{"total":222,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2206.08171","title":"K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions","created":"2022-06-16","cited_by_count":108,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2107.13802","title":"RigNet: Repetitive Image Guided Network for Depth Completion","created":"2021-07-29","cited_by_count":80,"area":null},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75,"area":null},{"id":"2204.03742","title":"Mitosis domain generalization in histopathology images -- The MIDOG challenge","created":"2022-04-06","cited_by_count":67,"area":null},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64,"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":"2106.06351","title":"Part-aware Panoptic Segmentation","created":"2021-06-11","cited_by_count":56,"area":null},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56,"area":null},{"id":"2209.07790","title":"A Large-scale Multiple-objective Method for Black-box Attack against Object Detection","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53,"area":null},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51,"area":null},{"id":"2202.11983","title":"GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021","created":"2022-02-24","cited_by_count":46,"area":null},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43,"area":null},{"id":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38,"area":null},{"id":"2204.04655","title":"Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation","created":"2022-04-10","cited_by_count":38,"area":null},{"id":"2106.02733","title":"DISCO: accurate Discrete Scale Convolutions","created":"2021-06-04","cited_by_count":36,"area":null},{"id":"2112.02582","title":"PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation","created":"2021-12-05","cited_by_count":36,"area":null},{"id":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36,"area":null},{"id":"2205.15361","title":"TubeFormer-DeepLab: Video Mask Transformer","created":"2022-05-30","cited_by_count":35,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"area":null},{"id":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32,"area":null},{"id":"2211.16200","title":"From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments","created":"2022-11-26","cited_by_count":32,"area":null},{"id":"2306.01736","title":"DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model","created":"2023-06-02","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":"2109.07107","title":"Anchor DETR: Query Design for Transformer-Based Object Detection","created":"2021-09-15","cited_by_count":30,"area":null},{"id":"2404.03507","title":"DQ-DETR: DETR with Dynamic Query for Tiny Object Detection","created":"2024-04-04","cited_by_count":28,"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":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25,"area":"moe"},{"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":"2404.08639","title":"COCONut: Modernizing COCO Segmentation","created":"2024-04-12","cited_by_count":24,"area":null},{"id":"2204.10380","title":"The 6th AI City Challenge","created":"2022-04-21","cited_by_count":23,"area":null},{"id":"2106.09748","title":"DeepLab2: A TensorFlow Library for Deep Labeling","created":"2021-06-17","cited_by_count":22,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2308.03594","title":"FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision","created":"2023-08-07","cited_by_count":22,"area":null},{"id":"2412.10116","title":"HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection","created":"2024-12-13","cited_by_count":22,"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":"2303.15062","title":"The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2301.00954","title":"PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation","created":"2023-01-03","cited_by_count":19,"area":null},{"id":"2111.10250","title":"Panoptic Segmentation: A Review","created":"2021-11-19","cited_by_count":18,"area":null},{"id":"2306.17319","title":"ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation","created":"2023-06-29","cited_by_count":18,"area":null},{"id":"2101.08040","title":"1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking","created":"2021-01-20","cited_by_count":17,"area":null},{"id":"2306.15988","title":"AFPN: Asymptotic Feature Pyramid Network for Object Detection","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2206.08016","title":"Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches","created":"2022-06-16","cited_by_count":15,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2311.01619","title":"InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images","created":"2023-11-02","cited_by_count":15,"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":"2107.06325","title":"Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2105.03148","title":"A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: From Classical Methods to Deep Learning Approaches","created":"2021-05-07","cited_by_count":12,"area":null},{"id":"2111.11057","title":"Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images","created":"2021-11-22","cited_by_count":12,"area":null},{"id":"2207.04044","title":"kMaX-DeepLab: k-means Mask Transformer","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2303.04240","title":"Gradient-Guided Knowledge Distillation for Object Detectors","created":"2023-03-07","cited_by_count":12,"area":"distill"},{"id":"2406.05755","title":"A DeNoising FPN With Transformer R-CNN for Tiny Object Detection","created":"2024-06-09","cited_by_count":12,"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":"2308.03193","title":"Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities","created":"2023-08-06","cited_by_count":11,"area":null},{"id":"2309.00655","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion","created":"2023-09-01","cited_by_count":11,"area":null},{"id":"2103.14027","title":"USB: Universal-Scale Object Detection Benchmark","created":"2021-03-25","cited_by_count":10,"area":null},{"id":"2106.03188","title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","created":"2021-06-06","cited_by_count":10,"area":null},{"id":"2206.06637","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2206.13728","title":"Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection","created":"2022-06-28","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":"2308.09105","title":"Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation","created":"2023-08-17","cited_by_count":10,"area":null},{"id":"2506.19472","title":"USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation","created":"2025-06-24","cited_by_count":10,"area":null},{"id":"2201.10781","title":"ASFD: Automatic and Scalable Face Detector","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2211.16290","title":"LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2302.06245","title":"Calibrating a Deep Neural Network with Its Predecessors","created":"2023-02-13","cited_by_count":9,"area":null},{"id":"2405.11276","title":"Visible and Clear: Finding Tiny Objects in Difference Map","created":"2024-05-18","cited_by_count":9,"area":null},{"id":"2104.04899","title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","created":"2021-04-11","cited_by_count":8,"area":null},{"id":"2201.08625","title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2022-01-21","cited_by_count":8,"area":null},{"id":"2204.07482","title":"Towards PAC Multi-Object Detection and Tracking","created":"2022-04-15","cited_by_count":8,"area":null},{"id":"2302.10473","title":"Oriented object detection in optical remote sensing images using deep learning: a survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2307.09143","title":"MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results","created":"2023-07-18","cited_by_count":8,"area":null},{"id":"2410.05577","title":"Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future","created":"2024-10-08","cited_by_count":8,"area":null},{"id":"2305.08069","title":"Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection","created":"2023-05-14","cited_by_count":7,"area":null},{"id":"2408.02285","title":"Joint-Motion Mutual Learning for Pose Estimation in Videos","created":"2024-08-05","cited_by_count":7,"area":null},{"id":"2101.09752","title":"AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systems","created":"2021-01-24","cited_by_count":6,"area":null},{"id":"2112.11366","title":"Contrastive Object Detection Using Knowledge Graph Embeddings","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2209.04861","title":"Inverse Image Frequency for Long-tailed Image Recognition","created":"2022-09-11","cited_by_count":6,"area":null},{"id":"2212.07671","title":"Multi-task Fusion for Efficient Panoptic-Part Segmentation","created":"2022-12-15","cited_by_count":6,"area":null},{"id":"2306.00440","title":"Edge-guided Representation Learning for Underwater Object Detection","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2307.14786","title":"Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning","created":"2023-07-27","cited_by_count":6,"area":null},{"id":"2310.02237","title":"Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2311.11587","title":"LDConv: Linear deformable convolution for improving convolutional neural networks","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2411.00552","title":"Tracking one-in-a-million: Large-scale benchmark for microbial single-cell tracking with experiment-aware robustness metrics","created":"2024-11-01","cited_by_count":6,"area":null},{"id":"2505.05741","title":"Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection","created":"2025-05-09","cited_by_count":6,"area":null},{"id":"2104.09059","title":"A Competitive Method to VIPriors Object Detection Challenge","created":"2021-04-19","cited_by_count":5,"area":null}],"next_cursor":"100"}