{"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-1/papers/50","list_of":"/task/object-detection-1","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":106,"rows_per_page":100,"rows":[4901,5000],"of":10514,"counts":{"archive_papers_tagged":10514,"with_a_code_link":4285,"where_syntology_ran_a_sample":1027,"not_listed_spam_title":0,"listed":10514,"listed_where_code_ran":1027,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":898,"every_run_a_failure_of_syntologys_instrument":129,"listed_with_a_run_with_no_instrument_failure":898,"listed_every_run_a_failure_of_syntologys_instrument":129,"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-1","prev":"/task/object-detection-1/papers/49","next":"/task/object-detection-1/papers/51","papers":[{"url":null,"slug":"efficient-3d-perception-on-multi-sweep-point","title":"Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning","date":"2024-11-12","arxiv_id":"2411.07742","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-frequency-enhancement-network-for","title":"Multi-scale Frequency Enhancement Network for Blind Image Deblurring","date":"2024-11-11","arxiv_id":"2411.06893","repositories_listed":0,"syntology":null},{"url":null,"slug":"track-any-peppers-weakly-supervised-sweet","title":"Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs","date":"2024-11-11","arxiv_id":"2411.06702","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-compass-a-comprehensive-and-effective","title":"AI-Compass: A Comprehensive and Effective Multi-module Testing Tool for AI Systems","date":"2024-11-09","arxiv_id":"2411.06146","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-collision-risk-estimation-via","title":"FuzzRisk: Online Collision Risk Estimation for Autonomous Vehicles based on Depth-Aware Object Detection via Fuzzy Inference","date":"2024-11-09","arxiv_id":"2411.08060","repositories_listed":0,"syntology":null},{"url":null,"slug":"pattern-integration-and-enhancement-vision","title":"Pattern Integration and Enhancement Vision Transformer for Self-Supervised Learning in Remote Sensing","date":"2024-11-09","arxiv_id":"2411.06091","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-object-detection-modality-into","title":"Integrating Object Detection Modality into Visual Language Model for Enhanced Autonomous Driving Agent","date":"2024-11-08","arxiv_id":"2411.05898","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-object-detection-towards-unified","title":"Open-set object detection: towards unified problem formulation and benchmarking","date":"2024-11-08","arxiv_id":"2411.05564","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplebev-improved-lidar-camera-fusion","title":"SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection","date":"2024-11-08","arxiv_id":"2411.05292","repositories_listed":0,"syntology":null},{"url":null,"slug":"zopp-a-framework-of-zero-shot-offboard","title":"ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving","date":"2024-11-08","arxiv_id":"2411.05311","repositories_listed":0,"syntology":null},{"url":null,"slug":"l0-regularized-sparse-coding-based","title":"l0-Regularized Sparse Coding-based Interpretable Network for Multi-Modal Image Fusion","date":"2024-11-07","arxiv_id":"2411.04519","repositories_listed":0,"syntology":null},{"url":null,"slug":"pose2trajectory-using-transformers-on-body","title":"Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory","date":"2024-11-07","arxiv_id":"2411.04501","repositories_listed":0,"syntology":null},{"url":null,"slug":"uevavd-a-dataset-for-developing-uav-s-eye","title":"UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection","date":"2024-11-07","arxiv_id":"2411.04348","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-of-psychosocial-work-environment","title":"Estimation of Psychosocial Work Environment Exposures Through Video Object Detection. Proof of Concept Using CCTV Footage","date":"2024-11-06","arxiv_id":"2411.03724","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-application-agnostic-automatic-target","title":"An Application-Agnostic Automatic Target Recognition System Using Vision Language Models","date":"2024-11-05","arxiv_id":"2411.03491","repositories_listed":0,"syntology":null},{"url":null,"slug":"centerness-based-instance-aware-knowledge","title":"Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery","date":"2024-11-05","arxiv_id":"2411.02861","repositories_listed":0,"syntology":null},{"url":null,"slug":"erup-yolo-enhancing-object-detection","title":"ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing","date":"2024-11-05","arxiv_id":"2411.02799","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-pixels-to-prose-advancing-multi-modal","title":"From Pixels to Prose: Advancing Multi-Modal Language Models for Remote Sensing","date":"2024-11-05","arxiv_id":"2411.05826","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-cross-modality-learning-for","title":"Self-supervised cross-modality learning for uncertainty-aware object detection and recognition in applications which lack pre-labelled training data","date":"2024-11-05","arxiv_id":"2411.03082","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-video-recording-optimization","title":"Intelligent Video Recording Optimization using Activity Detection for Surveillance Systems","date":"2024-11-04","arxiv_id":"2411.02632","repositories_listed":0,"syntology":null},{"url":"/paper/sira-scalable-inter-frame-relation-and-1","slug":"sira-scalable-inter-frame-relation-and-1","title":"SIRA: Scalable Inter-frame Relation and Association for Radar Perception","date":"2024-11-04","arxiv_id":"2411.02220","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-cas-a-realtime-vehicle-anti-collision","title":"V-CAS: A Realtime Vehicle Anti Collision System Using Vision Transformer on Multi-Camera Streams","date":"2024-11-04","arxiv_id":"2411.01963","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-visual-question-answering-method-for-sar","title":"A Visual Question Answering Method for SAR Ship: Breaking the Requirement for Multimodal Dataset Construction and Model Fine-Tuning","date":"2024-11-03","arxiv_id":"2411.01445","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-deep-learning-infrastructures-for","title":"Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision","date":"2024-11-03","arxiv_id":"2411.01431","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-for-all-multi-domain-joint-training-for","title":"One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection","date":"2024-11-03","arxiv_id":"2411.01584","repositories_listed":0,"syntology":null},{"url":null,"slug":"osad-open-set-aircraft-detection-in-sar","title":"OSAD: Open-Set Aircraft Detection in SAR Images","date":"2024-11-03","arxiv_id":"2411.01597","repositories_listed":0,"syntology":null},{"url":null,"slug":"autobiasing-event-cameras","title":"Autobiasing Event Cameras","date":"2024-11-01","arxiv_id":"2411.00729","repositories_listed":0,"syntology":null},{"url":null,"slug":"gafusion-adaptive-fusing-lidar-and-camera-1","title":"GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection","date":"2024-11-01","arxiv_id":"2411.00340","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-based-pipeline-architecture-for","title":"Generative AI-based Pipeline Architecture for Increasing Training Efficiency in Intelligent Weed Control Systems","date":"2024-11-01","arxiv_id":"2411.00548","repositories_listed":0,"syntology":null},{"url":null,"slug":"lam-yolo-drones-based-small-object-detection","title":"LAM-YOLO: Drones-based Small Object Detection on Lighting-Occlusion Attention Mechanism YOLO","date":"2024-11-01","arxiv_id":"2411.00485","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-token-selection-and-packing-for","title":"Context-Aware Token Selection and Packing for Enhanced Vision Transformer","date":"2024-10-31","arxiv_id":"2410.23608","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-evolution-of-yolo-you-only","title":"Evaluating the Evolution of YOLO (You Only Look Once) Models: A Comprehensive Benchmark Study of YOLO11 and Its Predecessors","date":"2024-10-31","arxiv_id":"2411.00201","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-web-data-to-real-fields-low-cost","title":"From Web Data to Real Fields: Low-Cost Unsupervised Domain Adaptation for Agricultural Robots","date":"2024-10-31","arxiv_id":"2410.23906","repositories_listed":0,"syntology":null},{"url":null,"slug":"localization-balance-and-affinity-a-stronger","title":"Localization, balance and affinity: a stronger multifaceted collaborative salient object detector in remote sensing images","date":"2024-10-31","arxiv_id":"2410.23991","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-set-3d-object-detection-in-lidar-data-as","title":"HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data","date":"2024-10-31","arxiv_id":"2410.23767","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-estimation-for-3d-object","title":"Uncertainty Estimation for 3D Object Detection via Evidential Learning","date":"2024-10-31","arxiv_id":"2410.23910","repositories_listed":0,"syntology":null},{"url":null,"slug":"whole-herd-elephant-pose-estimation-from","title":"Whole-Herd Elephant Pose Estimation from Drone Data for Collective Behavior Analysis","date":"2024-10-31","arxiv_id":"2411.00196","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptiveisp-learning-an-adaptive-image-signal","title":"AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection","date":"2024-10-30","arxiv_id":"2410.22939","repositories_listed":0,"syntology":null},{"url":null,"slug":"emma-end-to-end-multimodal-model-for","title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","date":"2024-10-30","arxiv_id":"2410.23262","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-place-solution-to-the-eccv-2024-road-1","title":"First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024","date":"2024-10-30","arxiv_id":"2410.23077","repositories_listed":0,"syntology":null},{"url":null,"slug":"s3pt-scene-semantics-and-structure-guided","title":"S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving","date":"2024-10-30","arxiv_id":"2410.23085","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-image-data-leakage-detection-in","title":"Improving Image Data Leakage Detection in Automotive Software","date":"2024-10-29","arxiv_id":"2410.23312","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-domain-generalization-and-adaptation","title":"Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection","date":"2024-10-29","arxiv_id":"2410.22461","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsetem-boosting-the-efficiency-of-cnn","title":"SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity","date":"2024-10-28","arxiv_id":"2410.20790","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetica-large-scale-synthetic-data-for","title":"Synthetica: Large Scale Synthetic Data for Robot Perception","date":"2024-10-28","arxiv_id":"2410.21153","repositories_listed":0,"syntology":null},{"url":null,"slug":"taco-adversarial-camouflage-optimization-on","title":"TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors","date":"2024-10-28","arxiv_id":"2410.21443","repositories_listed":0,"syntology":null},{"url":null,"slug":"historical-test-time-prompt-tuning-for-vision","title":"Historical Test-time Prompt Tuning for Vision Foundation Models","date":"2024-10-27","arxiv_id":"2410.20346","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-via-language","title":"Open-Vocabulary Object Detection via Language Hierarchy","date":"2024-10-27","arxiv_id":"2410.20371","repositories_listed":0,"syntology":null},{"url":null,"slug":"decade-towards-designing-efficient-yet","title":"DECADE: Towards Designing Efficient-yet-Accurate Distance Estimation Modules for Collision Avoidance in Mobile Advanced Driver Assistance Systems","date":"2024-10-25","arxiv_id":"2410.19336","repositories_listed":0,"syntology":null},{"url":null,"slug":"frozen-detr-enhancing-detr-with-image","title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","date":"2024-10-25","arxiv_id":"2410.19635","repositories_listed":0,"syntology":null},{"url":null,"slug":"metatrading-an-immersion-aware-model-trading","title":"MetaTrading: An Immersion-Aware Model Trading Framework for Vehicular Metaverse Services","date":"2024-10-25","arxiv_id":"2410.19665","repositories_listed":0,"syntology":null},{"url":null,"slug":"oreole-fm-successes-and-challenges-toward","title":"OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery","date":"2024-10-25","arxiv_id":"2410.19965","repositories_listed":0,"syntology":null},{"url":null,"slug":"hue-dataset-high-resolution-event-and-frame","title":"HUE Dataset: High-Resolution Event and Frame Sequences for Low-Light Vision","date":"2024-10-24","arxiv_id":"2410.19164","repositories_listed":0,"syntology":null},{"url":null,"slug":"radar-and-camera-fusion-for-object-detection","title":"Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey","date":"2024-10-24","arxiv_id":"2410.19872","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-defect-detection-and-grading-of","title":"Automated Defect Detection and Grading of Piarom Dates Using Deep Learning","date":"2024-10-23","arxiv_id":"2410.18208","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-illusion-real-world-challenges","title":"Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection","date":"2024-10-23","arxiv_id":"2410.19863","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo-vehicle-pro-a-cloud-edge-collaborative","title":"YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions","date":"2024-10-23","arxiv_id":"2410.17734","repositories_listed":0,"syntology":null},{"url":null,"slug":"dsort-mcu-detecting-small-objects-in-real","title":"DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units","date":"2024-10-22","arxiv_id":"2410.16769","repositories_listed":0,"syntology":null},{"url":null,"slug":"epcontrast-effective-point-level-contrastive","title":"EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding","date":"2024-10-22","arxiv_id":"2410.17207","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo-ts-real-time-traffic-sign-detection-with","title":"YOLO-TS: Real-Time Traffic Sign Detection with Enhanced Accuracy Using Optimized Receptive Fields and Anchor-Free Fusion","date":"2024-10-22","arxiv_id":"2410.17144","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-and-machine-learning-object","title":"Deep Learning and Machine Learning -- Object Detection and Semantic Segmentation: From Theory to Applications","date":"2024-10-21","arxiv_id":"2410.15584","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-target-driven-instance-detection","title":"Few-shot target-driven instance detection based on open-vocabulary object detection models","date":"2024-10-21","arxiv_id":"2410.16028","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-important-are-data-augmentations-to-close","title":"How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?","date":"2024-10-21","arxiv_id":"2410.15766","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-sensor-fusion-for-uav-classification","title":"Multi-Sensor Fusion for UAV Classification Based on Feature Maps of Image and Radar Data","date":"2024-10-21","arxiv_id":"2410.16089","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-pseudo-label-unified-object-detection","title":"Online Pseudo-Label Unified Object Detection for Multiple Datasets Training","date":"2024-10-21","arxiv_id":"2410.15569","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-yolov8-efficient-and-accurate-real-time","title":"P-YOLOv8: Efficient and Accurate Real-Time Detection of Distracted Driving","date":"2024-10-21","arxiv_id":"2410.15602","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-learning-to-defer-for-multi-task","title":"A Two-Stage Learning-to-Defer Approach for Multi-Task Learning","date":"2024-10-21","arxiv_id":"2410.15729","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo11-and-vision-transformers-based-3d-pose","title":"YOLO11 and Vision Transformers based 3D Pose Estimation of Immature Green Fruits in Commercial Apple Orchards for Robotic Thinning","date":"2024-10-21","arxiv_id":"2410.19846","repositories_listed":0,"syntology":null},{"url":null,"slug":"cutting-edge-detection-of-fatigue-in-drivers","title":"Cutting-Edge Detection of Fatigue in Drivers: A Comparative Study of Object Detection Models","date":"2024-10-19","arxiv_id":"2410.15030","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-generic-dynamic-object-detection-based","title":"Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps","date":"2024-10-18","arxiv_id":"2410.14799","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-in-vehicle-multiple-object-tracking","title":"Enhancing In-vehicle Multiple Object Tracking Systems with Embeddable Ising Machines","date":"2024-10-18","arxiv_id":"2410.14093","repositories_listed":0,"syntology":null},{"url":null,"slug":"ludvig-learning-free-uplifting-of-2d-visual","title":"LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes","date":"2024-10-18","arxiv_id":"2410.14462","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiorg-a-multi-rater-organoid-detection","title":"MultiOrg: A Multi-rater Organoid-detection Dataset","date":"2024-10-18","arxiv_id":"2410.14612","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-object-detection-with-yolov4-for","title":"Accelerating Object Detection with YOLOv4 for Real-Time Applications","date":"2024-10-17","arxiv_id":"2410.16320","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-surface-landmine-object-detection","title":"Comparing Surface Landmine Object Detection Models on a New Drone Flyby Dataset","date":"2024-10-17","arxiv_id":"2410.19807","repositories_listed":0,"syntology":null},{"url":null,"slug":"remotedet-mamba-a-hybrid-mamba-cnn-network","title":"RemoteDet-Mamba: A Hybrid Mamba-CNN Network for Multi-modal Object Detection in Remote Sensing Images","date":"2024-10-17","arxiv_id":"2410.13532","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-object-detection-for-improved","title":"Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring","date":"2024-10-17","arxiv_id":"2410.13616","repositories_listed":0,"syntology":null},{"url":null,"slug":"cocoon-robust-multi-modal-perception-with","title":"Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion","date":"2024-10-16","arxiv_id":"2410.12592","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-augmentation-for-self-supervised","title":"Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look","date":"2024-10-16","arxiv_id":"2410.12396","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-from-decomposition-a-self-supervised","title":"Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond","date":"2024-10-16","arxiv_id":"2410.12274","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambabev-an-efficient-3d-detection-model-with","title":"MambaBEV: An efficient 3D detection model with Mamba2","date":"2024-10-16","arxiv_id":"2410.12673","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-yolov5s-object-detection-through","title":"Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm","date":"2024-10-16","arxiv_id":"2410.12259","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-guided-masked-token-prediction-for-3d","title":"SAM-Guided Masked Token Prediction for 3D Scene Understanding","date":"2024-10-16","arxiv_id":"2410.12158","repositories_listed":0,"syntology":null},{"url":null,"slug":"syn2real-domain-generalization-for-underwater","title":"Syn2Real Domain Generalization for Underwater Mine-like Object Detection Using Side-Scan Sonar","date":"2024-10-16","arxiv_id":"2410.12953","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-limits-of-alignment-multi-modal","title":"Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmark","date":"2024-10-16","arxiv_id":"2410.12143","repositories_listed":0,"syntology":null},{"url":null,"slug":"polo-point-based-multi-class-animal-detection","title":"POLO -- Point-based, multi-class animal detection","date":"2024-10-15","arxiv_id":"2410.11741","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-similarity-a-better-guidance","title":"Representation Similarity: A Better Guidance of DNN Layer Sharing for Edge Computing without Training","date":"2024-10-15","arxiv_id":"2410.11233","repositories_listed":0,"syntology":null},{"url":null,"slug":"seadate-remedy-dual-attention-transformer","title":"SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection","date":"2024-10-15","arxiv_id":"2410.11358","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo-ela-efficient-local-attention-modeling","title":"YOLO-ELA: Efficient Local Attention Modeling for High-Performance Real-Time Insulator Defect Detection","date":"2024-10-15","arxiv_id":"2410.11727","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-gridded-emission-inventory-from","title":"Developing Gridded Emission Inventory from High-Resolution Satellite Object Detection for Improved Air Quality Forecasts","date":"2024-10-14","arxiv_id":"2410.19773","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-ground-vlms-without-forgetting","title":"Learning to Ground VLMs without Forgetting","date":"2024-10-14","arxiv_id":"2410.10491","repositories_listed":0,"syntology":null},{"url":null,"slug":"roa-bev-2d-region-oriented-attention-for-bev","title":"ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object","date":"2024-10-14","arxiv_id":"2410.10298","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav3d-a-large-scale-3d-perception-benchmark","title":"UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles","date":"2024-10-14","arxiv_id":"2410.11125","repositories_listed":0,"syntology":null},{"url":null,"slug":"eitnet-an-iot-enhanced-framework-for-real","title":"EITNet: An IoT-Enhanced Framework for Real-Time Basketball Action Recognition","date":"2024-10-13","arxiv_id":"2410.09954","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-waste-management-with-advanced","title":"Optimizing Waste Management with Advanced Object Detection for Garbage Classification","date":"2024-10-13","arxiv_id":"2410.09975","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-expeditious-spatial-mean-radiant","title":"An Expeditious Spatial Mean Radiant Temperature Mapping Framework using Visual SLAM and Semantic Segmentation","date":"2024-10-12","arxiv_id":"2410.09443","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-pruning-using-a-lightweight-background","title":"Token Pruning using a Lightweight Background Aware Vision Transformer","date":"2024-10-12","arxiv_id":"2410.09324","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-open-vocabulary-object-detection-by","title":"Boosting Open-Vocabulary Object Detection by Handling Background Samples","date":"2024-10-11","arxiv_id":"2410.08645","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmlf-multi-modal-multi-class-late-fusion-for","title":"MMLF: Multi-modal Multi-class Late Fusion for Object Detection with Uncertainty Estimation","date":"2024-10-11","arxiv_id":"2410.08739","repositories_listed":0,"syntology":null},{"url":null,"slug":"vovtrack-exploring-the-potentiality-in-videos","title":"VOVTrack: Exploring the Potentiality in Videos for Open-Vocabulary Object Tracking","date":"2024-10-11","arxiv_id":"2410.08529","repositories_listed":0,"syntology":null}],"record_sha256":"8e981d36ec3c77ebaf38b370ccad256577db3f8dfa51ea7010666a94ed4fac56","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}