{"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/60","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":60,"pages_in_order":110,"rows_per_page":100,"rows":[5901,6000],"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/59","next":"/task/object-detection/papers/61","papers":[{"url":null,"slug":"few-shot-object-detection-research-advances","title":"Few-Shot Object Detection: Research Advances and Challenges","date":"2024-04-07","arxiv_id":"2404.04799","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperbolic-learning-with-synthetic-captions","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","date":"2024-04-07","arxiv_id":"2404.05016","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffuser-diffusion-model-for-robust-multi","title":"DifFUSER: Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation","date":"2024-04-06","arxiv_id":"2404.04629","repositories_listed":0,"syntology":null},{"url":null,"slug":"glcm-based-feature-combination-for-extraction","title":"GLCM-Based Feature Combination for Extraction Model Optimization in Object Detection Using Machine Learning","date":"2024-04-06","arxiv_id":"2404.04578","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-large-language-models-for","title":"Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement","date":"2024-04-06","arxiv_id":"2404.04627","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-detection-in-aerial-images-by","title":"Context-Aware Aerial Object Detection: Leveraging Inter-Object and Background Relationships","date":"2024-04-05","arxiv_id":"2404.04140","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-methodology-to-study-the-impact-of-spiking","title":"A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data","date":"2024-04-04","arxiv_id":"2404.03493","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-temporal-cues-by-predicting-objects","title":"Learning Temporal Cues by Predicting Objects Move for Multi-camera 3D Object Detection","date":"2024-04-02","arxiv_id":"2404.01580","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-control-camera-exposure-via","title":"Learning to Control Camera Exposure via Reinforcement Learning","date":"2024-04-02","arxiv_id":"2404.01636","repositories_listed":0,"syntology":null},{"url":null,"slug":"lr-fpn-enhancing-remote-sensing-object","title":"LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network","date":"2024-04-02","arxiv_id":"2404.01614","repositories_listed":0,"syntology":null},{"url":"/paper/sparse-semi-detr-sparse-learnable-queries-for","slug":"sparse-semi-detr-sparse-learnable-queries-for","title":"Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection","date":"2024-04-02","arxiv_id":"2404.01819","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-integration-distillation-for-object","title":"Task Integration Distillation for Object Detectors","date":"2024-04-02","arxiv_id":"2404.01699","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-enhanced-analysis-of-lung-cancer","title":"Towards Enhanced Analysis of Lung Cancer Lesions in EBUS-TBNA -- A Semi-Supervised Video Object Detection Method","date":"2024-04-02","arxiv_id":"2404.01929","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect2interact-localizing-object-key-field","title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs","date":"2024-04-01","arxiv_id":"2404.01151","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-aware-group-quantization-for-vision","title":"Instance-Aware Group Quantization for Vision Transformers","date":"2024-04-01","arxiv_id":"2404.00928","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-robustness-of-open-vocabulary","title":"Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts","date":"2024-04-01","arxiv_id":"2405.14874","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-conditioned-bag-of-instances-for-few","title":"Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition","date":"2024-04-01","arxiv_id":"2404.01397","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-learning-for-oriented-power","title":"Prompt Learning for Oriented Power Transmission Tower Detection in High-Resolution SAR Images","date":"2024-04-01","arxiv_id":"2404.01074","repositories_listed":0,"syntology":null},{"url":null,"slug":"quad-query-based-interpretable-neural-motion","title":"QuAD: Query-based Interpretable Neural Motion Planning for Autonomous Driving","date":"2024-04-01","arxiv_id":"2404.01486","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolov5-vs-yolov8-in-marine-fisheries","title":"YOLOv5 vs. YOLOv8 in Marine Fisheries: Balancing Class Detection and Instance Count","date":"2024-04-01","arxiv_id":"2405.02312","repositories_listed":0,"syntology":null},{"url":null,"slug":"attire-based-anomaly-detection-in-restricted","title":"Attire-Based Anomaly Detection in Restricted Areas Using YOLOv8 for Enhanced CCTV Security","date":"2024-03-31","arxiv_id":"2404.00645","repositories_listed":0,"syntology":null},{"url":"/paper/dual-detrs-for-multi-label-temporal-action","slug":"dual-detrs-for-multi-label-temporal-action","title":"Dual DETRs for Multi-Label Temporal Action Detection","date":"2024-03-31","arxiv_id":"2404.00653","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-active-defense-leveraging-recurrent","title":"Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches","date":"2024-03-31","arxiv_id":"2404.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-cutting-point-estimation-for-robotic","title":"Accurate Cutting-point Estimation for Robotic Lychee Harvesting through Geometry-aware Learning","date":"2024-03-30","arxiv_id":"2404.00364","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolooc-yolo-based-open-class-incremental","title":"YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery","date":"2024-03-30","arxiv_id":"2404.00257","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambamixer-efficient-selective-state-space","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","date":"2024-03-29","arxiv_id":"2403.19888","repositories_listed":0,"syntology":null},{"url":null,"slug":"ploc-a-new-evaluation-criterion-based-on","title":"PLoc: A New Evaluation Criterion Based on Physical Location for Autonomous Driving Datasets","date":"2024-03-29","arxiv_id":"2403.19893","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-real-time-framework-for-domain-adaptive","title":"A Real-Time Framework for Domain-Adaptive Underwater Object Detection with Image Enhancement","date":"2024-03-28","arxiv_id":"2403.19079","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-ways-of-seeing-using-object","title":"Algorithmic Ways of Seeing: Using Object Detection to Facilitate Art Exploration","date":"2024-03-28","arxiv_id":"2403.19174","repositories_listed":0,"syntology":null},{"url":null,"slug":"cat-exploiting-inter-class-dynamics-for","title":"CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection","date":"2024-03-28","arxiv_id":"2403.19278","repositories_listed":0,"syntology":null},{"url":null,"slug":"crkd-enhanced-camera-radar-object-detection","title":"CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation","date":"2024-03-28","arxiv_id":"2403.19104","repositories_listed":0,"syntology":null},{"url":null,"slug":"bam-box-abstraction-monitors-for-real-time","title":"BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection","date":"2024-03-27","arxiv_id":"2403.18373","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosalpure-learning-concept-from-group-images","title":"CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection","date":"2024-03-27","arxiv_id":"2403.18554","repositories_listed":0,"syntology":null},{"url":null,"slug":"illicit-object-detection-in-x-ray-images","title":"Illicit object detection in X-ray images using Vision Transformers","date":"2024-03-27","arxiv_id":"2403.19043","repositories_listed":0,"syntology":null},{"url":null,"slug":"road-obstacle-detection-based-on-unknown","title":"Road Obstacle Detection based on Unknown Objectness Scores","date":"2024-03-27","arxiv_id":"2403.18207","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgdm-static-guided-dynamic-module-make","title":"SGDM: Static-Guided Dynamic Module Make Stronger Visual Models","date":"2024-03-27","arxiv_id":"2403.18282","repositories_listed":0,"syntology":null},{"url":null,"slug":"aide-an-automatic-data-engine-for-object","title":"AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving","date":"2024-03-26","arxiv_id":"2403.17373","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-pseudo-labeling-for-semi-supervised","title":"Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection","date":"2024-03-26","arxiv_id":"2403.17387","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssf3d-strict-semi-supervised-3d-object","title":"SSF3D: Strict Semi-Supervised 3D Object Detection with Switching Filter","date":"2024-03-26","arxiv_id":"2403.17390","repositories_listed":0,"syntology":null},{"url":null,"slug":"staircase-localization-for-autonomous","title":"Staircase Localization for Autonomous Exploration in Urban Environments","date":"2024-03-26","arxiv_id":"2403.17330","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-of-the-art-applications-of-deep","title":"State of the art applications of deep learning within tracking and detecting marine debris: A survey","date":"2024-03-26","arxiv_id":"2403.18067","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-solution-for-the-cvpr-2023-1st-foundation","title":"The Solution for the CVPR 2023 1st foundation model challenge-Track2","date":"2024-03-26","arxiv_id":"2403.17702","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-occurring-of-object-detection-and","title":"Co-Occurring of Object Detection and Identification towards unlabeled object discovery","date":"2024-03-25","arxiv_id":"2403.17223","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-video-compression-artifacts-on","title":"Impact of Video Compression Artifacts on Fisheye Camera Visual Perception Tasks","date":"2024-03-25","arxiv_id":"2403.16338","repositories_listed":0,"syntology":null},{"url":null,"slug":"isolated-diffusion-optimizing-multi-concept","title":"Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely with Isolated Diffusion Guidance","date":"2024-03-25","arxiv_id":"2403.16954","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-task-aware-language-image","title":"Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection","date":"2024-03-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-is-enough-only-semantic-information","title":"Semantic Is Enough: Only Semantic Information For NeRF Reconstruction","date":"2024-03-24","arxiv_id":"2403.16043","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-defense-teacher-for-cross-domain","title":"Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions","date":"2024-03-23","arxiv_id":"2403.15786","repositories_listed":0,"syntology":null},{"url":null,"slug":"parformer-vision-transformer-baseline-with","title":"ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding","date":"2024-03-22","arxiv_id":"2403.15004","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-detr3d-leveraging-imagery-data-with","title":"Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection","date":"2024-03-22","arxiv_id":"2403.15317","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-object-detection-from-point-cloud-via","title":"3D Object Detection from Point Cloud via Voting Step Diffusion","date":"2024-03-21","arxiv_id":"2403.14133","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-active-learning-a-reality-check","title":"Deep Active Learning: A Reality Check","date":"2024-03-21","arxiv_id":"2403.14800","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-vit-end-to-end-open-vocabulary","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","date":"2024-03-21","arxiv_id":"2403.14270","repositories_listed":0,"syntology":null},{"url":null,"slug":"detdiffusion-synergizing-generative-and","title":"DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception","date":"2024-03-20","arxiv_id":"2403.13304","repositories_listed":0,"syntology":null},{"url":null,"slug":"ec-iou-orienting-safety-for-object-detectors","title":"EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union","date":"2024-03-20","arxiv_id":"2403.15474","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecosense-energy-efficient-intelligent-sensing","title":"EcoSense: Energy-Efficient Intelligent Sensing for In-Shore Ship Detection through Edge-Cloud Collaboration","date":"2024-03-20","arxiv_id":"2403.14027","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-oriented-object-detection-with","title":"Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images","date":"2024-03-20","arxiv_id":"2403.13375","repositories_listed":0,"syntology":null},{"url":null,"slug":"fostc3net-a-lightweight-yolov5-based-on-the","title":"Fostc3net:A Lightweight YOLOv5 Based On the Network Structure Optimization","date":"2024-03-20","arxiv_id":"2403.13703","repositories_listed":0,"syntology":null},{"url":null,"slug":"as-firm-as-their-foundations-can-open-sourced","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","date":"2024-03-19","arxiv_id":"2403.12693","repositories_listed":0,"syntology":null},{"url":null,"slug":"entity6k-a-large-open-domain-evaluation","title":"Entity6K: A Large Open-Domain Evaluation Dataset for Real-World Entity Recognition","date":"2024-03-19","arxiv_id":"2403.12339","repositories_listed":0,"syntology":null},{"url":"/paper/scenescript-reconstructing-scenes-with-an","slug":"scenescript-reconstructing-scenes-with-an","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","date":"2024-03-19","arxiv_id":"2403.13064","repositories_listed":0,"syntology":null},{"url":null,"slug":"taptr-tracking-any-point-with-transformers-as","title":"TAPTR: Tracking Any Point with Transformers as Detection","date":"2024-03-19","arxiv_id":"2403.13042","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformmix-learning-transformation-and","title":"TransformMix: Learning Transformation and Mixing Strategies from Data","date":"2024-03-19","arxiv_id":"2403.12429","repositories_listed":0,"syntology":null},{"url":null,"slug":"effiperception-an-efficient-framework-for","title":"EffiPerception: an Efficient Framework for Various Perception Tasks","date":"2024-03-18","arxiv_id":"2403.12317","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexcap-generating-rich-localized-and","title":"FlexCap: Describe Anything in Images in Controllable Detail","date":"2024-03-18","arxiv_id":"2403.12026","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphbev-towards-robust-bev-feature-alignment","title":"GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection","date":"2024-03-18","arxiv_id":"2403.11848","repositories_listed":0,"syntology":null},{"url":null,"slug":"just-add-100-more-augmenting-nerf-based","title":"Just Add $100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem","date":"2024-03-18","arxiv_id":"2403.11573","repositories_listed":0,"syntology":null},{"url":null,"slug":"prototipo-de-un-contador-bidireccional","title":"Prototipo de un Contador Bidireccional Automático de Personas basado en sensores de visión 3D","date":"2024-03-18","arxiv_id":"2403.12310","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-real-time-fast-unmanned-aerial","title":"Towards Real-Time Fast Unmanned Aerial Vehicle Detection Using Dynamic Vision Sensors","date":"2024-03-18","arxiv_id":"2403.11875","repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectorynas-a-neural-architecture-search","title":"TrajectoryNAS: A Neural Architecture Search for Trajectory Prediction","date":"2024-03-18","arxiv_id":"2403.11695","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-knowledge-extraction-of-physical","title":"Advanced Knowledge Extraction of Physical Design Drawings, Translation and conversion to CAD formats using Deep Learning","date":"2024-03-17","arxiv_id":"2403.11291","repositories_listed":0,"syntology":null},{"url":null,"slug":"gra-detecting-oriented-objects-through-group","title":"GRA: Detecting Oriented Objects through Group-wise Rotating and Attention","date":"2024-03-17","arxiv_id":"2403.11127","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-railroad-grade-crossing","title":"Intelligent Railroad Grade Crossing: Leveraging Semantic Segmentation and Object Detection for Enhanced Safety","date":"2024-03-17","arxiv_id":"2403.11060","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2x-dgw-domain-generalization-for-multi-agent","title":"V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions","date":"2024-03-17","arxiv_id":"2403.11371","repositories_listed":0,"syntology":null},{"url":null,"slug":"fishnet-deep-neural-networks-for-low-cost","title":"FishNet: Deep Neural Networks for Low-Cost Fish Stock Estimation","date":"2024-03-16","arxiv_id":"2403.10916","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-snn-ann-network-for-event-based","title":"A Hybrid SNN-ANN Network for Event-based Object Detection with Spatial and Temporal Attention","date":"2024-03-15","arxiv_id":"2403.10173","repositories_listed":0,"syntology":null},{"url":null,"slug":"cannabis-seed-variant-detection-using-faster","title":"Cannabis Seed Variant Detection using Faster R-CNN","date":"2024-03-15","arxiv_id":"2403.10722","repositories_listed":0,"syntology":null},{"url":null,"slug":"csdnet-detect-salient-object-in-depth-thermal","title":"CSDNet: Detect Salient Object in Depth-Thermal via A Lightweight Cross Shallow and Deep Perception Network","date":"2024-03-15","arxiv_id":"2403.10104","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsefusion-efficient-sparse-multi-modal","title":"SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception","date":"2024-03-15","arxiv_id":"2403.10036","repositories_listed":0,"syntology":null},{"url":null,"slug":"spiking-neural-networks-for-fast-moving","title":"Detection of Fast-Moving Objects with Neuromorphic Hardware","date":"2024-03-15","arxiv_id":"2403.10677","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-yolo-a-robust-framework-for-object","title":"D-YOLO a robust framework for object detection in adverse weather conditions","date":"2024-03-14","arxiv_id":"2403.09233","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-distant-3d-object-detection-using","title":"Improving Distant 3D Object Detection Using 2D Box Supervision","date":"2024-03-14","arxiv_id":"2403.09230","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-object-detection-with-meta","title":"Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization","date":"2024-03-14","arxiv_id":"2403.09433","repositories_listed":0,"syntology":null},{"url":null,"slug":"poifusion-multi-modal-3d-object-detection-via","title":"PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest","date":"2024-03-14","arxiv_id":"2403.09212","repositories_listed":0,"syntology":null},{"url":null,"slug":"shan-object-level-privacy-detection-via","title":"SHAN: Object-Level Privacy Detection via Inference on Scene Heterogeneous Graph","date":"2024-03-14","arxiv_id":"2403.09172","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-fusion-network-for-student","title":"A Multimodal Fusion Network For Student Emotion Recognition Based on Transformer and Tensor Product","date":"2024-03-13","arxiv_id":"2403.08511","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-security-in-ai-systems-a-novel","title":"Advancing Security in AI Systems: A Novel Approach to Detecting Backdoors in Deep Neural Networks","date":"2024-03-13","arxiv_id":"2403.08208","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-bevformer-enhancing-multi-view-image","title":"CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow","date":"2024-03-13","arxiv_id":"2403.08919","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-yolov5-based-on-attention-mechanism","title":"Improved YOLOv5 Based on Attention Mechanism and FasterNet for Foreign Object Detection on Railway and Airway tracks","date":"2024-03-13","arxiv_id":"2403.08499","repositories_listed":0,"syntology":null},{"url":null,"slug":"shadowremovalnet-efficient-real-time-shadow","title":"FieldNet: Efficient Real-Time Shadow Removal for Enhanced Vision in Field Robotics","date":"2024-03-13","arxiv_id":"2403.08142","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-vision-transformers-in-autonomous","title":"A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions","date":"2024-03-12","arxiv_id":"2403.07542","repositories_listed":0,"syntology":null},{"url":null,"slug":"aedes-aegypti-egg-counting-with-neural","title":"Aedes aegypti Egg Counting with Neural Networks for Object Detection","date":"2024-03-12","arxiv_id":"2403.08016","repositories_listed":0,"syntology":null},{"url":null,"slug":"eliminating-cross-modal-conflicts-in-bev","title":"Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection","date":"2024-03-12","arxiv_id":"2403.07372","repositories_listed":0,"syntology":null},{"url":null,"slug":"jstr-joint-spatio-temporal-reasoning-for","title":"JSTR: Joint Spatio-Temporal Reasoning for Event-based Moving Object Detection","date":"2024-03-12","arxiv_id":"2403.07436","repositories_listed":0,"syntology":null},{"url":null,"slug":"mondrian-on-device-high-performance-video","title":"Mondrian: On-Device High-Performance Video Analytics with Compressive Packed Inference","date":"2024-03-12","arxiv_id":"2403.07598","repositories_listed":0,"syntology":null},{"url":null,"slug":"pelk-parameter-efficient-large-kernel","title":"PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution","date":"2024-03-12","arxiv_id":"2403.07589","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparselif-high-performance-sparse-lidar","title":"SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection","date":"2024-03-12","arxiv_id":"2403.07284","repositories_listed":0,"syntology":null},{"url":null,"slug":"taskclip-extend-large-vision-language-model","title":"TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection","date":"2024-03-12","arxiv_id":"2403.08108","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-energy-efficiency-of-few-shot","title":"Evaluating the Energy Efficiency of Few-Shot Learning for Object Detection in Industrial Settings","date":"2024-03-11","arxiv_id":"2403.06631","repositories_listed":0,"syntology":null},{"url":"/paper/inception-yolo-computational-cost-and","slug":"inception-yolo-computational-cost-and","title":"Inception-YOLO: Computational cost and accuracy improvement of the YOLOv5 model based on employing modified CSP, SPPF, and inception modules","date":"2024-03-11","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"aaf0cfa36dc531a0fed682717e9617f6ca1542f40dcf150ba9172978c7711b94","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}