{"total":291,"rows":[{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2108.07009","title":"Pixel Difference Networks for Efficient Edge Detection","created":"2021-08-16","cited_by_count":168,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141,"area":null},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124,"area":null},{"id":"2204.06986","title":"Cross-Image Relational Knowledge Distillation for Semantic Segmentation","created":"2022-04-14","cited_by_count":118,"area":"distill"},{"id":"2103.10429","title":"Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks","created":"2021-03-18","cited_by_count":103,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2101.06085","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","created":"2021-01-15","cited_by_count":89,"area":null},{"id":"2107.08623","title":"LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation","created":"2021-07-19","cited_by_count":85,"area":null},{"id":"2206.02066","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","created":"2022-06-04","cited_by_count":84,"area":null},{"id":"2108.11250","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","created":"2021-08-25","cited_by_count":82,"area":"wm"},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70,"area":"distill"},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69,"area":null},{"id":"2402.01881","title":"Large Language Model Agent for Hyper-Parameter Optimization","created":"2024-02-02","cited_by_count":64,"area":"agents"},{"id":"2201.02831","title":"CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation","created":"2022-01-08","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50,"area":null},{"id":"2104.02243","title":"3D-to-2D Distillation for Indoor Scene Parsing","created":"2021-04-06","cited_by_count":48,"area":null},{"id":"2110.08988","title":"FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation","created":"2021-10-18","cited_by_count":45,"area":null},{"id":"2112.05144","title":"Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing","created":"2021-12-09","cited_by_count":45,"area":null},{"id":"2108.09987","title":"Efficient Medical Image Segmentation Based on Knowledge Distillation","created":"2021-08-23","cited_by_count":43,"area":"distill"},{"id":"2103.12040","title":"LaneAF: Robust Multi-Lane Detection with Affinity Fields","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2303.14651","title":"You Only Segment Once: Towards Real-Time Panoptic Segmentation","created":"2023-03-26","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":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2303.09554","title":"PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision","created":"2023-03-16","cited_by_count":36,"area":null},{"id":"2305.03944","title":"Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation","created":"2023-05-06","cited_by_count":36,"area":"distill"},{"id":"2210.00173","title":"Predictive Inference with Feature Conformal Prediction","created":"2022-10-01","cited_by_count":34,"area":null},{"id":"2204.02681","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","created":"2022-04-06","cited_by_count":33,"area":null},{"id":"2107.03172","title":"Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World","created":"2021-07-07","cited_by_count":30,"area":null},{"id":"2112.02102","title":"Echocardiography Segmentation with Enforced Temporal Consistency","created":"2021-12-03","cited_by_count":30,"area":null},{"id":"2304.14845","title":"SFD2: Semantic-guided Feature Detection and Description","created":"2023-04-28","cited_by_count":28,"area":null},{"id":"2310.16069","title":"CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting","created":"2023-10-24","cited_by_count":28,"area":"lr"},{"id":"2105.02359","title":"MODS -- A USV-oriented object detection and obstacle segmentation benchmark","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2302.06378","title":"Semantic Image Segmentation: Two Decades of Research","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2211.08681","title":"Interclass Prototype Relation for Few-Shot Segmentation","created":"2022-11-16","cited_by_count":25,"area":null},{"id":"2103.17001","title":"Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Cameras","created":"2021-03-31","cited_by_count":24,"area":null},{"id":"2103.00868","title":"Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning","created":"2021-03-01","cited_by_count":23,"area":null},{"id":"2103.11351","title":"Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving","created":"2021-03-21","cited_by_count":23,"area":null},{"id":"2207.10614","title":"A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2108.09174","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","created":"2021-08-20","cited_by_count":22,"area":null},{"id":"2312.17071","title":"SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation","created":"2023-12-28","cited_by_count":22,"area":null},{"id":"2208.10590","title":"A Survey and Framework of Cooperative Perception: From Heterogeneous Singleton to Hierarchical Cooperation","created":"2022-08-22","cited_by_count":21,"area":null},{"id":"2401.01624","title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","created":"2024-01-03","cited_by_count":21,"area":null},{"id":"2107.08591","title":"Double Similarity Distillation for Semantic Image Segmentation","created":"2021-07-19","cited_by_count":19,"area":null},{"id":"2110.00934","title":"Bounding Box Tightness Prior for Weakly Supervised Image Segmentation","created":"2021-10-03","cited_by_count":19,"area":null},{"id":"2112.03241","title":"Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey","created":"2021-12-06","cited_by_count":19,"area":null},{"id":"2103.13109","title":"A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios","created":"2021-03-24","cited_by_count":18,"area":null},{"id":"2210.03925","title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","created":"2022-10-08","cited_by_count":18,"area":null},{"id":"2503.18445","title":"Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness","created":"2025-03-24","cited_by_count":18,"area":null},{"id":"2109.00699","title":"FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation","created":"2021-09-02","cited_by_count":17,"area":null},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17,"area":"distill"},{"id":"2205.03650","title":"Distilling Inter-Class Distance for Semantic Segmentation","created":"2022-05-07","cited_by_count":16,"area":"distill"},{"id":"2212.09098","title":"Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GAN","created":"2022-12-18","cited_by_count":16,"area":null},{"id":"2203.01177","title":"Detecting Adversarial Perturbations in Multi-Task Perception","created":"2022-03-02","cited_by_count":15,"area":null},{"id":"2203.04031","title":"Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes","created":"2022-03-08","cited_by_count":15,"area":null},{"id":"2203.15163","title":"CAT-Net: A Cross-Slice Attention Transformer Model for Prostate Zonal Segmentation in MRI","created":"2022-03-29","cited_by_count":15,"area":null},{"id":"2306.08075","title":"BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation","created":"2023-06-13","cited_by_count":15,"area":"distill"},{"id":"2407.13677","title":"PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2103.12212","title":"CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation","created":"2021-03-22","cited_by_count":14,"area":null},{"id":"2103.13044","title":"MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation","created":"2021-03-24","cited_by_count":14,"area":null},{"id":"2106.15322","title":"TNCR: Table Net Detection and Classification Dataset","created":"2021-06-19","cited_by_count":14,"area":null},{"id":"2201.11871","title":"Infrastructure-Based Object Detection and Tracking for Cooperative Driving Automation: A Survey","created":"2022-01-28","cited_by_count":14,"area":null},{"id":"2206.10711","title":"Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning","created":"2022-06-21","cited_by_count":14,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2208.14143","title":"FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation","created":"2022-08-30","cited_by_count":14,"area":"distill"},{"id":"2211.13238","title":"ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans","created":"2022-11-23","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","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":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2307.10705","title":"TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars","created":"2023-07-20","cited_by_count":13,"area":null},{"id":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2111.11629","title":"Uncertainty-Aware Deep Co-training for Semi-supervised Medical Image Segmentation","created":"2021-11-23","cited_by_count":12,"area":null},{"id":"2203.01074","title":"Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2302.10484","title":"Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN","created":"2023-02-21","cited_by_count":12,"area":null},{"id":"2105.04075","title":"CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation","created":"2021-05-10","cited_by_count":11,"area":null},{"id":"2205.07690","title":"Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml","created":"2022-05-16","cited_by_count":11,"area":null},{"id":"2601.08301","title":"ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation","created":"2026-01-13","cited_by_count":11,"area":"distill"},{"id":"2110.02833","title":"Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2206.07664","title":"CRISP - Reliable Uncertainty Estimation for Medical Image Segmentation","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2306.10364","title":"Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation","created":"2023-06-17","cited_by_count":10,"area":null},{"id":"2307.16418","title":"DRAW: Defending Camera-shooted RAW against Image Manipulation","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2503.06700","title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","created":"2025-03-09","cited_by_count":10,"area":null},{"id":"2507.01182","title":"Rapid Salient Object Detection with Difference Convolutional Neural Networks","created":"2025-07-01","cited_by_count":10,"area":null},{"id":"2103.00869","title":"Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning","created":"2021-03-01","cited_by_count":9,"area":null},{"id":"2208.05271","title":"Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation","created":"2022-08-10","cited_by_count":9,"area":null},{"id":"2302.02125","title":"Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2503.08043","title":"Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation","created":"2025-03-11","cited_by_count":9,"area":"distill"},{"id":"2401.01445","title":"Indoor Obstacle Discovery on Reflective Ground via Monocular Camera","created":"2024-01-02","cited_by_count":8,"area":null},{"id":"1810.07225","title":"Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories","created":"2018-10-16","cited_by_count":7,"area":"offlinerl"},{"id":"2108.04584","title":"UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2109.05443","title":"CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation","created":"2021-09-12","cited_by_count":7,"area":null},{"id":"2203.08667","title":"Graph Flow: Cross-layer Graph Flow Distillation for Dual Efficient Medical Image Segmentation","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2206.08605","title":"On Efficient Real-Time Semantic Segmentation: A Survey","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2304.01636","title":"Label-guided Attention Distillation for Lane Segmentation","created":"2023-04-04","cited_by_count":7,"area":null}],"next_cursor":"100"}