{"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/52","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":52,"pages_in_order":106,"rows_per_page":100,"rows":[5101,5200],"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/51","next":"/task/object-detection-1/papers/53","papers":[{"url":null,"slug":"transtreaming-adaptive-delay-aware","title":"Transtreaming: Adaptive Delay-aware Transformer for Real-time Streaming Perception","date":"2024-09-10","arxiv_id":"2409.06584","repositories_listed":0,"syntology":null},{"url":null,"slug":"proto-ood-enhancing-ood-object-detection-with","title":"Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity","date":"2024-09-09","arxiv_id":"2409.05466","repositories_listed":0,"syntology":null},{"url":null,"slug":"renormalized-connection-for-scale-preferred","title":"Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery","date":"2024-09-09","arxiv_id":"2409.05624","repositories_listed":0,"syntology":null},{"url":null,"slug":"replay-consolidation-with-label-propagation","title":"Replay Consolidation with Label Propagation for Continual Object Detection","date":"2024-09-09","arxiv_id":"2409.05650","repositories_listed":0,"syntology":null},{"url":"/paper/rcbevdet-toward-high-accuracy-radar-camera","slug":"rcbevdet-toward-high-accuracy-radar-camera","title":"RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Network","date":"2024-09-08","arxiv_id":"2409.04979","repositories_listed":0,"syntology":null},{"url":null,"slug":"spotactor-training-free-layout-controlled","title":"SpotActor: Training-Free Layout-Controlled Consistent Image Generation","date":"2024-09-07","arxiv_id":"2409.04801","repositories_listed":0,"syntology":null},{"url":null,"slug":"bfa-yolo-balanced-multiscale-object-detection","title":"BFA-YOLO: A balanced multiscale object detection network for building façade attachments detection","date":"2024-09-06","arxiv_id":"2409.04025","repositories_listed":0,"syntology":null},{"url":null,"slug":"d4-text-guided-diffusion-model-based-domain","title":"D4: Text-guided diffusion model-based domain adaptive data augmentation for vineyard shoot detection","date":"2024-09-06","arxiv_id":"2409.04060","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-compression-for-cloud-edge-multimodal","title":"Feature Compression for Cloud-Edge Multimodal 3D Object Detection","date":"2024-09-06","arxiv_id":"2409.04123","repositories_listed":0,"syntology":null},{"url":null,"slug":"future-does-matter-boosting-3d-object","title":"Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences","date":"2024-09-06","arxiv_id":"2409.04390","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-feature-fusion-with-point-pyramid","title":"Multi-scale Feature Fusion with Point Pyramid for 3D Object Detection","date":"2024-09-06","arxiv_id":"2409.04601","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolo-ppa-based-efficient-traffic-sign","title":"YOLO-PPA based Efficient Traffic Sign Detection for Cruise Control in Autonomous Driving","date":"2024-09-05","arxiv_id":"2409.03320","repositories_listed":0,"syntology":null},{"url":null,"slug":"pluralistic-salient-object-detection","title":"Pluralistic Salient Object Detection","date":"2024-09-04","arxiv_id":"2409.02368","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-modern-take-on-visual-relationship","title":"A Modern Take on Visual Relationship Reasoning for Grasp Planning","date":"2024-09-03","arxiv_id":"2409.02035","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-apple-object-detection-with","title":"Improving Apple Object Detection with Occlusion-Enhanced Distillation","date":"2024-09-03","arxiv_id":"2409.01573","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-indoor-object-detection-based-on","title":"Real-Time Indoor Object Detection based on hybrid CNN-Transformer Approach","date":"2024-09-03","arxiv_id":"2409.01871","repositories_listed":0,"syntology":null},{"url":null,"slug":"surveying-you-only-look-once-yolo","title":"Surveying You Only Look Once (YOLO) Multispectral Object Detection Advancements, Applications And Challenges","date":"2024-09-03","arxiv_id":"2409.12977","repositories_listed":0,"syntology":null},{"url":null,"slug":"conda-condensed-deep-association-learning-for","title":"CONDA: Condensed Deep Association Learning for Co-Salient Object Detection","date":"2024-09-02","arxiv_id":"2409.01021","repositories_listed":0,"syntology":null},{"url":null,"slug":"ds-myolo-a-reliable-object-detector-based-on","title":"DS MYOLO: A Reliable Object Detector Based on SSMs for Driving Scenarios","date":"2024-09-02","arxiv_id":"2409.01093","repositories_listed":0,"syntology":null},{"url":null,"slug":"ivgf-the-fusion-guided-infrared-and-visible","title":"IVGF: The Fusion-Guided Infrared and Visible General Framework","date":"2024-09-02","arxiv_id":"2409.00973","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-and-interactive-regression-modeling","title":"Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detection","date":"2024-09-01","arxiv_id":"2409.00690","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-recognition-and-pose-estimation-of","title":"Detection, Recognition and Pose Estimation of Tabletop Objects","date":"2024-09-01","arxiv_id":"2409.00869","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-of-dropout-in-pointpillars-with-3d","title":"Study of Dropout in PointPillars with 3D Object Detection","date":"2024-09-01","arxiv_id":"2409.00673","repositories_listed":0,"syntology":null},{"url":null,"slug":"cp-votenet-contrastive-prototypical-votenet","title":"CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection","date":"2024-08-30","arxiv_id":"2408.17036","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-classification-regression-adaptive","title":"Hybrid Classification-Regression Adaptive Loss for Dense Object Detection","date":"2024-08-30","arxiv_id":"2408.17182","repositories_listed":0,"syntology":null},{"url":null,"slug":"structuring-a-training-strategy-to-robustify","title":"Structuring a Training Strategy to Robustify Perception Models with Realistic Image Augmentations","date":"2024-08-30","arxiv_id":"2408.17311","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-errors-in-controlled-turret-system","title":"Analyzing Errors in Controlled Turret System Given Target Location Input from Artificial Intelligence Methods in Automatic Target Recognition","date":"2024-08-29","arxiv_id":"2408.16923","repositories_listed":0,"syntology":null},{"url":null,"slug":"anno-incomplete-multi-dataset-detection","title":"Anno-incomplete Multi-dataset Detection","date":"2024-08-29","arxiv_id":"2408.16247","repositories_listed":0,"syntology":null},{"url":null,"slug":"fa-yolo-research-on-efficient-feature","title":"FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modules","date":"2024-08-29","arxiv_id":"2408.16313","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-based-human-body-detector-selection-and","title":"UAV-Based Human Body Detector Selection and Fusion for Geolocated Saliency Map Generation","date":"2024-08-29","arxiv_id":"2408.16501","repositories_listed":0,"syntology":null},{"url":null,"slug":"microyolo-towards-single-shot-object","title":"microYOLO: Towards Single-Shot Object Detection on Microcontrollers","date":"2024-08-28","arxiv_id":"2408.15865","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-detection-for-vehicle-dashcams-using","title":"Object Detection for Vehicle Dashcams using Transformers","date":"2024-08-28","arxiv_id":"2408.15809","repositories_listed":0,"syntology":null},{"url":null,"slug":"ride-boosting-3d-object-detection-for-lidar","title":"RIDE: Boosting 3D Object Detection for LiDAR Point Clouds via Rotation-Invariant Analysis","date":"2024-08-28","arxiv_id":"2408.15643","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-object-detection-for-indoor-assistance","title":"Small Object Detection for Indoor Assistance to the Blind using YOLO NAS Small and Super Gradients","date":"2024-08-28","arxiv_id":"2409.07469","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-from-simulated-to-real","title":"Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection","date":"2024-08-28","arxiv_id":"2408.15637","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-yolov8-an-in-depth-exploration-of-the","title":"What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector","date":"2024-08-28","arxiv_id":"2408.15857","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-transformer-based-models-for","title":"A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationships","date":"2024-08-27","arxiv_id":"2408.15178","repositories_listed":0,"syntology":null},{"url":null,"slug":"box3d-lightweight-camera-lidar-fusion-for-3d","title":"BOX3D: Lightweight Camera-LiDAR Fusion for 3D Object Detection and Localization","date":"2024-08-27","arxiv_id":"2408.14941","repositories_listed":0,"syntology":null},{"url":null,"slug":"head-a-bandwidth-efficient-cooperative","title":"HEAD: A Bandwidth-Efficient Cooperative Perception Approach for Heterogeneous Connected and Autonomous Vehicles","date":"2024-08-27","arxiv_id":"2408.15428","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-discovery-in-optical-music","title":"Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation","date":"2024-08-27","arxiv_id":"2408.15002","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-few-shot-object-detection-a-detailed","title":"Beyond Few-shot Object Detection: A Detailed Survey","date":"2024-08-26","arxiv_id":"2408.14249","repositories_listed":0,"syntology":null},{"url":null,"slug":"emdfnet-efficient-multi-scale-and-diverse","title":"EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection","date":"2024-08-26","arxiv_id":"2408.14189","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-pictures-say-more-visual-intersection","title":"More Pictures Say More: Visual Intersection Network for Open Set Object Detection","date":"2024-08-26","arxiv_id":"2408.14032","repositories_listed":0,"syntology":null},{"url":null,"slug":"pvafn-point-voxel-attention-fusion-network","title":"PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection","date":"2024-08-26","arxiv_id":"2408.14600","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-real-world-and","title":"Bridging the Gap between Real-world and Synthetic Images for Testing Autonomous Driving Systems","date":"2024-08-25","arxiv_id":"2408.13950","repositories_listed":0,"syntology":null},{"url":null,"slug":"infrared-domain-adaptation-with-zero-shot","title":"Infrared Domain Adaptation with Zero-Shot Quantization","date":"2024-08-25","arxiv_id":"2408.13925","repositories_listed":0,"syntology":null},{"url":null,"slug":"selectively-dilated-convolution-for-accuracy","title":"Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection","date":"2024-08-25","arxiv_id":"2408.13798","repositories_listed":0,"syntology":null},{"url":null,"slug":"trail-det-transformation-invariant-local","title":"TraIL-Det: Transformation-Invariant Local Feature Networks for 3D LiDAR Object Detection with Unsupervised Pre-Training","date":"2024-08-25","arxiv_id":"2408.13902","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaocc-adaptive-resolution-occupancy","title":"AdaOcc: Adaptive-Resolution Occupancy Prediction","date":"2024-08-24","arxiv_id":"2408.13454","repositories_listed":0,"syntology":null},{"url":null,"slug":"mean-height-aided-post-processing-for","title":"Mean Height Aided Post-Processing for Pedestrian Detection","date":"2024-08-24","arxiv_id":"2408.13646","repositories_listed":0,"syntology":null},{"url":null,"slug":"mctr-multi-camera-tracking-transformer","title":"MCTR: Multi Camera Tracking Transformer","date":"2024-08-23","arxiv_id":"2408.13243","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetric-masking-strategy-enhances-the","title":"Symmetric masking strategy enhances the performance of Masked Image Modeling","date":"2024-08-23","arxiv_id":"2408.12772","repositories_listed":0,"syntology":null},{"url":null,"slug":"catfree3d-category-agnostic-3d-object","title":"CatFree3D: Category-agnostic 3D Object Detection with Diffusion","date":"2024-08-22","arxiv_id":"2408.12747","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-balanced-open-set-semi-supervised","title":"Class-balanced Open-set Semi-supervised Object Detection for Medical Images","date":"2024-08-22","arxiv_id":"2408.12355","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-parking-perception-by-multi-task","title":"Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers","date":"2024-08-22","arxiv_id":"2408.12575","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-cross-domain-problem-for-lidar","title":"Revisiting Cross-Domain Problem for LiDAR-based 3D Object Detection","date":"2024-08-22","arxiv_id":"2408.12708","repositories_listed":0,"syntology":null},{"url":null,"slug":"carla-drone-monocular-3d-object-detection","title":"CARLA Drone: Monocular 3D Object Detection from a Different Perspective","date":"2024-08-21","arxiv_id":"2408.11958","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-invariant-progressive-knowledge","title":"Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection","date":"2024-08-21","arxiv_id":"2408.11407","repositories_listed":0,"syntology":null},{"url":null,"slug":"sbdet-a-symmetry-breaking-object-detector-via","title":"SBDet: A Symmetry-Breaking Object Detector via Relaxed Rotation-Equivariance","date":"2024-08-21","arxiv_id":"2408.11760","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-data-augmentation-strategies","title":"A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection","date":"2024-08-20","arxiv_id":"2408.10940","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-in-industrial-machine-vision-a","title":"Generative AI in Industrial Machine Vision -- A Review","date":"2024-08-20","arxiv_id":"2408.10775","repositories_listed":0,"syntology":null},{"url":null,"slug":"just-a-hint-point-supervised-camouflaged","title":"Just a Hint: Point-Supervised Camouflaged Object Detection","date":"2024-08-20","arxiv_id":"2408.10777","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-potential-of-open-vocabulary-models","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","date":"2024-08-20","arxiv_id":"2408.11221","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-cod-sam-guided-unified-framework-for","title":"SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection","date":"2024-08-20","arxiv_id":"2408.10760","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-diffusion-for-guided-document-table","title":"Latent Diffusion for Guided Document Table Generation","date":"2024-08-19","arxiv_id":"2408.09800","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-superfluous-information-in","title":"Leveraging Superfluous Information in Contrastive Representation Learning","date":"2024-08-19","arxiv_id":"2408.10292","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacked-teacher-for-unsupervised","title":"Adversarial Attacked Teacher for Unsupervised Domain Adaptive Object Detection","date":"2024-08-18","arxiv_id":"2408.09431","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-recovering-network-for-temporal","title":"Boundary-Recovering Network for Temporal Action Detection","date":"2024-08-18","arxiv_id":"2408.09354","repositories_listed":0,"syntology":null},{"url":null,"slug":"yolov1-to-yolov10-the-fastest-and-most","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","date":"2024-08-18","arxiv_id":"2408.09332","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-guided-texture-diffusion-for-image","title":"Depth-guided Texture Diffusion for Image Semantic Segmentation","date":"2024-08-17","arxiv_id":"2408.09097","repositories_listed":0,"syntology":null},{"url":null,"slug":"gslamot-a-tracklet-and-query-graph-based","title":"GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System","date":"2024-08-17","arxiv_id":"2408.09191","repositories_listed":0,"syntology":null},{"url":null,"slug":"maskbev-towards-a-unified-framework-for-bev","title":"MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation","date":"2024-08-17","arxiv_id":"2408.09122","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-object-detection-with-hybrid","title":"Enhancing Object Detection with Hybrid dataset in Manufacturing Environments: Comparing Federated Learning to Conventional Techniques","date":"2024-08-16","arxiv_id":"2408.08974","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-relational-triple-extraction-with","title":"Multimodal Relational Triple Extraction with Query-based Entity Object Transformer","date":"2024-08-16","arxiv_id":"2408.08709","repositories_listed":0,"syntology":null},{"url":null,"slug":"tell-codec-what-worth-compressing","title":"Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs","date":"2024-08-16","arxiv_id":"2408.08575","repositories_listed":0,"syntology":null},{"url":null,"slug":"camoteacher-dual-rotation-consistency","title":"CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detection","date":"2024-08-15","arxiv_id":"2408.08050","repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-multimodal-compression-for-autonomous","title":"Learned Multimodal Compression for Autonomous Driving","date":"2024-08-15","arxiv_id":"2408.08211","repositories_listed":0,"syntology":null},{"url":null,"slug":"oc3d-weakly-supervised-outdoor-3d-object","title":"SC3D: Label-Efficient Outdoor 3D Object Detection via Single Click Annotation","date":"2024-08-15","arxiv_id":"2408.08092","repositories_listed":0,"syntology":null},{"url":null,"slug":"infra-yolo-efficient-neural-network-structure","title":"Infra-YOLO: Efficient Neural Network Structure with Model Compression for Real-Time Infrared Small Object Detection","date":"2024-08-14","arxiv_id":"2408.07455","repositories_listed":0,"syntology":null},{"url":"/paper/see-it-all-contextualized-late-aggregation","slug":"see-it-all-contextualized-late-aggregation","title":"See It All: Contextualized Late Aggregation for 3D Dense Captioning","date":"2024-08-14","arxiv_id":"2408.07648","repositories_listed":0,"syntology":null},{"url":null,"slug":"divide-and-conquer-improving-multi-camera-3d","title":"Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries","date":"2024-08-13","arxiv_id":"2408.06901","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-domain-shift-on-radar-based-3d","title":"Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions","date":"2024-08-13","arxiv_id":"2408.06772","repositories_listed":0,"syntology":null},{"url":"/paper/mv-detr-multi-modality-indoor-object","slug":"mv-detr-multi-modality-indoor-object","title":"MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers","date":"2024-08-13","arxiv_id":"2408.06604","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-model-for-interpretable-and","title":"Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces","date":"2024-08-13","arxiv_id":"2408.07146","repositories_listed":0,"syntology":null},{"url":null,"slug":"dpdetr-decoupled-position-detection","title":"DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection","date":"2024-08-12","arxiv_id":"2408.06123","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-disentanglement-for-low-light-image","title":"Latent Disentanglement for Low Light Image Enhancement","date":"2024-08-12","arxiv_id":"2408.06245","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-contrastive-adaptor-learning-for","title":"Multi-scale Contrastive Adaptor Learning for Segmenting Anything in Underperformed Scenes","date":"2024-08-12","arxiv_id":"2408.05936","repositories_listed":0,"syntology":null},{"url":null,"slug":"mv2dfusion-leveraging-modality-specific","title":"MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection","date":"2024-08-12","arxiv_id":"2408.05945","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-vision-transformers-with-data-free","title":"Optimizing Vision Transformers with Data-Free Knowledge Transfer","date":"2024-08-12","arxiv_id":"2408.05952","repositories_listed":0,"syntology":null},{"url":"/paper/weakly-supervised-video-anomaly-detection-and","slug":"weakly-supervised-video-anomaly-detection-and","title":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","date":"2024-08-12","arxiv_id":"2408.05905","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-bm3d-and-nbnet-a-comprehensive","title":"Evaluating BM3D and NBNet: A Comprehensive Study of Image Denoising Across Multiple Datasets","date":"2024-08-11","arxiv_id":"2408.05697","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-pavement-distress-detection-in","title":"Advancing Pavement Distress Detection in Developing Countries: A Novel Deep Learning Approach with Locally-Collected Datasets","date":"2024-08-10","arxiv_id":"2408.05649","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilated-convolution-with-learnable-spacings-2","title":"Dilated Convolution with Learnable Spacings","date":"2024-08-10","arxiv_id":"2408.06383","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recurrent-yolov8-based-framework-for-event","title":"A Recurrent YOLOv8-based framework for Event-Based Object Detection","date":"2024-08-09","arxiv_id":"2408.05321","repositories_listed":0,"syntology":null},{"url":null,"slug":"radarpillars-efficient-object-detection-from","title":"RadarPillars: Efficient Object Detection from 4D Radar Point Clouds","date":"2024-08-09","arxiv_id":"2408.05020","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-pixel-control-challenges-and","title":"Data-Driven Pixel Control: Challenges and Prospects","date":"2024-08-08","arxiv_id":"2408.04767","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-car-speed-using-object-detection","title":"Detecting Car Speed using Object Detection and Depth Estimation: A Deep Learning Framework","date":"2024-08-08","arxiv_id":"2408.04360","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-extremely-memory-efficient-cnns-for","title":"Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks","date":"2024-08-07","arxiv_id":"2408.03663","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02891","title":"Diverse Generation while Maintaining Semantic Coordination: A Diffusion-Based Data Augmentation Method for Object Detection","date":"2024-08-06","arxiv_id":"2408.02891","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-foundation-models-in-remote-sensing-a","title":"AI Foundation Models in Remote Sensing: A Survey","date":"2024-08-06","arxiv_id":"2408.03464","repositories_listed":0,"syntology":null}],"record_sha256":"18ff92f9c8ef3ebe8d3ac9c1ae071334184ea18766ac9a96fe5f46e57e2b58f5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}