2019-09-02","cited_by_count":16},{"id":"2308.06530","title":"BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation","created":"2023-08-12","cited_by_count":14},{"id":"2405.07865","title":"AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous Driving","created":"2024-05-13","cited_by_count":14},{"id":"2410.00337","title":"SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs","created":"2024-10-01","cited_by_count":14},{"id":"2505.10685","title":"GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention","created":"2025-05-15","cited_by_count":14},{"id":"2403.05329","title":"OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction","created":"2024-03-08","cited_by_count":13},{"id":"2506.04623","title":"VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection","created":"2025-06-05","cited_by_count":13},{"id":"2310.12152","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","created":"2023-10-18","cited_by_count":11},{"id":"2404.15879","title":"Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection","created":"2024-04-24","cited_by_count":11},{"id":"2403.14366","title":"SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field","created":"2024-03-21","cited_by_count":10},{"id":"2503.15185","title":"3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation","created":"2025-03-19","cited_by_count":9},{"id":"2504.10117","title":"AGO: Adaptive Grounding for Open World 3D Occupancy Prediction","created":"2025-04-14","cited_by_count":9},{"id":"2509.03887","title":"OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction","created":"2025-09-04","cited_by_count":9},{"id":"2404.12501","title":"SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation","created":"2024-04-18","cited_by_count":8},{"id":"2412.08243","title":"Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction","created":"2024-12-11","cited_by_count":8},{"id":"2411.03696","title":"OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction","created":"2024-11-06","cited_by_count":7},{"id":"2507.08555","title":"Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion","created":"2025-07-11","cited_by_count":7},{"id":"2403.11796","title":"OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation","created":"2024-03-18","cited_by_count":6},{"id":"2503.10605","title":"OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction","created":"2025-03-13","cited_by_count":6},{"id":"2410.08687","title":"Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation","created":"2024-10-11","cited_by_count":4},{"id":"2510.04759","title":"Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction","created":"2025-10-06","cited_by_count":4},{"id":"2510.22141","title":"LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction","created":"2025-10-25","cited_by_count":4},{"id":"2410.23767","title":"HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data","created":"2024-10-31","cited_by_count":2},{"id":"2503.22309","title":"A Dataset for Semantic Segmentation in the Presence of Unknowns","created":"2025-03-28","cited_by_count":2},{"id":"2505.22461","title":"SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels","created":"2025-05-28","cited_by_count":2},{"id":"2505.23115","title":"Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving","created":"2025-05-29","cited_by_count":2},{"id":"2506.21185","title":"Out-of-Distribution Semantic Occupancy Prediction","created":"2025-06-26","cited_by_count":2},{"id":"2509.19973","title":"OmniScene: Attention-Augmented Multimodal 4D Scene Understanding for Autonomous Driving","created":"2025-09-24","cited_by_count":2},{"id":"2510.08631","title":"Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMs","created":"2025-10-08","cited_by_count":2},{"id":"2511.06720","title":"Relative Energy Learning for LiDAR Out-of-Distribution Detection","created":"2025-11-10","cited_by_count":2},{"id":"2508.17634","title":"Finding Outliers in a Haystack: Anomaly Detection for Large Pointcloud Scenes","created":"2025-08-25","cited_by_count":1},{"id":"2510.13198","title":"Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion","created":"2025-10-15","cited_by_count":1}],"next_cursor":null}