{"total":244,"rows":[{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2311.11722","title":"Sparse4D v3: Advancing End-to-End 3D Detection and Tracking","created":"2023-11-20","cited_by_count":70,"area":null},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68,"area":null},{"id":"2310.16288","title":"MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network","created":"2023-10-25","cited_by_count":64,"area":null},{"id":"2304.00967","title":"Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction","created":"2023-04-03","cited_by_count":49,"area":null},{"id":"2406.04875","title":"3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views","created":"2024-06-07","cited_by_count":39,"area":null},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35,"area":null},{"id":"2409.08475","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","created":"2024-09-13","cited_by_count":32,"area":null},{"id":"2403.16131","title":"Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement","created":"2024-03-24","cited_by_count":31,"area":null},{"id":"2407.11699","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","created":"2024-07-16","cited_by_count":28,"area":null},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24,"area":null},{"id":"2412.04077","title":"SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning","created":"2024-12-05","cited_by_count":24,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2410.01615","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2305.12724","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","created":"2023-05-22","cited_by_count":20,"area":null},{"id":"2311.13596","title":"T-Rex: Counting by Visual Prompting","created":"2023-11-22","cited_by_count":20,"area":null},{"id":"2403.06892","title":"Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head","created":"2024-03-11","cited_by_count":20,"area":null},{"id":"2404.15770","title":"ChEX: Interactive Localization and Region Description in Chest X-rays","created":"2024-04-24","cited_by_count":19,"area":null},{"id":"2412.09283","title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption","created":"2024-12-12","cited_by_count":17,"area":null},{"id":"2504.04519","title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","created":"2025-04-06","cited_by_count":17,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2312.07266","title":"ProxyDet: Synthesizing Proxy Novel Classes via Classwise Mixup for Open-Vocabulary Object Detection","created":"2023-12-12","cited_by_count":15,"area":null},{"id":"2310.08027","title":"Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection","created":"2023-10-12","cited_by_count":13,"area":null},{"id":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13,"area":null},{"id":"2410.11301","title":"Open World Object Detection: A Survey","created":"2024-10-15","cited_by_count":13,"area":null},{"id":"2410.19635","title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","created":"2024-10-25","cited_by_count":13,"area":null},{"id":"2506.16991","title":"ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Clouds","created":"2025-06-20","cited_by_count":13,"area":null},{"id":"2504.13099","title":"RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity","created":"2025-04-17","cited_by_count":12,"area":null},{"id":"2405.20459","title":"On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2501.16751","title":"HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging","created":"2025-01-28","cited_by_count":11,"area":null},{"id":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2402.16013","title":"Semi-supervised Open-World Object Detection","created":"2024-02-25","cited_by_count":10,"area":null},{"id":"2405.15995","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","created":"2024-05-25","cited_by_count":10,"area":null},{"id":"2406.15778","title":"ObjectNLQ @ Ego4D Episodic Memory Challenge 2024","created":"2024-06-22","cited_by_count":10,"area":null},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10,"area":null},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10,"area":null},{"id":"2305.07598","title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","created":"2023-05-12","cited_by_count":9,"area":null},{"id":"2403.04309","title":"AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection","created":"2024-03-07","cited_by_count":9,"area":null},{"id":"2403.10353","title":"SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras","created":"2024-03-15","cited_by_count":9,"area":null},{"id":"2407.10083","title":"Plain-Det: A Plain Multi-Dataset Object Detector","created":"2024-07-14","cited_by_count":9,"area":null},{"id":"2501.05783","title":"UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2212.04067","title":"Consistency-Aware Anchor Pyramid Network for Crowd Localization","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2304.13027","title":"A Strong and Reproducible Object Detector with Only Public Datasets","created":"2023-04-25","cited_by_count":8,"area":null},{"id":"2308.13900","title":"Semi-Supervised Semantic Segmentation via Marginal Contextual Information","created":"2023-08-26","cited_by_count":8,"area":null},{"id":"2406.04330","title":"Parameter-Inverted Image Pyramid Networks","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2501.07783","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2502.05147","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","created":"2025-02-07","cited_by_count":8,"area":null},{"id":"2505.16314","title":"NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2309.07315","title":"Traveling Words: A Geometric Interpretation of Transformers","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2311.14762","title":"The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024","created":"2023-11-23","cited_by_count":7,"area":null},{"id":"2503.06261","title":"Segment Anything, Even Occluded","created":"2025-03-08","cited_by_count":7,"area":null},{"id":"2508.10528","title":"Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Dataset","created":"2025-08-14","cited_by_count":7,"area":null},{"id":"2308.09242","title":"ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation","created":"2023-08-18","cited_by_count":6,"area":null},{"id":"2405.10148","title":"SpecDETR: A transformer-based hyperspectral point object detection network","created":"2024-05-16","cited_by_count":6,"area":null},{"id":"2409.09412","title":"Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations","created":"2024-09-14","cited_by_count":6,"area":null},{"id":"2510.03701","title":"Referring Expression Comprehension for Small Objects","created":"2025-10-04","cited_by_count":6,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2308.01300","title":"Revisiting DETR Pre-training for Object Detection","created":"2023-08-02","cited_by_count":5,"area":null},{"id":"2405.00187","title":"Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2407.16327","title":"Understanding Impacts of Electromagnetic Signal Injection Attacks on Object Detection","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2409.09293","title":"Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown","created":"2024-09-14","cited_by_count":5,"area":null},{"id":"2504.02534","title":"Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2506.05342","title":"Refer to Any Segmentation Mask Group With Vision-Language Prompts","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2507.00170","title":"SelvaBox: A high-resolution dataset for tropical tree crown detection","created":"2025-06-30","cited_by_count":5,"area":null},{"id":"2509.23316","title":"C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2308.04025","title":"MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognition","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2405.04971","title":"End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2406.06947","title":"CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2407.01302","title":"Robot Instance Segmentation with Few Annotations for Grasping","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2411.18288","title":"Optimizing Multispectral Object Detection: A Bag of Tricks and Comprehensive Benchmarks","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2505.15755","title":"Exploring The Visual Feature Space for Multimodal Neural Decoding","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.17473","title":"InfoDet: A Dataset for Infographic Element Detection","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2505.20639","title":"Open-Det: An Efficient Learning Framework for Open-Ended Detection","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2507.05108","title":"Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2509.04758","title":"Dynamic Group Detection using VLM-augmented Temporal Groupness Graph","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2510.18229","title":"Unbiased Object Detection Beyond Frequency with Visually Prompted Image Synthesis","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2603.06917","title":"PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2306.09165","title":"DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detection","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2403.15209","title":"MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2403.15977","title":"Towards Two-Stream Foveation-based Active Vision Learning","created":"2024-03-24","cited_by_count":3,"area":null},{"id":"2403.19043","title":"Illicit object detection in X-ray images using Vision Transformers","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2404.10078","title":"Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasets","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2404.13657","title":"MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions","created":"2024-04-21","cited_by_count":3,"area":null},{"id":"2407.12346","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2407.14204","title":"Bucketed Ranking-based Losses for Efficient Training of Object Detectors","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2407.19178","title":"Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection","created":"2024-07-27","cited_by_count":3,"area":null},{"id":"2410.23728","title":"GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2501.05239","title":"Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception","created":"2025-01-09","cited_by_count":3,"area":null},{"id":"2501.16665","title":"CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2504.07603","title":"RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2504.12552","title":"Privacy-Preserving Operating Room Workflow Analysis using Digital Twins","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2504.21614","title":"Mcity Data Engine: Iterative Model Improvement Through Open-Vocabulary Data Selection","created":"2025-04-30","cited_by_count":3,"area":null}],"next_cursor":"100"}