{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object-detection/papers/62","list_of":"/task/object-detection","task":"Object Detection","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":62,"pages_in_order":110,"rows_per_page":100,"rows":[6101,6200],"of":10957,"counts":{"archive_papers_tagged":10957,"with_a_code_link":4657,"where_syntology_ran_a_sample":1183,"not_listed_spam_title":0,"listed":10957,"listed_where_code_ran":1183,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1038,"every_run_a_failure_of_syntologys_instrument":145,"listed_with_a_run_with_no_instrument_failure":1038,"listed_every_run_a_failure_of_syntologys_instrument":145,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object-detection","prev":"/task/object-detection/papers/61","next":"/task/object-detection/papers/63","papers":[{"url":null,"slug":"real-time-traffic-object-detection-for","title":"Real-time Traffic Object Detection for Autonomous Driving","date":"2024-01-31","arxiv_id":"2402.00128","repositories_listed":0,"syntology":null},{"url":null,"slug":"source-free-domain-adaptive-object-detection","title":"Source-free Domain Adaptive Object Detection in Remote Sensing Images","date":"2024-01-31","arxiv_id":"2401.17916","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterization-of-magnetic-labyrinthine","title":"Characterization of Magnetic Labyrinthine Structures Through Junctions and Terminals Detection Using Template Matching and CNN","date":"2024-01-30","arxiv_id":"2401.16688","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-why-when-and-how-to-use-active-learning","title":"The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration","date":"2024-01-30","arxiv_id":"2401.16634","repositories_listed":0,"syntology":null},{"url":null,"slug":"verification-for-object-detection-ibp-iou","title":"Verification for Object Detection -- IBP IoU","date":"2024-01-30","arxiv_id":"2403.08788","repositories_listed":0,"syntology":null},{"url":null,"slug":"computer-vision-for-primate-behavior-analysis","title":"Computer Vision for Primate Behavior Analysis in the Wild","date":"2024-01-29","arxiv_id":"2401.16424","repositories_listed":0,"syntology":null},{"url":null,"slug":"lcvo-an-efficient-pretraining-free-framework","title":"LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering","date":"2024-01-29","arxiv_id":"2401.15842","repositories_listed":0,"syntology":null},{"url":null,"slug":"rectify-the-regression-bias-in-long-tailed","title":"Rectify the Regression Bias in Long-Tailed Object Detection","date":"2024-01-29","arxiv_id":"2401.15885","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-object-detection-and-robotic","title":"Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach","date":"2024-01-28","arxiv_id":"2401.15785","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-foggy-object-detecting-model","title":"New Foggy Object Detecting Model","date":"2024-01-27","arxiv_id":"2401.15455","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-look-bottom-up-for-monocular-3d","title":"You Only Look Bottom-Up for Monocular 3D Object Detection","date":"2024-01-27","arxiv_id":"2401.15319","repositories_listed":0,"syntology":null},{"url":"/paper/from-blurry-to-brilliant-detection-yolov5","slug":"from-blurry-to-brilliant-detection-yolov5","title":"From Blurry to Brilliant Detection: YOLOv5-Based Aerial Object Detection with Super Resolution","date":"2024-01-26","arxiv_id":"2401.14661","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graph-driven-uav-cognitive-semantic","title":"Knowledge Graph Driven UAV Cognitive Semantic Communication Systems for Efficient Object Detection","date":"2024-01-25","arxiv_id":"2401.13995","repositories_listed":0,"syntology":null},{"url":null,"slug":"urbangenai-reconstructing-urban-landscapes","title":"UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Models","date":"2024-01-25","arxiv_id":"2401.14379","repositories_listed":0,"syntology":null},{"url":null,"slug":"amanet-advancing-sar-ship-detection-with","title":"AMANet: Advancing SAR Ship Detection with Adaptive Multi-Hierarchical Attention Network","date":"2024-01-24","arxiv_id":"2401.13214","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-and-relation-distillation-for","title":"Towards Complementary Knowledge Distillation for Efficient Dense Image Prediction","date":"2024-01-24","arxiv_id":"2401.13174","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-improved-polyp-detection","title":"Deep Learning for Improved Polyp Detection from Synthetic Narrow-Band Imaging","date":"2024-01-24","arxiv_id":"2401.13315","repositories_listed":0,"syntology":null},{"url":null,"slug":"plate-a-perception-latency-aware-estimator","title":"PLATE: A perception-latency aware estimator,","date":"2024-01-24","arxiv_id":"2401.13596","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-object-detection-performance-for","title":"Enhancing Object Detection Performance for Small Objects through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios","date":"2024-01-23","arxiv_id":"2401.12729","repositories_listed":0,"syntology":null},{"url":null,"slug":"pragmatic-communication-in-multi-agent","title":"Pragmatic Communication in Multi-Agent Collaborative Perception","date":"2024-01-23","arxiv_id":"2401.12694","repositories_listed":0,"syntology":null},{"url":"/paper/small-language-model-meets-with-reinforced","slug":"small-language-model-meets-with-reinforced","title":"Small Language Model Meets with Reinforced Vision Vocabulary","date":"2024-01-23","arxiv_id":"2401.12503","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-saliency-enhanced-feature-fusion-based","title":"A Saliency Enhanced Feature Fusion based multiscale RGB-D Salient Object Detection Network","date":"2024-01-22","arxiv_id":"2401.11914","repositories_listed":0,"syntology":null},{"url":null,"slug":"concealed-object-segmentation-with","title":"Concealed Object Segmentation with Hierarchical Coherence Modeling","date":"2024-01-22","arxiv_id":"2401.11767","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-receptive-field-strategy-and-important","title":"Large receptive field strategy and important feature extraction strategy in 3D object detection","date":"2024-01-22","arxiv_id":"2401.11913","repositories_listed":0,"syntology":null},{"url":null,"slug":"mssvt-mixed-scale-sparse-voxel-transformer","title":"MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detection","date":"2024-01-22","arxiv_id":"2401.11718","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-plasticity-decoupled-fine-tuning","title":"Stability Plasticity Decoupled Fine-tuning For Few-shot end-to-end Object Detection","date":"2024-01-20","arxiv_id":"2401.11140","repositories_listed":0,"syntology":null},{"url":null,"slug":"badodd-bangladeshi-autonomous-driving-object","title":"BadODD: Bangladeshi Autonomous Driving Object Detection Dataset","date":"2024-01-19","arxiv_id":"2401.10659","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-thermal-events-by-semi","title":"Detection of Thermal Events by Semi-Supervised Learning for Tokamak First Wall Safety","date":"2024-01-19","arxiv_id":"2401.10958","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-the-impact-of-scene-level-objects","title":"Measuring the Impact of Scene Level Objects on Object Detection: Towards Quantitative Explanations of Detection Decisions","date":"2024-01-19","arxiv_id":"2401.10790","repositories_listed":0,"syntology":null},{"url":null,"slug":"tdc-less-direct-time-of-flight-imaging-using","title":"TDC-less Direct Time-of-Flight Imaging Using Spiking Neural Networks","date":"2024-01-19","arxiv_id":"2401.10793","repositories_listed":0,"syntology":null},{"url":null,"slug":"agricultural-object-detection-with-you-look","title":"Agricultural Object Detection with You Look Only Once (YOLO) Algorithm: A Bibliometric and Systematic Literature Review","date":"2024-01-18","arxiv_id":"2401.10379","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-over-rgb-automatic-evaluation-of-open","title":"Depth Over RGB: Automatic Evaluation of Open Surgery Skills Using Depth Camera","date":"2024-01-18","arxiv_id":"2401.10037","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-an-ai-based-integrated-system-for","title":"Developing an AI-based Integrated System for Bee Health Evaluation","date":"2024-01-18","arxiv_id":"2401.09988","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-fine-grained-understanding-in-image","title":"Improving fine-grained understanding in image-text pre-training","date":"2024-01-18","arxiv_id":"2401.09865","repositories_listed":0,"syntology":null},{"url":null,"slug":"m3bunet-mobile-mean-max-unet-for-pancreas","title":"M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scans","date":"2024-01-18","arxiv_id":"2401.10419","repositories_listed":0,"syntology":null},{"url":null,"slug":"design-and-development-of-opto-neural","title":"Design and development of opto-neural processors for simulation of neural networks trained in image detection for potential implementation in hybrid robotics","date":"2024-01-17","arxiv_id":"2401.10289","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-lidar-based-object-detection-in","title":"Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time","date":"2024-01-17","arxiv_id":"2401.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-optimized-image-compression-with-1","title":"End-to-End Optimized Image Compression with the Frequency-Oriented Transform","date":"2024-01-16","arxiv_id":"2401.08194","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-object-detection-by-detr-via","title":"Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion","date":"2024-01-16","arxiv_id":"2401.08017","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-consensus-mining-with-a","title":"Discriminative Consensus Mining with A Thousand Groups for More Accurate Co-Salient Object Detection","date":"2024-01-15","arxiv_id":"2403.12057","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-based-object-tracking","title":"Machine Learning Based Object Tracking","date":"2024-01-15","arxiv_id":"2401.07929","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-object-detection-and-high-resolution","title":"3D Object Detection and High-Resolution Traffic Parameters Extraction Using Low-Resolution LiDAR Data","date":"2024-01-13","arxiv_id":"2401.06946","repositories_listed":0,"syntology":null},{"url":null,"slug":"da-bev-unsupervised-domain-adaptation-for","title":"DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception","date":"2024-01-13","arxiv_id":"2401.08687","repositories_listed":0,"syntology":null},{"url":null,"slug":"univision-a-unified-framework-for-vision","title":"UniVision: A Unified Framework for Vision-Centric 3D Perception","date":"2024-01-13","arxiv_id":"2401.06994","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-optical-flow-estimation-using-sparse","title":"Dense Optical Flow Estimation Using Sparse Regularizers from Reduced Measurements","date":"2024-01-12","arxiv_id":"2401.06396","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedded-planogram-compliance-control-system","title":"Embedded Planogram Compliance Control System","date":"2024-01-12","arxiv_id":"2401.06690","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-aware-3d-object-detection-in","title":"Robustness-Aware 3D Object Detection in Autonomous Driving: A Review and Outlook","date":"2024-01-12","arxiv_id":"2401.06542","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-centric-diffusion-for-efficient-video","title":"Object-Centric Diffusion for Efficient Video Editing","date":"2024-01-11","arxiv_id":"2401.05735","repositories_listed":0,"syntology":null},{"url":"/paper/yolo-former-yolo-shakes-hand-with-vit","slug":"yolo-former-yolo-shakes-hand-with-vit","title":"YOLO-Former: YOLO Shakes Hand With ViT","date":"2024-01-11","arxiv_id":"2401.06244","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimising-graph-representation-for-hardware","title":"Optimising Graph Representation for Hardware Implementation of Graph Convolutional Networks for Event-based Vision","date":"2024-01-10","arxiv_id":"2401.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrity-assessment-of-maritime-object","title":"Integrity Assessment of Maritime Object Detection Impacted by Partial Camera Obstruction","date":"2024-01-08","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"soap-cross-sensor-domain-adaptation-for-3d","title":"SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling","date":"2024-01-08","arxiv_id":"2401.04230","repositories_listed":0,"syntology":null},{"url":null,"slug":"ufo-unidentified-foreground-object-detection","title":"UFO: Unidentified Foreground Object Detection in 3D Point Cloud","date":"2024-01-08","arxiv_id":"2401.03846","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-objective-newton-optimization","title":"A Multi-objective Newton Optimization Algorithm for Hyper-Parameter Search","date":"2024-01-07","arxiv_id":"2401.03580","repositories_listed":0,"syntology":null},{"url":null,"slug":"setformer-is-what-you-need-for-vision-and","title":"SeTformer is What You Need for Vision and Language","date":"2024-01-07","arxiv_id":"2401.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-human-detection-by-unmanned-aerial","title":"Real Time Human Detection by Unmanned Aerial Vehicles","date":"2024-01-06","arxiv_id":"2401.03275","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-data-curation-via-object-detection","title":"Multimodal Data Curation via Object Detection and Filter Ensembles","date":"2024-01-05","arxiv_id":"2401.12225","repositories_listed":0,"syntology":null},{"url":null,"slug":"voxelnextfusion-a-simple-unified-and","title":"VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection","date":"2024-01-05","arxiv_id":"2401.02702","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypersense-accelerating-hyper-dimensional","title":"HyperSense: Hyperdimensional Intelligent Sensing for Energy-Efficient Sparse Data Processing","date":"2024-01-04","arxiv_id":"2401.10267","repositories_listed":0,"syntology":null},{"url":null,"slug":"shapeaug-occlusion-augmentation-for-event","title":"ShapeAug: Occlusion Augmentation for Event Camera Data","date":"2024-01-04","arxiv_id":"2401.02274","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffyolo-object-detection-for-anti-noise-via","title":"DiffYOLO: Object Detection for Anti-Noise via YOLO and Diffusion Models","date":"2024-01-03","arxiv_id":"2401.01659","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-temporal-knowledge-with-masked","title":"Distilling Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection","date":"2024-01-03","arxiv_id":"2401.01918","repositories_listed":0,"syntology":null},{"url":null,"slug":"fmgs-foundation-model-embedded-3d-gaussian","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","date":"2024-01-03","arxiv_id":"2401.01970","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-computational-model-for","title":"Deep Learning-Based Computational Model for Disease Identification in Cocoa Pods (Theobroma cacao L.)","date":"2024-01-02","arxiv_id":"2401.01247","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-discriminative-metric-learning-for-1","title":"Depth-discriminative Metric Learning for Monocular 3D Object Detection","date":"2024-01-02","arxiv_id":"2401.01075","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-pooling-and-convolutional-network-for","title":"Hybrid Pooling and Convolutional Network for Improving Accuracy and Training Convergence Speed in Object Detection","date":"2024-01-02","arxiv_id":"2401.01134","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-object-detection-in-occluded","title":"Real-Time Object Detection in Occluded Environment with Background Cluttering Effects Using Deep Learning","date":"2024-01-02","arxiv_id":"2401.00986","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-teacher-asymmetric-network-for-3d-semi","title":"A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-domain-adaptation-with-false-negative","title":"Active Domain Adaptation with False Negative Prediction for Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bilateral-adaptation-for-human-object","title":"Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"credible-teacher-for-semi-supervised-object","title":"Credible Teacher for Semi-Supervised Object Detection in Open Scene","date":"2024-01-01","arxiv_id":"2401.00695","repositories_listed":0,"syntology":null},{"url":null,"slug":"dr2net-dynamic-reversible-dual-residual","title":"Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"endow-sam-with-keen-eyes-temporal-spatial","title":"Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"error-detection-in-egocentric-procedural-task","title":"Error Detection in Egocentric Procedural Task Videos","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-region-word-alignment-in-built-in","title":"Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-object-detection-with-foundation","title":"Few-Shot Object Detection with Foundation Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monodiff-monocular-3d-object-detection-and","title":"MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"msu-4s-the-michigan-state-university-four","title":"MSU-4S - The Michigan State University Four Seasons Dataset","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-collaborative-perception-via","title":"Multi-agent Collaborative Perception via Motion-aware Robust Communication Network","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-exposure-fusion-for-high-dynamic-range","title":"Neural Exposure Fusion for High-Dynamic Range Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-scaling-up-a-multilingual-vision-and","title":"On Scaling Up a Multilingual Vision and Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reg-ptq-regression-specialized-post-training","title":"Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-matching-for-weakly-semi","title":"Relational Matching for Weakly Semi-Supervised Oriented Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-adaptive-and-region-aware-multi-modal","title":"Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"snida-unlocking-few-shot-object-detection","title":"SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-io-2-scaling-autoregressive-1","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unleashing-channel-potential-space-frequency","title":"Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/weakly-misalignment-free-adaptive-feature","slug":"weakly-misalignment-free-adaptive-feature","title":"Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-text-to-pixels-a-context-aware-semantic","title":"From Text to Pixels: A Context-Aware Semantic Synergy Solution for Infrared and Visible Image Fusion","date":"2023-12-31","arxiv_id":"2401.00421","repositories_listed":0,"syntology":null},{"url":null,"slug":"horizontal-federated-computer-vision","title":"Horizontal Federated Computer Vision","date":"2023-12-31","arxiv_id":"2401.00390","repositories_listed":0,"syntology":null},{"url":null,"slug":"rainsd-rain-style-diversification-module-for","title":"RainSD: Rain Style Diversification Module for Image Synthesis Enhancement using Feature-Level Style Distribution","date":"2023-12-31","arxiv_id":"2401.00460","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssl-ota-unveiling-backdoor-threats-in-self","title":"SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection","date":"2023-12-30","arxiv_id":"2401.00137","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvpatch-more-vivid-patch-for-adversarial","title":"MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World","date":"2023-12-29","arxiv_id":"2312.17431","repositories_listed":0,"syntology":null},{"url":null,"slug":"delr-active-learning-for-detection-with","title":"DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query","date":"2023-12-28","arxiv_id":"2312.16931","repositories_listed":0,"syntology":null},{"url":null,"slug":"doepatch-dynamically-optimized-ensemble-model","title":"DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation","date":"2023-12-28","arxiv_id":"2312.16907","repositories_listed":0,"syntology":null},{"url":null,"slug":"evplug-learn-a-plug-and-play-module-for-event","title":"EvPlug: Learn a Plug-and-Play Module for Event and Image Fusion","date":"2023-12-28","arxiv_id":"2312.16933","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-quantum-convolutional-neural-networks","title":"Fast Quantum Convolutional Neural Networks for Low-Complexity Object Detection in Autonomous Driving Applications","date":"2023-12-28","arxiv_id":"2401.01370","repositories_listed":0,"syntology":null},{"url":null,"slug":"sar-net-multi-scale-direction-aware-sar","title":"Multi-scale direction-aware SAR object detection network via global information fusion","date":"2023-12-28","arxiv_id":"2312.16943","repositories_listed":0,"syntology":null},{"url":null,"slug":"grsdet-learning-to-generate-local-reverse","title":"GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection","date":"2023-12-27","arxiv_id":"2312.16571","repositories_listed":0,"syntology":null},{"url":null,"slug":"virtualpainting-addressing-sparsity-with","title":"VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection","date":"2023-12-26","arxiv_id":"2312.16141","repositories_listed":0,"syntology":null}],"record_sha256":"96b204272da48def33d3b6e836602f5846118efb9c88779d523c009cb7558598","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}