{"total":189,"rows":[{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204,"area":null},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143,"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":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2106.12735","title":"Multi-Modal 3D Object Detection in Autonomous Driving: a Survey","created":"2021-06-24","cited_by_count":63,"area":null},{"id":"2203.09831","title":"DTA: Physical Camouflage Attacks using Differentiable Transformation Network","created":"2022-03-18","cited_by_count":51,"area":null},{"id":"2112.02838","title":"Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook","created":"2021-12-06","cited_by_count":46,"area":null},{"id":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","cited_by_count":42,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2203.04946","title":"Do better ImageNet classifiers assess perceptual similarity better?","created":"2022-03-09","cited_by_count":34,"area":null},{"id":"2308.07009","title":"ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion","created":"2023-08-14","cited_by_count":31,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2207.07812","title":"A Survey on Collaborative DNN Inference for Edge Intelligence","created":"2022-07-16","cited_by_count":24,"area":null},{"id":"2207.09295","title":"The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting","created":"2022-07-19","cited_by_count":24,"area":null},{"id":"2311.17286","title":"LEOD: Label-Efficient Object Detection for Event Cameras","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2203.13903","title":"Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection","created":"2022-03-25","cited_by_count":23,"area":null},{"id":"2406.07661","title":"ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones","created":"2024-06-11","cited_by_count":22,"area":null},{"id":"2204.00484","title":"Proper Reuse of Image Classification Features Improves Object Detection","created":"2022-04-01","cited_by_count":20,"area":null},{"id":"2204.03934","title":"Does Robustness on ImageNet Transfer to Downstream Tasks?","created":"2022-04-08","cited_by_count":20,"area":null},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2103.17242","title":"Dogfight: Detecting Drones from Drones Videos","created":"2021-03-31","cited_by_count":18,"area":null},{"id":"2312.02919","title":"Fine-grained Controllable Video Generation via Object Appearance and Context","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17,"area":null},{"id":"2310.18329","title":"Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices","created":"2023-10-19","cited_by_count":17,"area":null},{"id":"2402.15490","title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2101.09553","title":"Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagery","created":"2021-01-23","cited_by_count":15,"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":"2309.11039","title":"Federated Learning in Intelligent Transportation Systems: Recent Applications and Open Problems","created":"2023-09-20","cited_by_count":15,"area":null},{"id":"2104.13872","title":"Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning","created":"2021-04-28","cited_by_count":14,"area":null},{"id":"2404.02112","title":"ImageNot: A contrast with ImageNet preserves model rankings","created":"2024-04-02","cited_by_count":14,"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":"2102.04980","title":"Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval","created":"2021-02-09","cited_by_count":12,"area":null},{"id":"2207.10959","title":"QueryProp: Object Query Propagation for High-Performance Video Object Detection","created":"2022-07-22","cited_by_count":12,"area":null},{"id":"2208.10895","title":"A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey","created":"2022-08-23","cited_by_count":12,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2106.00880","title":"Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery","created":"2021-06-02","cited_by_count":11,"area":null},{"id":"2103.00119","title":"ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation","created":"2021-02-27","cited_by_count":10,"area":null},{"id":"2103.06403","title":"A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2103.14027","title":"USB: Universal-Scale Object Detection Benchmark","created":"2021-03-25","cited_by_count":10,"area":null},{"id":"2106.15315","title":"Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics","created":"2021-06-21","cited_by_count":10,"area":null},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2208.07479","title":"Context-Aware Streaming Perception in Dynamic Environments","created":"2022-08-16","cited_by_count":8,"area":null},{"id":"2101.05357","title":"Towards Creating a Deployable Grasp Type Probability Estimator for a Prosthetic Hand","created":"2021-01-13","cited_by_count":7,"area":null},{"id":"2104.08859","title":"Filtering Empty Camera Trap Images in Embedded Systems","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2203.03195","title":"Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2304.02101","title":"MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2308.09960","title":"Towards Self-Adaptive Machine Learning-Enabled Systems Through QoS-Aware Model Switching","created":"2023-08-19","cited_by_count":7,"area":null},{"id":"2104.03888","title":"Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2109.00810","title":"Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2212.10596","title":"Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2301.04608","title":"Padding Module: Learning the Padding in Deep Neural Networks","created":"2023-01-11","cited_by_count":6,"area":null},{"id":"2302.09835","title":"Simple U-net Based Synthetic Polyp Image Generation: Polyp to Negative and Negative to Polyp","created":"2023-02-20","cited_by_count":6,"area":null},{"id":"2403.19866","title":"Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization","created":"2024-03-28","cited_by_count":6,"area":null},{"id":"2104.00432","title":"Anchor Pruning for Object Detection","created":"2021-04-01","cited_by_count":5,"area":null},{"id":"2106.05665","title":"Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2107.11845","title":"On-Device Content Moderation","created":"2021-07-25","cited_by_count":5,"area":null},{"id":"2202.07315","title":"Using Social Media Images for Building Function Classification","created":"2022-02-15","cited_by_count":5,"area":null},{"id":"2212.09408","title":"Universal Object Detection with Large Vision Model","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2301.08664","title":"AccDecoder: Accelerated Decoding for Neural-enhanced Video Analytics","created":"2023-01-20","cited_by_count":5,"area":null},{"id":"2103.15456","title":"Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions","created":"2021-03-29","cited_by_count":4,"area":null},{"id":"2105.07986","title":"Learning to Automatically Catch Potholes in Worldwide Road Scene Images","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2106.11208","title":"Temporal Early Exits for Efficient Video Object Detection","created":"2021-06-21","cited_by_count":4,"area":null},{"id":"2110.10523","title":"Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2112.01320","title":"Multi-task fusion for improving mammography screening data classification","created":"2021-12-01","cited_by_count":4,"area":null},{"id":"2112.14706","title":"Intersection focused Situation Coverage-based Verification and Validation Framework for Autonomous Vehicles Implemented in CARLA","created":"2021-12-24","cited_by_count":4,"area":null},{"id":"2211.07122","title":"ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2301.06187","title":"CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2303.06458","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","created":"2023-03-11","cited_by_count":4,"area":null},{"id":"2305.02398","title":"Learning-based Relational Object Matching Across Views","created":"2023-05-03","cited_by_count":4,"area":null},{"id":"2502.07826","title":"Deep Learning in Automated Power Line Inspection: A Review","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2101.01260","title":"SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection","created":"2021-01-04","cited_by_count":3,"area":null},{"id":"2103.11276","title":"High precision control and deep learning-based corn stand counting algorithms for agricultural robot","created":"2021-03-21","cited_by_count":3,"area":null},{"id":"2107.07927","title":"A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2108.00977","title":"Multilevel Knowledge Transfer for Cross-Domain Object Detection","created":"2021-08-02","cited_by_count":3,"area":null},{"id":"2110.11867","title":"CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking Detection","created":"2021-10-22","cited_by_count":3,"area":null},{"id":"2112.13194","title":"Network-Aware 5G Edge Computing for Object Detection: Augmenting Wearables to \"See\" More, Farther and Faster","created":"2021-12-25","cited_by_count":3,"area":null},{"id":"2112.13341","title":"AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform","created":"2021-12-26","cited_by_count":3,"area":null},{"id":"2202.00866","title":"Decoupled IoU Regression for Object Detection","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2204.06846","title":"OmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2205.01142","title":"Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detection","created":"2022-05-02","cited_by_count":3,"area":null},{"id":"2205.02421","title":"Towards Real-time Traffic Sign and Traffic Light Detection on Embedded Systems","created":"2022-05-05","cited_by_count":3,"area":null},{"id":"2303.14311","title":"Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection","created":"2023-03-25","cited_by_count":3,"area":null},{"id":"2310.18920","title":"Improving Multi-Person Pose Tracking with A Confidence Network","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2101.04943","title":"Learning to be EXACT, Cell Detection for Asthma on Partially Annotated Whole Slide Images","created":"2021-01-13","cited_by_count":2,"area":null},{"id":"2101.05661","title":"A Pipeline for Vision-Based On-Orbit Proximity Operations Using Deep Learning and Synthetic Imagery","created":"2021-01-14","cited_by_count":2,"area":null},{"id":"2104.06826","title":"Towards Automatic Model Specialization for Edge Video Analytics","created":"2021-04-14","cited_by_count":2,"area":null},{"id":"2104.11761","title":"Towards Trustworthy Deception Detection: Benchmarking Model Robustness across Domains, Modalities, and Languages","created":"2021-04-23","cited_by_count":2,"area":null},{"id":"2106.13933","title":"Inverting and Understanding Object Detectors","created":"2021-06-26","cited_by_count":2,"area":null},{"id":"2106.14597","title":"Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2109.04422","title":"TxT: Crossmodal End-to-End Learning with Transformers","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2110.11829","title":"CNN-based Omnidirectional Object Detection for HermesBot Autonomous Delivery Robot with Preliminary Frame Classification","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2201.11105","title":"Do You See What I See? Capabilities and Limits of Automated Multimedia Content Analysis","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2203.09181","title":"An Interactive Explanatory AI System for Industrial Quality Control","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2204.02227","title":"SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution","created":"2022-04-05","cited_by_count":2,"area":null},{"id":"2209.08163","title":"Belief Revision based Caption Re-ranker with Visual Semantic Information","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2210.16083","title":"ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy","created":"2022-10-28","cited_by_count":2,"area":null},{"id":"2301.08784","title":"Visual Semantic Relatedness Dataset for Image Captioning","created":"2023-01-20","cited_by_count":2,"area":null}],"next_cursor":"100"}