{"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/50","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":50,"pages_in_order":110,"rows_per_page":100,"rows":[4901,5000],"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/49","next":"/task/object-detection/papers/51","papers":[{"url":null,"slug":"style-evolving-along-chain-of-thought-for","title":"Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection","date":"2025-03-13","arxiv_id":"2503.09968","repositories_listed":0,"syntology":null},{"url":null,"slug":"tars-traffic-aware-radar-scene-flow","title":"TARS: Traffic-Aware Radar Scene Flow Estimation","date":"2025-03-13","arxiv_id":"2503.10210","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-power-of-one-a-single-example-is-all-it","title":"The Power of One: A Single Example is All it Takes for Segmentation in VLMs","date":"2025-03-13","arxiv_id":"2503.10779","repositories_listed":0,"syntology":null},{"url":null,"slug":"cleverdistiller-simple-and-spatially","title":"CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation","date":"2025-03-12","arxiv_id":"2503.09878","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-climate-action-computer","title":"Deep Learning for Climate Action: Computer Vision Analysis of Visual Narratives on X","date":"2025-03-12","arxiv_id":"2503.09361","repositories_listed":0,"syntology":null},{"url":null,"slug":"dithub-a-modular-framework-for-incremental","title":"DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection","date":"2025-03-12","arxiv_id":"2503.09271","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-domain-homogeneous-fusion-with-cross","title":"Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detection","date":"2025-03-12","arxiv_id":"2503.08992","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-impact-of-synthetic-data-on","title":"Evaluating the Impact of Synthetic Data on Object Detection Tasks in Autonomous Driving","date":"2025-03-12","arxiv_id":"2503.09803","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-synthetic-training-for-visual-quality","title":"Fully-Synthetic Training for Visual Quality Inspection in Automotive Production","date":"2025-03-12","arxiv_id":"2503.09354","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-good-are-deep-learning-methods-for","title":"How good are deep learning methods for automated road safety analysis using video data? An experimental study","date":"2025-03-12","arxiv_id":"2503.09807","repositories_listed":0,"syntology":null},{"url":null,"slug":"polygonizing-roof-segments-from-high","title":"Polygonizing Roof Segments from High-Resolution Aerial Images Using Yolov8-Based Edge Detection","date":"2025-03-12","arxiv_id":"2503.09187","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-regression-for-leitmotif-detection","title":"Boundary Regression for Leitmotif Detection in Music Audio","date":"2025-03-11","arxiv_id":"2503.07977","repositories_listed":0,"syntology":null},{"url":null,"slug":"bring-remote-sensing-object-detect-into","title":"Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method","date":"2025-03-11","arxiv_id":"2503.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-based-ai-methodology-for-material","title":"Physics-based AI methodology for Material Parameter Extraction from Optical Data","date":"2025-03-11","arxiv_id":"2503.08183","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-automotive-radar-with-lidar-and","title":"Simulating Automotive Radar with Lidar and Camera Inputs","date":"2025-03-11","arxiv_id":"2503.08068","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsevoxformer-sparse-voxel-based","title":"SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detection","date":"2025-03-11","arxiv_id":"2503.08092","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-light-perspective-for-3d-object-detection","title":"A Light Perspective for 3D Object Detection","date":"2025-03-10","arxiv_id":"2503.07133","repositories_listed":0,"syntology":null},{"url":null,"slug":"hgo-yolo-advancing-anomaly-behavior-detection","title":"HGO-YOLO: Advancing Anomaly Behavior Detection with Hierarchical Features and Lightweight Optimized Detection","date":"2025-03-10","arxiv_id":"2503.07371","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-cross-modal-alignment-for-open","title":"Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","date":"2025-03-10","arxiv_id":"2503.07593","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-guided-progressive","title":"Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection","date":"2025-03-10","arxiv_id":"2503.06948","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-in-yolo-based","title":"Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection","date":"2025-03-10","arxiv_id":"2503.07330","repositories_listed":0,"syntology":null},{"url":null,"slug":"rs2v-l-vehicle-mounted-lidar-data-generation","title":"RS2AD: End-to-End Autonomous Driving Data Generation from Roadside Sensor Observations","date":"2025-03-10","arxiv_id":"2503.07085","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-communications-with-computer-vision","title":"Semantic Communications with Computer Vision Sensing for Edge Video Transmission","date":"2025-03-10","arxiv_id":"2503.07252","repositories_listed":0,"syntology":null},{"url":null,"slug":"vocaleyes-enhancing-environmental-perception","title":"VocalEyes: Enhancing Environmental Perception for the Visually Impaired through Vision-Language Models and Distance-Aware Object Detection","date":"2025-03-10","arxiv_id":"2503.16488","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-layer-attention-efficiency-through","title":"Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals","date":"2025-03-09","arxiv_id":"2503.06473","repositories_listed":0,"syntology":null},{"url":"/paper/ov-scan-semantically-consistent-alignment-for","slug":"ov-scan-semantically-consistent-alignment-for","title":"OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection","date":"2025-03-09","arxiv_id":"2503.06435","repositories_listed":0,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ov-scan-semantically-consistent-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2503.06435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06435"}},"official":null}},{"url":null,"slug":"acam-kd-adaptive-and-cooperative-attention","title":"ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation","date":"2025-03-08","arxiv_id":"2503.06307","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-and-efficient-two-stage-gun","title":"Accurate and Efficient Two-Stage Gun Detection in Video","date":"2025-03-08","arxiv_id":"2503.06317","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-endogaussian-feature-distilled","title":"Feature-EndoGaussian: Feature Distilled Gaussian Splatting in Surgical Deformable Scene Reconstruction","date":"2025-03-08","arxiv_id":"2503.06161","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-dataset-to-real-world-general-3d-object","title":"From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning","date":"2025-03-08","arxiv_id":"2503.06282","repositories_listed":0,"syntology":null},{"url":null,"slug":"get-in-video-add-anything-you-want-to-the","title":"Get In Video: Add Anything You Want to the Video","date":"2025-03-08","arxiv_id":"2503.06268","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sam-for-camouflaged-object","title":"Improving SAM for Camouflaged Object Detection via Dual Stream Adapters","date":"2025-03-08","arxiv_id":"2503.06042","repositories_listed":0,"syntology":null},{"url":null,"slug":"openrsd-towards-open-prompts-for-object","title":"OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images","date":"2025-03-08","arxiv_id":"2503.06146","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-object-detection-a-survey","title":"2D Object Detection: A Survey","date":"2025-03-07","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-florence2-for-enhanced-object","title":"Fine-Tuning Florence2 for Enhanced Object Detection in Un-constructed Environments: Vision-Language Model Approach","date":"2025-03-06","arxiv_id":"2503.04918","repositories_listed":0,"syntology":null},{"url":null,"slug":"floxels-fast-unsupervised-voxel-based-scene","title":"Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation","date":"2025-03-06","arxiv_id":"2503.04718","repositories_listed":0,"syntology":null},{"url":null,"slug":"shaken-not-stirred-a-novel-dataset-for-visual","title":"Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Tasks","date":"2025-03-06","arxiv_id":"2503.04308","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-yolo-to-remember-a-self-distillation","title":"Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection","date":"2025-03-06","arxiv_id":"2503.04688","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-driven-multi-stage-computer-vision-system","title":"AI-Driven Multi-Stage Computer Vision System for Defect Detection in Laser-Engraved Industrial Nameplates","date":"2025-03-05","arxiv_id":"2503.03395","repositories_listed":0,"syntology":null},{"url":null,"slug":"bevmosnet-multimodal-fusion-for-bev-moving","title":"BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation","date":"2025-03-05","arxiv_id":"2503.03280","repositories_listed":0,"syntology":null},{"url":null,"slug":"miadapt-source-free-few-shot-domain-adaptive","title":"MIAdapt: Source-free Few-shot Domain Adaptive Object Detection for Microscopic Images","date":"2025-03-05","arxiv_id":"2503.03370","repositories_listed":0,"syntology":null},{"url":null,"slug":"periodontal-bone-loss-analysis-via-keypoint","title":"Periodontal Bone Loss Analysis via Keypoint Detection With Heuristic Post-Processing","date":"2025-03-05","arxiv_id":"2503.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-aware-pillarmix-can-mixed-sample-data","title":"Class-Aware PillarMix: Can Mixed Sample Data Augmentation Enhance 3D Object Detection with Radar Point Clouds?","date":"2025-03-04","arxiv_id":"2503.02687","repositories_listed":0,"syntology":null},{"url":null,"slug":"reraw-rgb-to-raw-image-reconstruction-via","title":"ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge","date":"2025-03-04","arxiv_id":"2503.03782","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-detection-of-overlapping-bioacoustic","title":"Robust detection of overlapping bioacoustic sound events","date":"2025-03-04","arxiv_id":"2503.02389","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssnet-saliency-prior-and-state-space-model","title":"SSNet: Saliency Prior and State Space Model-based Network for Salient Object Detection in RGB-D Images","date":"2025-03-04","arxiv_id":"2503.02270","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipgrader-leveraging-vision-language-models","title":"ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection","date":"2025-03-03","arxiv_id":"2503.02897","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-stenosis-detection-with-grounding","title":"Evaluating Stenosis Detection with Grounding DINO, YOLO, and DINO-DETR","date":"2025-03-03","arxiv_id":"2503.01601","repositories_listed":0,"syntology":null},{"url":null,"slug":"illuminant-and-light-direction-estimation","title":"Illuminant and light direction estimation using Wasserstein distance method","date":"2025-03-03","arxiv_id":"2503.05802","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-object-detection-and-phrase","title":"A Comparison of Object Detection and Phrase Grounding Models in Chest X-ray Abnormality Localization using Eye-tracking Data","date":"2025-03-02","arxiv_id":"2503.01037","repositories_listed":0,"syntology":null},{"url":null,"slug":"rfwnet-a-lightweight-remote-sensing-object","title":"RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multi-Scale Receptive Fields and Foreground Focus Mechanism","date":"2025-03-01","arxiv_id":"2503.00545","repositories_listed":0,"syntology":null},{"url":"/paper/unifa-a-unified-feature-hallucination","slug":"unifa-a-unified-feature-hallucination","title":"UniFa: A unified feature hallucination framework for any-shot object detection","date":"2025-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-for-reid-sam-on-skitb-visual","title":"Technical Report for ReID-SAM on SkiTB Visual Tracking Challenge 2025","date":"2025-02-28","arxiv_id":"2503.01907","repositories_listed":0,"syntology":null},{"url":null,"slug":"bevdiffuser-plug-and-play-diffusion-model-for","title":"BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance","date":"2025-02-27","arxiv_id":"2502.19694","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-mask-invariant-mutual-information","title":"Learning Mask Invariant Mutual Information for Masked Image Modeling","date":"2025-02-27","arxiv_id":"2502.19718","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-neighborhood-occupancy-masked","title":"Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds","date":"2025-02-27","arxiv_id":"2502.20316","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-yolo-based-real-time-power-line","title":"Advanced YOLO-based Real-time Power Line Detection for Vegetation Management","date":"2025-02-26","arxiv_id":"2503.00044","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-yolov12-with-llm-generated-synthetic","title":"Improved YOLOv12 with LLM-Generated Synthetic Data for Enhanced Apple Detection and Benchmarking Against YOLOv11 and YOLOv10","date":"2025-02-26","arxiv_id":"2503.00057","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-transformers-on-the-edge-a","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","date":"2025-02-26","arxiv_id":"2503.02891","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-vehicle-detection-using-detr-a","title":"Automatic Vehicle Detection using DETR: A Transformer-Based Approach for Navigating Treacherous Roads","date":"2025-02-25","arxiv_id":"2502.17843","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-local-alignment-for-medical","title":"Progressive Local Alignment for Medical Multimodal Pre-training","date":"2025-02-25","arxiv_id":"2502.18047","repositories_listed":0,"syntology":null},{"url":null,"slug":"experimental-validation-of-uav-search-and","title":"Experimental validation of UAV search and detection system in real wilderness environment","date":"2025-02-24","arxiv_id":"2502.17372","repositories_listed":0,"syntology":null},{"url":null,"slug":"lcv2i-communication-efficient-and-high","title":"LCV2I: Communication-Efficient and High-Performance Collaborative Perception Framework with Low-Resolution LiDAR","date":"2025-02-24","arxiv_id":"2502.17039","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-approaches-to-surgical-video","title":"Deep learning approaches to surgical video segmentation and object detection: A Scoping Review","date":"2025-02-23","arxiv_id":"2502.16459","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometry-aware-3d-salient-object-detection","title":"Geometry-Aware 3D Salient Object Detection Network","date":"2025-02-23","arxiv_id":"2502.16488","repositories_listed":0,"syntology":null},{"url":null,"slug":"mqadet-a-plug-and-play-paradigm-for-enhancing","title":"MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering","date":"2025-02-23","arxiv_id":"2502.16486","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-aware-fusion-method-based-on-image-and","title":"Depth-aware Fusion Method based on Image and 4D Radar Spectrum for 3D Object Detection","date":"2025-02-21","arxiv_id":"2502.15516","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-framework-for-3d-object","title":"Generative AI Framework for 3D Object Generation in Augmented Reality","date":"2025-02-21","arxiv_id":"2502.15869","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-petr-quant-aware-position-embedding","title":"Q-PETR: Quant-aware Position Embedding Transformation for Multi-View 3D Object Detection","date":"2025-02-21","arxiv_id":"2502.15488","repositories_listed":0,"syntology":null},{"url":null,"slug":"lxlv2-enhanced-lidar-excluded-lean-3d-object","title":"LXLv2: Enhanced LiDAR Excluded Lean 3D Object Detection with Fusion of 4D Radar and Camera","date":"2025-02-20","arxiv_id":"2502.14503","repositories_listed":0,"syntology":null},{"url":null,"slug":"odverse33-is-the-new-yolo-version-always","title":"ODVerse33: Is the New YOLO Version Always Better? A Multi Domain benchmark from YOLO v5 to v11","date":"2025-02-20","arxiv_id":"2502.14314","repositories_listed":0,"syntology":null},{"url":"/paper/yolov12-a-breakdown-of-the-key-architectural","slug":"yolov12-a-breakdown-of-the-key-architectural","title":"YOLOv12: A Breakdown of the Key Architectural Features","date":"2025-02-20","arxiv_id":"2502.14740","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overall-real-time-mechanism-for","title":"An Overall Real-Time Mechanism for Classification and Quality Evaluation of Rice","date":"2025-02-19","arxiv_id":"2502.13764","repositories_listed":0,"syntology":null},{"url":"/paper/groundcap-a-visually-grounded-image","slug":"groundcap-a-visually-grounded-image","title":"GroundCap: A Visually Grounded Image Captioning Dataset","date":"2025-02-19","arxiv_id":"2502.13898","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-compositing-is-all-you-need-for-data","title":"Image compositing is all you need for data augmentation","date":"2025-02-19","arxiv_id":"2502.13936","repositories_listed":0,"syntology":null},{"url":null,"slug":"msvcod-a-large-scale-multi-scene-dataset-for","title":"MSVCOD:A Large-Scale Multi-Scene Dataset for Video Camouflage Object Detection","date":"2025-02-19","arxiv_id":"2502.13859","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-distribution-shift-aerial-mds-a-a","title":"Multiple Distribution Shift -- Aerial (MDS-A): A Dataset for Test-Time Error Detection and Model Adaptation","date":"2025-02-18","arxiv_id":"2502.13289","repositories_listed":0,"syntology":null},{"url":null,"slug":"roburcdet-enhancing-robustness-of-radar","title":"RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection","date":"2025-02-18","arxiv_id":"2502.13071","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-semantic-communication-for","title":"Task-Oriented Semantic Communication for Stereo-Vision 3D Object Detection","date":"2025-02-18","arxiv_id":"2502.12735","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-transparent-object-pose-estimation","title":"Enhancing Transparent Object Pose Estimation: A Fusion of GDR-Net and Edge Detection","date":"2025-02-17","arxiv_id":"2502.12027","repositories_listed":0,"syntology":null},{"url":null,"slug":"clockdistill-consistent-location-and-context","title":"CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs","date":"2025-02-15","arxiv_id":"2502.10683","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-segmentation-of-scene-sketches-using","title":"Instance Segmentation of Scene Sketches Using Natural Image Priors","date":"2025-02-13","arxiv_id":"2502.09608","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-the-impact-of-prominent-position","title":"Mitigating the Impact of Prominent Position Shift in Drone-based RGBT Object Detection","date":"2025-02-13","arxiv_id":"2502.09311","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-user","title":"Deep Reinforcement Learning-Based User Scheduling for Collaborative Perception","date":"2025-02-12","arxiv_id":"2502.10456","repositories_listed":0,"syntology":null},{"url":null,"slug":"plantation-monitoring-using-drone-images-a","title":"Plantation Monitoring Using Drone Images: A Dataset and Performance Review","date":"2025-02-12","arxiv_id":"2502.08233","repositories_listed":0,"syntology":null},{"url":null,"slug":"take-what-you-need-flexible-multi-task","title":"Take What You Need: Flexible Multi-Task Semantic Communications with Channel Adaptation","date":"2025-02-12","arxiv_id":"2502.08221","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-mamba-architecture-for-vision","title":"A Survey on Mamba Architecture for Vision Applications","date":"2025-02-11","arxiv_id":"2502.07161","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-object-detection-based-on-de","title":"Dense Object Detection Based on De-homogenized Queries","date":"2025-02-11","arxiv_id":"2502.07194","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-cos-a-fast-one-stage-object-detector","title":"Fast-COS: A Fast One-Stage Object Detector Based on Reparameterized Attention Vision Transformer for Autonomous Driving","date":"2025-02-11","arxiv_id":"2502.07417","repositories_listed":0,"syntology":null},{"url":null,"slug":"foreign-object-detection-in-high-voltage","title":"Foreign-Object Detection in High-Voltage Transmission Line Based on Improved YOLOv8m","date":"2025-02-11","arxiv_id":"2502.07175","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparseformer-detecting-objects-in-hrw-shots","title":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","date":"2025-02-11","arxiv_id":"2502.07216","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-objects-to-events-unlocking-complex","title":"From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning","date":"2025-02-09","arxiv_id":"2502.05843","repositories_listed":0,"syntology":null},{"url":null,"slug":"secure-visual-data-processing-via-federated","title":"Secure Visual Data Processing via Federated Learning","date":"2025-02-09","arxiv_id":"2502.06889","repositories_listed":0,"syntology":null},{"url":null,"slug":"demystifying-catastrophic-forgetting-in-two","title":"Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector","date":"2025-02-08","arxiv_id":"2502.05540","repositories_listed":0,"syntology":null},{"url":null,"slug":"aiqvit-architecture-informed-post-training","title":"AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers","date":"2025-02-07","arxiv_id":"2502.04628","repositories_listed":0,"syntology":null},{"url":null,"slug":"counting-fish-with-temporal-representations","title":"Counting Fish with Temporal Representations of Sonar Video","date":"2025-02-07","arxiv_id":"2502.05129","repositories_listed":0,"syntology":null},{"url":null,"slug":"detvpcc-roi-based-point-cloud-sequence","title":"DetVPCC: RoI-based Point Cloud Sequence Compression for 3D Object Detection","date":"2025-02-07","arxiv_id":"2502.04804","repositories_listed":0,"syntology":null},{"url":null,"slug":"lp-detr-layer-wise-progressive-relations-for","title":"LP-DETR: Layer-wise Progressive Relations for Object Detection","date":"2025-02-07","arxiv_id":"2502.05147","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-performance-analysis-of-you-only-look-once","title":"A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications","date":"2025-02-06","arxiv_id":"2502.15737","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-object-detection-and-pose-estimation","title":"Advanced Object Detection and Pose Estimation with Hybrid Task Cascade and High-Resolution Networks","date":"2025-02-06","arxiv_id":"2502.03877","repositories_listed":0,"syntology":null}],"record_sha256":"536e15a002ed46b69c0cabccbd8dbc2118518db95df78a76b0ce07a0c28ef70e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}