{"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/15","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":15,"pages_in_order":110,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/task/object-detection/papers/16","papers":[{"url":"/paper/dreb-net-dual-stream-restoration-embedding","slug":"dreb-net-dual-stream-restoration-embedding","title":"DREB-Net: Dual-stream Restoration Embedding Blur-feature Fusion Network for High-mobility UAV Object Detection","date":"2024-10-23","arxiv_id":"2410.17822","repositories_listed":1,"syntology":null},{"url":"/paper/ovt-b-a-new-large-scale-benchmark-for-open","slug":"ovt-b-a-new-large-scale-benchmark-for-open","title":"OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking","date":"2024-10-23","arxiv_id":"2410.17534","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ovt-b-a-new-large-scale-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2410.17534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17534"}},"official":{"repos":["coo1sea/ovt-b-dataset"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/plantcamo-plant-camouflage-detection","slug":"plantcamo-plant-camouflage-detection","title":"PlantCamo: Plant Camouflage Detection","date":"2024-10-23","arxiv_id":"2410.17598","repositories_listed":1,"syntology":null},{"url":"/paper/yolov11-an-overview-of-the-key-architectural","slug":"yolov11-an-overview-of-the-key-architectural","title":"YOLOv11: An Overview of the Key Architectural Enhancements","date":"2024-10-23","arxiv_id":"2410.17725","repositories_listed":1,"syntology":null},{"url":"/paper/attriprompter-auto-prompting-with-attribute","slug":"attriprompter-auto-prompting-with-attribute","title":"AttriPrompter: Auto-Prompting with Attribute Semantics for Zero-shot Nuclei Detection via Visual-Language Pre-trained Models","date":"2024-10-22","arxiv_id":"2410.16820","repositories_listed":1,"syntology":null},{"url":"/paper/di-maskdino-a-joint-object-detection-and","slug":"di-maskdino-a-joint-object-detection-and","title":"DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model","date":"2024-10-22","arxiv_id":"2410.16707","repositories_listed":1,"syntology":null},{"url":"/paper/fire-and-smoke-detection-with-burning","slug":"fire-and-smoke-detection-with-burning","title":"Fire and Smoke Detection with Burning Intensity Representation","date":"2024-10-22","arxiv_id":"2410.16642","repositories_listed":1,"syntology":null},{"url":"/paper/griffon-g-bridging-vision-language-and-vision","slug":"griffon-g-bridging-vision-language-and-vision","title":"Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models","date":"2024-10-21","arxiv_id":"2410.16163","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-vs-closed-set-best-practice","slug":"open-vocabulary-vs-closed-set-best-practice","title":"Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability","date":"2024-10-20","arxiv_id":"2410.15315","repositories_listed":1,"syntology":null},{"url":"/paper/trackme-a-simple-and-effective-multiple","slug":"trackme-a-simple-and-effective-multiple","title":"TrackMe:A Simple and Effective Multiple Object Tracking Annotation Tool","date":"2024-10-20","arxiv_id":"2410.15518","repositories_listed":1,"syntology":null},{"url":"/paper/mambasod-dual-mamba-driven-cross-modal-fusion","slug":"mambasod-dual-mamba-driven-cross-modal-fusion","title":"MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detection","date":"2024-10-19","arxiv_id":"2410.15015","repositories_listed":1,"syntology":null},{"url":"/paper/part-whole-relational-fusion-towards-multi","slug":"part-whole-relational-fusion-towards-multi","title":"Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding","date":"2024-10-19","arxiv_id":"2410.14944","repositories_listed":1,"syntology":null},{"url":"/paper/multi-source-spatial-knowledge-understanding","slug":"multi-source-spatial-knowledge-understanding","title":"Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech","date":"2024-10-18","arxiv_id":"2410.14101","repositories_listed":1,"syntology":null},{"url":"/paper/context-infused-visual-grounding-for-art","slug":"context-infused-visual-grounding-for-art","title":"Context-Infused Visual Grounding for Art","date":"2024-10-16","arxiv_id":"2410.12369","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-infused-visual-grounding-for-art#ran","syntology_url":"https://syntology.ai/paper/2410.12369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12369"}},"official":{"repos":["selinakhan/CIGAr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-stereo-based-3d-object-detection","slug":"real-time-stereo-based-3d-object-detection","title":"Real-time Stereo-based 3D Object Detection for Streaming Perception","date":"2024-10-16","arxiv_id":"2410.12394","repositories_listed":1,"syntology":null},{"url":"/paper/cvcp-fusion-on-implicit-depth-estimation-for","slug":"cvcp-fusion-on-implicit-depth-estimation-for","title":"CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Prediction","date":"2024-10-15","arxiv_id":"2410.11211","repositories_listed":1,"syntology":null},{"url":"/paper/fractal-calibration-for-long-tailed-object","slug":"fractal-calibration-for-long-tailed-object","title":"Fractal Calibration for long-tailed object detection","date":"2024-10-15","arxiv_id":"2410.11774","repositories_listed":1,"syntology":null},{"url":"/paper/multiview-scene-graph","slug":"multiview-scene-graph","title":"Multiview Scene Graph","date":"2024-10-15","arxiv_id":"2410.11187","repositories_listed":1,"syntology":{"n":37,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":20,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":37,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/multiview-scene-graph#ran","syntology_url":"https://syntology.ai/paper/2410.11187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11187"}},"official":{"repos":["ai4ce/MSG"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":20,"ran_from_kinds":["official"]}}},{"url":"/paper/open-world-object-detection-a-survey","slug":"open-world-object-detection-a-survey","title":"Open World Object Detection: A Survey","date":"2024-10-15","arxiv_id":"2410.11301","repositories_listed":1,"syntology":null},{"url":"/paper/teocc-radar-camera-multi-modal-occupancy","slug":"teocc-radar-camera-multi-modal-occupancy","title":"TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement","date":"2024-10-15","arxiv_id":"2410.11228","repositories_listed":1,"syntology":null},{"url":"/paper/globalmamba-global-image-serialization-for","slug":"globalmamba-global-image-serialization-for","title":"GlobalMamba: Global Image Serialization for Vision Mamba","date":"2024-10-14","arxiv_id":"2410.10316","repositories_listed":1,"syntology":null},{"url":"/paper/out-of-bounding-box-triggers-a-stealthy","slug":"out-of-bounding-box-triggers-a-stealthy","title":"Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors","date":"2024-10-14","arxiv_id":"2410.10091","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/out-of-bounding-box-triggers-a-stealthy#ran","syntology_url":"https://syntology.ai/paper/2410.10091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10091"}},"official":{"repos":["lintotao/out-of-bbox-attack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rosar-an-adversarial-re-training-framework","slug":"rosar-an-adversarial-re-training-framework","title":"ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection","date":"2024-10-14","arxiv_id":"2410.10554","repositories_listed":1,"syntology":null},{"url":"/paper/v2m-visual-2-dimensional-mamba-for-image","slug":"v2m-visual-2-dimensional-mamba-for-image","title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","date":"2024-10-14","arxiv_id":"2410.10382","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-intelligent-video-surveillance","slug":"distributed-intelligent-video-surveillance","title":"Distributed Intelligent Video Surveillance for Early Armed Robbery Detection based on Deep Learning","date":"2024-10-13","arxiv_id":"2410.09731","repositories_listed":1,"syntology":null},{"url":"/paper/loli-street-benchmarking-low-light-image","slug":"loli-street-benchmarking-low-light-image","title":"LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond","date":"2024-10-13","arxiv_id":"2410.09831","repositories_listed":1,"syntology":null},{"url":"/paper/da-ada-learning-domain-aware-adapter-for","slug":"da-ada-learning-domain-aware-adapter-for","title":"DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection","date":"2024-10-11","arxiv_id":"2410.09004","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/da-ada-learning-domain-aware-adapter-for#ran","syntology_url":"https://syntology.ai/paper/2410.09004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09004"}},"official":{"repos":["therock90421/da-ada"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/debiformer-vision-transformer-with-deformable","slug":"debiformer-vision-transformer-with-deformable","title":"DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention","date":"2024-10-11","arxiv_id":"2410.08582","repositories_listed":1,"syntology":null},{"url":"/paper/hespi-a-pipeline-for-automatically-detecting","slug":"hespi-a-pipeline-for-automatically-detecting","title":"Hespi: A pipeline for automatically detecting information from hebarium specimen sheets","date":"2024-10-11","arxiv_id":"2410.08740","repositories_listed":1,"syntology":null},{"url":"/paper/lime-eval-rethinking-low-light-image","slug":"lime-eval-rethinking-low-light-image","title":"LIME-Eval: Rethinking Low-light Image Enhancement Evaluation via Object Detection","date":"2024-10-11","arxiv_id":"2410.08810","repositories_listed":1,"syntology":null},{"url":"/paper/pointobb-v2-towards-simpler-faster-and","slug":"pointobb-v2-towards-simpler-faster-and","title":"PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection","date":"2024-10-10","arxiv_id":"2410.08210","repositories_listed":1,"syntology":null},{"url":"/paper/quadmamba-learning-quadtree-based-selective","slug":"quadmamba-learning-quadtree-based-selective","title":"QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model","date":"2024-10-09","arxiv_id":"2410.06806","repositories_listed":1,"syntology":null},{"url":"/paper/suranet-surrounding-aware-network-for","slug":"suranet-surrounding-aware-network-for","title":"SurANet: Surrounding-Aware Network for Concealed Object Detection via Highly-Efficient Interactive Contrastive Learning Strategy","date":"2024-10-09","arxiv_id":"2410.06842","repositories_listed":1,"syntology":null},{"url":"/paper/pixlens-a-novel-framework-for-disentangled","slug":"pixlens-a-novel-framework-for-disentangled","title":"PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAM","date":"2024-10-08","arxiv_id":"2410.05710","repositories_listed":1,"syntology":null},{"url":"/paper/sia-ovd-shape-invariant-adapter-for-bridging","slug":"sia-ovd-shape-invariant-adapter-for-bridging","title":"SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection","date":"2024-10-08","arxiv_id":"2410.05650","repositories_listed":1,"syntology":null},{"url":"/paper/underwater-object-detection-in-the-era-of","slug":"underwater-object-detection-in-the-era-of","title":"Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future","date":"2024-10-08","arxiv_id":"2410.05577","repositories_listed":1,"syntology":null},{"url":"/paper/unobserved-object-detection-using-generative","slug":"unobserved-object-detection-using-generative","title":"Believing is Seeing: Unobserved Object Detection using Generative Models","date":"2024-10-08","arxiv_id":"2410.05869","repositories_listed":1,"syntology":null},{"url":"/paper/improved-detection-of-discarded-fish-species","slug":"improved-detection-of-discarded-fish-species","title":"Improved detection of discarded fish species through BoxAL active learning","date":"2024-10-07","arxiv_id":"2410.04880","repositories_listed":1,"syntology":null},{"url":"/paper/learning-de-biased-representations-for-remote","slug":"learning-de-biased-representations-for-remote","title":"Learning De-Biased Representations for Remote-Sensing Imagery","date":"2024-10-06","arxiv_id":"2410.04546","repositories_listed":1,"syntology":null},{"url":"/paper/cross-resolution-encoding-decoding-for","slug":"cross-resolution-encoding-decoding-for","title":"Cross Resolution Encoding-Decoding For Detection Transformers","date":"2024-10-05","arxiv_id":"2410.04088","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-capsule-routing-towards-part-whole","slug":"mamba-capsule-routing-towards-part-whole","title":"Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection","date":"2024-10-05","arxiv_id":"2410.03987","repositories_listed":1,"syntology":null},{"url":"/paper/stone-a-submodular-optimization-framework-for","slug":"stone-a-submodular-optimization-framework-for","title":"STONE: A Submodular Optimization Framework for Active 3D Object Detection","date":"2024-10-04","arxiv_id":"2410.03918","repositories_listed":1,"syntology":null},{"url":"/paper/synco-synthetic-hard-negatives-in-contrastive","slug":"synco-synthetic-hard-negatives-in-contrastive","title":"SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations","date":"2024-10-03","arxiv_id":"2410.02401","repositories_listed":1,"syntology":null},{"url":"/paper/3dgs-det-empower-3d-gaussian-splatting-with","slug":"3dgs-det-empower-3d-gaussian-splatting-with","title":"3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection","date":"2024-10-02","arxiv_id":"2410.01647","repositories_listed":1,"syntology":null},{"url":"/paper/a-versatile-machine-learning-workflow-for","slug":"a-versatile-machine-learning-workflow-for","title":"A versatile machine learning workflow for high-throughput analysis of supported metal catalyst particles","date":"2024-10-02","arxiv_id":"2410.01213","repositories_listed":1,"syntology":null},{"url":"/paper/perceptual-piercing-human-visual-cue-based","slug":"perceptual-piercing-human-visual-cue-based","title":"Perceptual Piercing: Human Visual Cue-based Object Detection in Low Visibility Conditions","date":"2024-10-02","arxiv_id":"2410.01225","repositories_listed":1,"syntology":null},{"url":"/paper/descriptor-face-detection-dataset-for","slug":"descriptor-face-detection-dataset-for","title":"Descriptor: Face Detection Dataset for Programmable Threshold-Based Sparse-Vision","date":"2024-10-01","arxiv_id":"2410.00368","repositories_listed":1,"syntology":null},{"url":"/paper/fce-yolov8-yolov8-with-feature-context","slug":"fce-yolov8-yolov8-with-feature-context","title":"Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images","date":"2024-10-01","arxiv_id":"2410.01031","repositories_listed":1,"syntology":null},{"url":"/paper/ossa-unsupervised-one-shot-style-adaptation","slug":"ossa-unsupervised-one-shot-style-adaptation","title":"OSSA: Unsupervised One-Shot Style Adaptation","date":"2024-10-01","arxiv_id":"2410.00900","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-non-maximum-suppression-a-graph","slug":"accelerating-non-maximum-suppression-a-graph","title":"Accelerating Non-Maximum Suppression: A Graph Theory Perspective","date":"2024-09-30","arxiv_id":"2409.20520","repositories_listed":1,"syntology":null},{"url":"/paper/daocc-3d-object-detection-assisted-multi","slug":"daocc-3d-object-detection-assisted-multi","title":"DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction","date":"2024-09-30","arxiv_id":"2409.19972","repositories_listed":1,"syntology":null},{"url":"/paper/hazydet-open-source-benchmark-for-drone-view","slug":"hazydet-open-source-benchmark-for-drone-view","title":"HazyDet: Open-source Benchmark for Drone-view Object Detection with Depth-cues in Hazy Scenes","date":"2024-09-30","arxiv_id":"2409.19833","repositories_listed":1,"syntology":null},{"url":"/paper/tsdetector-temporal-spatial-self-correction","slug":"tsdetector-temporal-spatial-self-correction","title":"TSdetector: Temporal-Spatial Self-correction Collaborative Learning for Colonoscopy Video Detection","date":"2024-09-30","arxiv_id":"2409.19983","repositories_listed":1,"syntology":null},{"url":"/paper/orientedformer-an-end-to-end-transformer-1","slug":"orientedformer-an-end-to-end-transformer-1","title":"OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images","date":"2024-09-29","arxiv_id":"2409.19648","repositories_listed":1,"syntology":null},{"url":"/paper/a-confidence-aware-matching-strategy-for","slug":"a-confidence-aware-matching-strategy-for","title":"A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking","date":"2024-09-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-unified-architecture-for-low-shot","slug":"a-novel-unified-architecture-for-low-shot","title":"A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation","date":"2024-09-27","arxiv_id":"2409.18686","repositories_listed":1,"syntology":null},{"url":"/paper/bitq-tailoring-block-floating-point-precision","slug":"bitq-tailoring-block-floating-point-precision","title":"BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices","date":"2024-09-25","arxiv_id":"2409.17093","repositories_listed":1,"syntology":null},{"url":"/paper/pix2next-leveraging-vision-foundation-models","slug":"pix2next-leveraging-vision-foundation-models","title":"Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation","date":"2024-09-25","arxiv_id":"2409.16706","repositories_listed":1,"syntology":null},{"url":"/paper/source-free-domain-adaptation-for-yolo-object","slug":"source-free-domain-adaptation-for-yolo-object","title":"Source-Free Domain Adaptation for YOLO Object Detection","date":"2024-09-25","arxiv_id":"2409.16538","repositories_listed":1,"syntology":null},{"url":"/paper/tsbp-improving-object-detection-in-histology","slug":"tsbp-improving-object-detection-in-histology","title":"TSBP: Improving Object Detection in Histology Images via Test-time Self-guided Bounding-box Propagation","date":"2024-09-25","arxiv_id":"2409.16678","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-open-source-ultrasound-dataset-with","slug":"a-novel-open-source-ultrasound-dataset-with","title":"A novel open-source ultrasound dataset with deep learning benchmarks for spinal cord injury localization and anatomical segmentation","date":"2024-09-24","arxiv_id":"2409.16441","repositories_listed":1,"syntology":null},{"url":"/paper/neuromorphic-drone-detection-an-event-rgb","slug":"neuromorphic-drone-detection-an-event-rgb","title":"Neuromorphic Drone Detection: an Event-RGB Multimodal Approach","date":"2024-09-24","arxiv_id":"2409.16099","repositories_listed":1,"syntology":null},{"url":"/paper/pdt-uav-target-detection-dataset-for-pests","slug":"pdt-uav-target-detection-dataset-for-pests","title":"PDT: Uav Target Detection Dataset for Pests and Diseases Tree","date":"2024-09-24","arxiv_id":"2409.15679","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-robotics-dataset-and-benchmark-for","slug":"tiny-robotics-dataset-and-benchmark-for","title":"Tiny Robotics Dataset and Benchmark for Continual Object Detection","date":"2024-09-24","arxiv_id":"2409.16215","repositories_listed":1,"syntology":null},{"url":"/paper/msdet-receptive-field-enhanced-multiscale","slug":"msdet-receptive-field-enhanced-multiscale","title":"MSDet: Receptive Field Enhanced Multiscale Detection for Tiny Pulmonary Nodule","date":"2024-09-21","arxiv_id":"2409.14028","repositories_listed":1,"syntology":null},{"url":"/paper/potato-a-dataset-for-analyzing-polarimetric","slug":"potato-a-dataset-for-analyzing-polarimetric","title":"PoTATO: A Dataset for Analyzing Polarimetric Traces of Afloat Trash Objects","date":"2024-09-19","arxiv_id":"2409.12659","repositories_listed":1,"syntology":null},{"url":"/paper/rocktrack-a-3d-robust-multi-camera-ken-multi","slug":"rocktrack-a-3d-robust-multi-camera-ken-multi","title":"RockTrack: A 3D Robust Multi-Camera-Ken Multi-Object Tracking Framework","date":"2024-09-18","arxiv_id":"2409.11749","repositories_listed":1,"syntology":null},{"url":"/paper/stcmot-spatio-temporal-cohesion-learning-for","slug":"stcmot-spatio-temporal-cohesion-learning-for","title":"STCMOT: Spatio-Temporal Cohesion Learning for UAV-Based Multiple Object Tracking","date":"2024-09-17","arxiv_id":"2409.11234","repositories_listed":1,"syntology":null},{"url":"/paper/ultimatedo-an-efficient-framework-to-marry","slug":"ultimatedo-an-efficient-framework-to-marry","title":"UltimateDO: An Efficient Framework to Marry Occupancy Prediction with 3D Object Detection via Channel2height","date":"2024-09-17","arxiv_id":"2409.11160","repositories_listed":1,"syntology":null},{"url":"/paper/valo-a-versatile-anytime-framework-for-lidar","slug":"valo-a-versatile-anytime-framework-for-lidar","title":"VALO: A Versatile Anytime Framework for LiDAR-based Object Detection Deep Neural Networks","date":"2024-09-17","arxiv_id":"2409.11542","repositories_listed":1,"syntology":null},{"url":"/paper/comamba-real-time-cooperative-perception","slug":"comamba-real-time-cooperative-perception","title":"CoMamba: Real-time Cooperative Perception Unlocked with State Space Models","date":"2024-09-16","arxiv_id":"2409.10699","repositories_listed":1,"syntology":null},{"url":"/paper/glconet-learning-multi-source-perception","slug":"glconet-learning-multi-source-perception","title":"GLCONet: Learning Multi-source Perception Representation for Camouflaged Object Detection","date":"2024-09-15","arxiv_id":"2409.09588","repositories_listed":1,"syntology":null},{"url":"/paper/sparx-a-sparse-cross-layer-connection","slug":"sparx-a-sparse-cross-layer-connection","title":"SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks","date":"2024-09-15","arxiv_id":"2409.09649","repositories_listed":1,"syntology":null},{"url":"/paper/label-convergence-defining-an-upper","slug":"label-convergence-defining-an-upper","title":"Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations","date":"2024-09-14","arxiv_id":"2409.09412","repositories_listed":1,"syntology":null},{"url":"/paper/nbbox-noisy-bounding-box-improves-remote","slug":"nbbox-noisy-bounding-box-improves-remote","title":"NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection","date":"2024-09-14","arxiv_id":"2409.09424","repositories_listed":1,"syntology":null},{"url":"/paper/one-missing-piece-in-vision-and-language-a","slug":"one-missing-piece-in-vision-and-language-a","title":"One missing piece in Vision and Language: A Survey on Comics Understanding","date":"2024-09-14","arxiv_id":"2409.09502","repositories_listed":1,"syntology":null},{"url":"/paper/rt-detrv3-real-time-end-to-end-object","slug":"rt-detrv3-real-time-end-to-end-object","title":"RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision","date":"2024-09-13","arxiv_id":"2409.08475","repositories_listed":1,"syntology":null},{"url":"/paper/enact-entropy-based-clustering-of-attention","slug":"enact-entropy-based-clustering-of-attention","title":"ENACT: Entropy-based Clustering of Attention Input for Improving the Computational Performance of Object Detection Transformers","date":"2024-09-11","arxiv_id":"2409.07541","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/enact-entropy-based-clustering-of-attention#ran","syntology_url":"https://syntology.ai/paper/2409.07541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07541"}},"official":{"repos":["gsavathrakis/enact"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-self-supervised-learning-with","slug":"cross-modal-self-supervised-learning-with","title":"Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point Clouds","date":"2024-09-10","arxiv_id":"2409.06827","repositories_listed":1,"syntology":null},{"url":"/paper/distribution-discrepancy-and-feature","slug":"distribution-discrepancy-and-feature","title":"Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection","date":"2024-09-09","arxiv_id":"2409.05425","repositories_listed":1,"syntology":null},{"url":"/paper/lerojd-lidar-extended-radar-only-object","slug":"lerojd-lidar-extended-radar-only-object","title":"LEROjD: Lidar Extended Radar-Only Object Detection","date":"2024-09-09","arxiv_id":"2409.05564","repositories_listed":1,"syntology":null},{"url":"/paper/a-low-computational-video-synopsis-framework","slug":"a-low-computational-video-synopsis-framework","title":"A Low-Computational Video Synopsis Framework with a Standard Dataset","date":"2024-09-08","arxiv_id":"2409.05230","repositories_listed":1,"syntology":null},{"url":"/paper/can-ood-object-detectors-learn-from","slug":"can-ood-object-detectors-learn-from","title":"Can OOD Object Detectors Learn from Foundation Models?","date":"2024-09-08","arxiv_id":"2409.05162","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-ood-object-detectors-learn-from#ran","syntology_url":"https://syntology.ai/paper/2409.05162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05162"}},"official":{"repos":["cvmi-lab/syncood"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-v2x-a-large-scale-multi-modal-multi","slug":"multi-v2x-a-large-scale-multi-modal-multi","title":"Multi-V2X: A Large Scale Multi-modal Multi-penetration-rate Dataset for Cooperative Perception","date":"2024-09-08","arxiv_id":"2409.04980","repositories_listed":1,"syntology":null},{"url":"/paper/visual-grounding-with-multi-modal-conditional","slug":"visual-grounding-with-multi-modal-conditional","title":"Visual Grounding with Multi-modal Conditional Adaptation","date":"2024-09-08","arxiv_id":"2409.04999","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visual-grounding-with-multi-modal-conditional#ran","syntology_url":"https://syntology.ai/paper/2409.04999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04999"}},"official":{"repos":["mr-bigworth/mmca"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ssfam-scribble-supervised-salient-object","slug":"ssfam-scribble-supervised-salient-object","title":"SSFam: Scribble Supervised Salient Object Detection Family","date":"2024-09-07","arxiv_id":"2409.04817","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-power-of-generic-segmentation","slug":"unleashing-the-power-of-generic-segmentation","title":"Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection","date":"2024-09-07","arxiv_id":"2409.04714","repositories_listed":1,"syntology":null},{"url":"/paper/unidet3d-multi-dataset-indoor-3d-object","slug":"unidet3d-multi-dataset-indoor-3d-object","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","date":"2024-09-06","arxiv_id":"2409.04234","repositories_listed":1,"syntology":null},{"url":"/paper/lowformer-hardware-efficient-design-for","slug":"lowformer-hardware-efficient-design-for","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","date":"2024-09-05","arxiv_id":"2409.03460","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lowformer-hardware-efficient-design-for#ran","syntology_url":"https://syntology.ai/paper/2409.03460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03460"}},"official":{"repos":["altair199797/lowformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/training-free-conversion-of-pretrained-anns","slug":"training-free-conversion-of-pretrained-anns","title":"Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications","date":"2024-09-05","arxiv_id":"2409.03368","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/training-free-conversion-of-pretrained-anns#ran","syntology_url":"https://syntology.ai/paper/2409.03368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03368"}},"official":{"repos":["putshua/inference-scale-ann-snn"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/boundless-generating-photorealistic-synthetic","slug":"boundless-generating-photorealistic-synthetic","title":"Boundless: Generating Photorealistic Synthetic Data for Object Detection in Urban Streetscapes","date":"2024-09-04","arxiv_id":"2409.03022","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-dynamic-scale-aware-fusion","slug":"real-time-dynamic-scale-aware-fusion","title":"Real-Time Dynamic Scale-Aware Fusion Detection Network: Take Road Damage Detection as an example","date":"2024-09-04","arxiv_id":"2409.02546","repositories_listed":1,"syntology":null},{"url":"/paper/tp-gmot-tracking-generic-multiple-object-by","slug":"tp-gmot-tracking-generic-multiple-object-by","title":"TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT","date":"2024-09-04","arxiv_id":"2409.02490","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-and-comparison-of-visual-language","slug":"evaluation-and-comparison-of-visual-language","title":"Evaluation and Comparison of Visual Language Models for Transportation Engineering Problems","date":"2024-09-03","arxiv_id":"2409.02278","repositories_listed":1,"syntology":null},{"url":"/paper/frequency-spatial-entanglement-learning-for","slug":"frequency-spatial-entanglement-learning-for","title":"Frequency-Spatial Entanglement Learning for Camouflaged Object Detection","date":"2024-09-03","arxiv_id":"2409.01686","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/frequency-spatial-entanglement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2409.01686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01686"}},"official":{"repos":["csysi/fsel"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/geobev-learning-geometric-bev-representation","slug":"geobev-learning-geometric-bev-representation","title":"GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection","date":"2024-09-03","arxiv_id":"2409.01816","repositories_listed":1,"syntology":null},{"url":"/paper/k-origins-better-colour-quantification-for","slug":"k-origins-better-colour-quantification-for","title":"K-Origins: Better Colour Quantification for Neural Networks","date":"2024-09-03","arxiv_id":"2409.02281","repositories_listed":1,"syntology":null},{"url":"/paper/latent-distillation-for-continual-object","slug":"latent-distillation-for-continual-object","title":"Latent Distillation for Continual Object Detection at the Edge","date":"2024-09-03","arxiv_id":"2409.01872","repositories_listed":1,"syntology":null},{"url":"/paper/kvasir-vqa-a-text-image-pair-gi-tract-dataset","slug":"kvasir-vqa-a-text-image-pair-gi-tract-dataset","title":"Kvasir-VQA: A Text-Image Pair GI Tract Dataset","date":"2024-09-02","arxiv_id":"2409.01437","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/kvasir-vqa-a-text-image-pair-gi-tract-dataset#ran","syntology_url":"https://syntology.ai/paper/2409.01437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01437"}},"official":{"repos":["simula/Kvasir-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/real-time-multi-scene-visibility-enhancement","slug":"real-time-multi-scene-visibility-enhancement","title":"Real-Time Multi-Scene Visibility Enhancement for Promoting Navigational Safety of Vessels Under Complex Weather Conditions","date":"2024-09-02","arxiv_id":"2409.01500","repositories_listed":1,"syntology":null}],"record_sha256":"0c919dbe29c40bf47f7be9d8678247cdd6c99983a58132679d52795d08327119","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}