{"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/17","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":17,"pages_in_order":110,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/task/object-detection/papers/18","papers":[{"url":"/paper/cerberusdet-unified-multi-task-object","slug":"cerberusdet-unified-multi-task-object","title":"CerberusDet: Unified Multi-Dataset Object Detection","date":"2024-07-17","arxiv_id":"2407.12632","repositories_listed":1,"syntology":null},{"url":"/paper/colormae-exploring-data-independent-masking","slug":"colormae-exploring-data-independent-masking","title":"ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders","date":"2024-07-17","arxiv_id":"2407.13036","repositories_listed":1,"syntology":null},{"url":"/paper/embracing-events-and-frames-with-hierarchical","slug":"embracing-events-and-frames-with-hierarchical","title":"Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection","date":"2024-07-17","arxiv_id":"2407.12582","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":0,"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/embracing-events-and-frames-with-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2407.12582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12582"}},"official":{"repos":["hucaofighting/frn"],"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/enhancing-wrist-abnormality-detection-with","slug":"enhancing-wrist-abnormality-detection-with","title":"Enhancing Wrist Fracture Detection with YOLO","date":"2024-07-17","arxiv_id":"2407.12597","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-deeper-segment-anything-model-with","slug":"exploring-deeper-segment-anything-model-with","title":"Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection","date":"2024-07-17","arxiv_id":"2407.12339","repositories_listed":1,"syntology":null},{"url":"/paper/glare-low-light-image-enhancement-via","slug":"glare-low-light-image-enhancement-via","title":"GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval","date":"2024-07-17","arxiv_id":"2407.12431","repositories_listed":1,"syntology":null},{"url":"/paper/weighting-pseudo-labels-via-high-activation","slug":"weighting-pseudo-labels-via-high-activation","title":"Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation","date":"2024-07-17","arxiv_id":"2407.12630","repositories_listed":1,"syntology":null},{"url":"/paper/bridge-past-and-future-overcoming-information","slug":"bridge-past-and-future-overcoming-information","title":"Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection","date":"2024-07-16","arxiv_id":"2407.11499","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bridge-past-and-future-overcoming-information#ran","syntology_url":"https://syntology.ai/paper/2407.11499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11499"}},"official":{"repos":["isee-laboratory/bpf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/crowd-sam-sam-as-a-smart-annotator-for-object","slug":"crowd-sam-sam-as-a-smart-annotator-for-object","title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","date":"2024-07-16","arxiv_id":"2407.11464","repositories_listed":1,"syntology":null},{"url":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lami-detr-open-vocabulary-detection-with#ran","syntology_url":"https://syntology.ai/paper/2407.11335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11335"}},"official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tcformer-visual-recognition-via-token","slug":"tcformer-visual-recognition-via-token","title":"TCFormer: Visual Recognition via Token Clustering Transformer","date":"2024-07-16","arxiv_id":"2407.11321","repositories_listed":1,"syntology":null},{"url":"/paper/open-object-wise-position-embedding-for-multi","slug":"open-object-wise-position-embedding-for-multi","title":"OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection","date":"2024-07-15","arxiv_id":"2407.10753","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/open-object-wise-position-embedding-for-multi#ran","syntology_url":"https://syntology.ai/paper/2407.10753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10753"}},"official":{"repos":["AlmoonYsl/OPEN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/openpsg-open-set-panoptic-scene-graph","slug":"openpsg-open-set-panoptic-scene-graph","title":"OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models","date":"2024-07-15","arxiv_id":"2407.11213","repositories_listed":1,"syntology":null},{"url":"/paper/ovlw-detr-open-vocabulary-light-weighted","slug":"ovlw-detr-open-vocabulary-light-weighted","title":"OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer","date":"2024-07-15","arxiv_id":"2407.10655","repositories_listed":1,"syntology":null},{"url":"/paper/repvf-a-unified-vector-fields-representation","slug":"repvf-a-unified-vector-fields-representation","title":"RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception","date":"2024-07-15","arxiv_id":"2407.10876","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/repvf-a-unified-vector-fields-representation#ran","syntology_url":"https://syntology.ai/paper/2407.10876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10876"}},"official":{"repos":["jbji/repvf"],"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/augmented-neural-fine-tuning-for-efficient","slug":"augmented-neural-fine-tuning-for-efficient","title":"Augmented Neural Fine-Tuning for Efficient Backdoor Purification","date":"2024-07-14","arxiv_id":"2407.10052","repositories_listed":1,"syntology":null},{"url":"/paper/fsd-bev-foreground-self-distillation-for","slug":"fsd-bev-foreground-self-distillation-for","title":"FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection","date":"2024-07-14","arxiv_id":"2407.10135","repositories_listed":1,"syntology":null},{"url":"/paper/labeldistill-label-guided-cross-modal","slug":"labeldistill-label-guided-cross-modal","title":"LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection","date":"2024-07-14","arxiv_id":"2407.10164","repositories_listed":1,"syntology":null},{"url":"/paper/plain-det-a-plain-multi-dataset-object","slug":"plain-det-a-plain-multi-dataset-object","title":"Plain-Det: A Plain Multi-Dataset Object Detector","date":"2024-07-14","arxiv_id":"2407.10083","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/plain-det-a-plain-multi-dataset-object#ran","syntology_url":"https://syntology.ai/paper/2407.10083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10083"}},"official":{"repos":["chengshiest/plain-det"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/shape2scene-3d-scene-representation-learning","slug":"shape2scene-3d-scene-representation-learning","title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","date":"2024-07-14","arxiv_id":"2407.10200","repositories_listed":1,"syntology":null},{"url":"/paper/when-pedestrian-detection-meets-multi-modal","slug":"when-pedestrian-detection-meets-multi-modal","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","date":"2024-07-14","arxiv_id":"2407.10125","repositories_listed":1,"syntology":null},{"url":"/paper/mutdet-mutually-optimizing-pre-training-for","slug":"mutdet-mutually-optimizing-pre-training-for","title":"MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detection","date":"2024-07-13","arxiv_id":"2407.09920","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mutdet-mutually-optimizing-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2407.09920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09920"}},"official":{"repos":["floatingstarz/mutdet"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-3d-object-detection-with-1","slug":"semi-supervised-3d-object-detection-with-1","title":"Semi-supervised 3D Object Detection with PatchTeacher and PillarMix","date":"2024-07-13","arxiv_id":"2407.09787","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/semi-supervised-3d-object-detection-with-1#ran","syntology_url":"https://syntology.ai/paper/2407.09787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09787"}},"official":{"repos":["littlepey/ptpm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dart-an-automated-end-to-end-object-detection","slug":"dart-an-automated-end-to-end-object-detection","title":"DART: An Automated End-to-End Object Detection Pipeline with Data Diversification, Open-Vocabulary Bounding Box Annotation, Pseudo-Label Review, and Model Training","date":"2024-07-12","arxiv_id":"2407.09174","repositories_listed":1,"syntology":null},{"url":"/paper/dronemot-drone-based-multi-object-tracking","slug":"dronemot-drone-based-multi-object-tracking","title":"DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objects","date":"2024-07-12","arxiv_id":"2407.09051","repositories_listed":1,"syntology":null},{"url":"/paper/approaching-outside-scaling-unsupervised-3d","slug":"approaching-outside-scaling-unsupervised-3d","title":"Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene","date":"2024-07-11","arxiv_id":"2407.08569","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/approaching-outside-scaling-unsupervised-3d#ran","syntology_url":"https://syntology.ai/paper/2407.08569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08569"}},"official":{"repos":["ruiyang-061x/lise"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/dmm-disparity-guided-multispectral-mamba-for","slug":"dmm-disparity-guided-multispectral-mamba-for","title":"DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing","date":"2024-07-11","arxiv_id":"2407.08132","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-to-effectively-attain","slug":"knowledge-distillation-to-effectively-attain","title":"Knowledge distillation to effectively attain both region-of-interest and global semantics from an image where multiple objects appear","date":"2024-07-11","arxiv_id":"2407.08257","repositories_listed":1,"syntology":null},{"url":"/paper/projecting-points-to-axes-oriented-object","slug":"projecting-points-to-axes-oriented-object","title":"Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation","date":"2024-07-11","arxiv_id":"2407.08489","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-detector-combination-for-object","slug":"bayesian-detector-combination-for-object","title":"Bayesian Detector Combination for Object Detection with Crowdsourced Annotations","date":"2024-07-10","arxiv_id":"2407.07958","repositories_listed":1,"syntology":null},{"url":"/paper/ov-dino-unified-open-vocabulary-detection","slug":"ov-dino-unified-open-vocabulary-detection","title":"OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion","date":"2024-07-10","arxiv_id":"2407.07844","repositories_listed":1,"syntology":null},{"url":"/paper/simplifying-source-free-domain-adaptation-for","slug":"simplifying-source-free-domain-adaptation-for","title":"Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights","date":"2024-07-10","arxiv_id":"2407.07586","repositories_listed":1,"syntology":null},{"url":"/paper/cola-conditional-dropout-and-language-driven","slug":"cola-conditional-dropout-and-language-driven","title":"CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection","date":"2024-07-09","arxiv_id":"2407.06780","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cola-conditional-dropout-and-language-driven#ran","syntology_url":"https://syntology.ai/paper/2407.06780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06780"}},"official":{"repos":["ssecv/CoLA"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cue-point-estimation-using-object-detection","slug":"cue-point-estimation-using-object-detection","title":"Cue Point Estimation using Object Detection","date":"2024-07-09","arxiv_id":"2407.06823","repositories_listed":1,"syntology":null},{"url":"/paper/multi-clue-consistency-learning-to-bridge","slug":"multi-clue-consistency-learning-to-bridge","title":"Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection","date":"2024-07-08","arxiv_id":"2407.05909","repositories_listed":1,"syntology":null},{"url":"/paper/short-term-object-interaction-anticipation","slug":"short-term-object-interaction-anticipation","title":"Short-term Object Interaction Anticipation with Disentangled Object Detection @ Ego4D Short Term Object Interaction Anticipation Challenge","date":"2024-07-08","arxiv_id":"2407.05713","repositories_listed":1,"syntology":null},{"url":"/paper/the-dynamic-net-architecture-learning-robust","slug":"the-dynamic-net-architecture-learning-robust","title":"The Cooperative Network Architecture: Learning Structured Networks as Representation of Sensory Patterns","date":"2024-07-08","arxiv_id":"2407.05650","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-test-time-domain-adaptation","slug":"weakly-supervised-test-time-domain-adaptation","title":"Weakly Supervised Test-Time Domain Adaptation for Object Detection","date":"2024-07-08","arxiv_id":"2407.05607","repositories_listed":1,"syntology":null},{"url":"/paper/clamp-vit-contrastive-data-free-learning-for","slug":"clamp-vit-contrastive-data-free-learning-for","title":"CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs","date":"2024-07-07","arxiv_id":"2407.05266","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/clamp-vit-contrastive-data-free-learning-for#ran","syntology_url":"https://syntology.ai/paper/2407.05266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05266"}},"official":{"repos":["georgia-tech-synergy-lab/clamp-vit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/scsa-exploring-the-synergistic-effects","slug":"scsa-exploring-the-synergistic-effects","title":"SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention","date":"2024-07-06","arxiv_id":"2407.05128","repositories_listed":1,"syntology":null},{"url":"/paper/multi-branch-auxiliary-fusion-yolo-with-re","slug":"multi-branch-auxiliary-fusion-yolo-with-re","title":"Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection","date":"2024-07-05","arxiv_id":"2407.04381","repositories_listed":1,"syntology":null},{"url":"/paper/comix-a-comprehensive-benchmark-for-multi","slug":"comix-a-comprehensive-benchmark-for-multi","title":"CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding","date":"2024-07-04","arxiv_id":"2407.03550","repositories_listed":1,"syntology":null},{"url":"/paper/detect-closer-surfaces-that-can-be-seen-new","slug":"detect-closer-surfaces-that-can-be-seen-new","title":"Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detection","date":"2024-07-04","arxiv_id":"2407.04061","repositories_listed":1,"syntology":null},{"url":"/paper/streamlts-query-based-temporal-spatial-lidar","slug":"streamlts-query-based-temporal-spatial-lidar","title":"StreamLTS: Query-based Temporal-Spatial LiDAR Fusion for Cooperative Object Detection","date":"2024-07-04","arxiv_id":"2407.03825","repositories_listed":1,"syntology":null},{"url":"/paper/global-context-modeling-in-yolov8-for","slug":"global-context-modeling-in-yolov8-for","title":"Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detection","date":"2024-07-03","arxiv_id":"2407.03163","repositories_listed":1,"syntology":null},{"url":"/paper/segvg-transferring-object-bounding-box-to","slug":"segvg-transferring-object-bounding-box-to","title":"SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding","date":"2024-07-03","arxiv_id":"2407.03200","repositories_listed":1,"syntology":{"n":31,"n_ran":20,"n_constructed":15,"n_ran_checked":15,"n_instrument":5,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":31,"phrase":"20 ran (of which 15 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/segvg-transferring-object-bounding-box-to#ran","syntology_url":"https://syntology.ai/paper/2407.03200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03200"}},"official":{"repos":["weitaikang/segvg"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":15,"n_ran_no_instrument_failure":15,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-modality-balanced-online-knowledge","slug":"adaptive-modality-balanced-online-knowledge","title":"Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object Detection","date":"2024-07-02","arxiv_id":"2407.01894","repositories_listed":1,"syntology":null},{"url":"/paper/multi-grained-contrast-for-data-efficient","slug":"multi-grained-contrast-for-data-efficient","title":"Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning","date":"2024-07-02","arxiv_id":"2407.02014","repositories_listed":1,"syntology":null},{"url":"/paper/similarity-distance-based-label-assignment","slug":"similarity-distance-based-label-assignment","title":"Similarity Distance-Based Label Assignment for Tiny Object Detection","date":"2024-07-02","arxiv_id":"2407.02394","repositories_listed":1,"syntology":null},{"url":"/paper/smile-leveraging-submodular-mutual","slug":"smile-leveraging-submodular-mutual","title":"SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection","date":"2024-07-02","arxiv_id":"2407.02665","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":1,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/smile-leveraging-submodular-mutual#ran","syntology_url":"https://syntology.ai/paper/2407.02665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02665"}},"official":{"repos":["amajee11us/smile-fsod"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/eliminating-position-bias-of-language-models","slug":"eliminating-position-bias-of-language-models","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","date":"2024-07-01","arxiv_id":"2407.01100","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":0,"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/eliminating-position-bias-of-language-models#ran","syntology_url":"https://syntology.ai/paper/2407.01100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01100"}},"official":{"repos":["wzq016/pine"],"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/formal-verification-of-object-detection","slug":"formal-verification-of-object-detection","title":"Formal Verification of Deep Neural Networks for Object Detection","date":"2024-07-01","arxiv_id":"2407.01295","repositories_listed":1,"syntology":null},{"url":"/paper/sood-leveraging-unlabeled-data-to-boost","slug":"sood-leveraging-unlabeled-data-to-boost","title":"SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection","date":"2024-07-01","arxiv_id":"2407.01016","repositories_listed":1,"syntology":null},{"url":"/paper/repact-the-re-parameterizable-adaptive","slug":"repact-the-re-parameterizable-adaptive","title":"RepAct: The Re-parameterizable Adaptive Activation Function","date":"2024-06-28","arxiv_id":"2407.00131","repositories_listed":1,"syntology":null},{"url":"/paper/borg-a-brain-organoid-based-mitosis-dataset","slug":"borg-a-brain-organoid-based-mitosis-dataset","title":"BOrg: A Brain Organoid-Based Mitosis Dataset for Automatic Analysis of Brain Diseases","date":"2024-06-27","arxiv_id":"2406.19556","repositories_listed":1,"syntology":null},{"url":"/paper/huwsod-holistic-self-training-for-unified","slug":"huwsod-holistic-self-training-for-unified","title":"HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection","date":"2024-06-27","arxiv_id":"2406.19394","repositories_listed":1,"syntology":null},{"url":"/paper/instance-temperature-knowledge-distillation","slug":"instance-temperature-knowledge-distillation","title":"Instance Temperature Knowledge Distillation","date":"2024-06-27","arxiv_id":"2407.00115","repositories_listed":1,"syntology":null},{"url":"/paper/weighted-circle-fusion-ensembling-circle","slug":"weighted-circle-fusion-ensembling-circle","title":"Weighted Circle Fusion: Ensembling Circle Representation from Different Object Detection Results","date":"2024-06-27","arxiv_id":"2406.19540","repositories_listed":1,"syntology":null},{"url":"/paper/the-surprising-effectiveness-of-multimodal","slug":"the-surprising-effectiveness-of-multimodal","title":"The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval","date":"2024-06-26","arxiv_id":"2406.18113","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/the-surprising-effectiveness-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2406.18113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18113"}},"official":{"repos":["sudo-Boris/mr-Blip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/unveiling-the-unknown-conditional-evidence","slug":"unveiling-the-unknown-conditional-evidence","title":"Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundary","date":"2024-06-26","arxiv_id":"2406.18443","repositories_listed":1,"syntology":null},{"url":"/paper/mdha-multi-scale-deformable-transformer-with","slug":"mdha-multi-scale-deformable-transformer-with","title":"MDHA: Multi-Scale Deformable Transformer with Hybrid Anchors for Multi-View 3D Object Detection","date":"2024-06-25","arxiv_id":"2406.17654","repositories_listed":1,"syntology":null},{"url":"/paper/liteyolo-id-a-lightweight-object-detection","slug":"liteyolo-id-a-lightweight-object-detection","title":"LiteYOLO-ID: A Lightweight Object Detection Network for Insulator Defect Detection","date":"2024-06-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/smart-feature-is-what-you-need","slug":"smart-feature-is-what-you-need","title":"Smart Feature is What You Need","date":"2024-06-22","arxiv_id":"2406.15805","repositories_listed":1,"syntology":null},{"url":"/paper/dipex-dispersing-prompt-expansion-for-class","slug":"dipex-dispersing-prompt-expansion-for-class","title":"DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection","date":"2024-06-21","arxiv_id":"2406.14924","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dipex-dispersing-prompt-expansion-for-class#ran","syntology_url":"https://syntology.ai/paper/2406.14924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14924"}},"official":{"repos":["jason-lim26/dipex"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mos-model-synergy-for-test-time-adaptation-on","slug":"mos-model-synergy-for-test-time-adaptation-on","title":"MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection","date":"2024-06-21","arxiv_id":"2406.14878","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mos-model-synergy-for-test-time-adaptation-on#ran","syntology_url":"https://syntology.ai/paper/2406.14878","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14878"}},"official":{"repos":["zhuoxiao-chen/mos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enhanced-bank-check-security-introducing-a","slug":"enhanced-bank-check-security-introducing-a","title":"Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification","date":"2024-06-20","arxiv_id":"2406.14370","repositories_listed":1,"syntology":null},{"url":"/paper/leyolo-new-scalable-and-efficient-cnn","slug":"leyolo-new-scalable-and-efficient-cnn","title":"LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection","date":"2024-06-20","arxiv_id":"2406.14239","repositories_listed":1,"syntology":null},{"url":"/paper/ssad-self-supervised-auxiliary-detection","slug":"ssad-self-supervised-auxiliary-detection","title":"SSAD: Self-supervised Auxiliary Detection Framework for Panoramic X-ray based Dental Disease Diagnosis","date":"2024-06-20","arxiv_id":"2406.13963","repositories_listed":1,"syntology":null},{"url":"/paper/towards-the-in-situ-trunk-identification-and","slug":"towards-the-in-situ-trunk-identification-and","title":"Towards the in-situ Trunk Identification and Length Measurement of Sea Cucumbers via Bézier Curve Modelling","date":"2024-06-20","arxiv_id":"2406.13951","repositories_listed":1,"syntology":null},{"url":"/paper/visible-thermal-tiny-object-detection-a","slug":"visible-thermal-tiny-object-detection-a","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","date":"2024-06-20","arxiv_id":"2406.14482","repositories_listed":1,"syntology":null},{"url":"/paper/dpo-dual-perturbation-optimization-for-test","slug":"dpo-dual-perturbation-optimization-for-test","title":"DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection","date":"2024-06-19","arxiv_id":"2406.13891","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/dpo-dual-perturbation-optimization-for-test#ran","syntology_url":"https://syntology.ai/paper/2406.13891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13891"}},"official":{"repos":["jo-wang/dpo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/snowy-scenes-clear-detections-a-robust-model","slug":"snowy-scenes-clear-detections-a-robust-model","title":"Snowy Scenes,Clear Detections: A Robust Model for Traffic Light Detection in Adverse Weather Conditions","date":"2024-06-19","arxiv_id":"2406.13473","repositories_listed":1,"syntology":null},{"url":"/paper/strengthening-layer-interaction-via-dynamic","slug":"strengthening-layer-interaction-via-dynamic","title":"Strengthening Layer Interaction via Dynamic Layer Attention","date":"2024-06-19","arxiv_id":"2406.13392","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/strengthening-layer-interaction-via-dynamic#ran","syntology_url":"https://syntology.ai/paper/2406.13392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13392"}},"official":{"repos":["tunantu/dynamic-layer-attention"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/privacy-preserving-federated-learning-in","slug":"privacy-preserving-federated-learning-in","title":"Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation","date":"2024-06-18","arxiv_id":"2406.12815","repositories_listed":1,"syntology":null},{"url":"/paper/vidsod-100-a-new-dataset-and-a-baseline-model","slug":"vidsod-100-a-new-dataset-and-a-baseline-model","title":"ViDSOD-100: A New Dataset and a Baseline Model for RGB-D Video Salient Object Detection","date":"2024-06-18","arxiv_id":"2406.12536","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-efficient-masked-autoencoder-learning","slug":"scaling-efficient-masked-autoencoder-learning","title":"Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset","date":"2024-06-17","arxiv_id":"2406.11933","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"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) · 3 unverified","sample_list":"/paper/scaling-efficient-masked-autoencoder-learning#ran","syntology_url":"https://syntology.ai/paper/2406.11933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11933"}},"official":{"repos":["Fengxiang23/SelectiveMAE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-domain-adaptation-using","slug":"semi-supervised-domain-adaptation-using","title":"Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detection","date":"2024-06-17","arxiv_id":"2406.11313","repositories_listed":1,"syntology":null},{"url":"/paper/syn-to-real-unsupervised-domain-adaptation","slug":"syn-to-real-unsupervised-domain-adaptation","title":"Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection","date":"2024-06-17","arxiv_id":"2406.11311","repositories_listed":1,"syntology":null},{"url":"/paper/yolo9tr-a-lightweight-model-for-pavement","slug":"yolo9tr-a-lightweight-model-for-pavement","title":"YOLO9tr: A Lightweight Model for Pavement Damage Detection Utilizing a Generalized Efficient Layer Aggregation Network and Attention Mechanism","date":"2024-06-17","arxiv_id":"2406.11254","repositories_listed":1,"syntology":null},{"url":"/paper/mmvr-millimeter-wave-multi-view-radar-dataset","slug":"mmvr-millimeter-wave-multi-view-radar-dataset","title":"MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perception","date":"2024-06-15","arxiv_id":"2406.10708","repositories_listed":1,"syntology":null},{"url":"/paper/voxel-mamba-group-free-state-space-models-for","slug":"voxel-mamba-group-free-state-space-models-for","title":"Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection","date":"2024-06-15","arxiv_id":"2406.10700","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/voxel-mamba-group-free-state-space-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.10700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10700"}},"official":{"repos":["gwenzhang/voxel-mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efm3d-a-benchmark-for-measuring-progress","slug":"efm3d-a-benchmark-for-measuring-progress","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","date":"2024-06-14","arxiv_id":"2406.10224","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efm3d-a-benchmark-for-measuring-progress#ran","syntology_url":"https://syntology.ai/paper/2406.10224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10224"}},"official":{"repos":["facebookresearch/efm3d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shelf-supervised-multi-modal-pre-training-for","slug":"shelf-supervised-multi-modal-pre-training-for","title":"Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection","date":"2024-06-14","arxiv_id":"2406.10115","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shelf-supervised-multi-modal-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2406.10115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10115"}},"official":{"repos":["meharkhurana03/cm3d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-the-visual-cognition-gap-between","slug":"what-is-the-visual-cognition-gap-between","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","date":"2024-06-14","arxiv_id":"2406.10424","repositories_listed":1,"syntology":null},{"url":"/paper/bevspread-spread-voxel-pooling-for-bird-s-eye-1","slug":"bevspread-spread-voxel-pooling-for-bird-s-eye-1","title":"BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection","date":"2024-06-13","arxiv_id":"2406.08785","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bevspread-spread-voxel-pooling-for-bird-s-eye-1#ran","syntology_url":"https://syntology.ai/paper/2406.08785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08785"}},"official":{"repos":["datongjie/bevspread"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/denoisereid-denoising-model-for","slug":"denoisereid-denoising-model-for","title":"DenoiseRep: Denoising Model for Representation Learning","date":"2024-06-13","arxiv_id":"2406.08773","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":2,"n_ran_checked":17,"n_instrument":0,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":14,"n_pointer_only":6,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 1 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/denoisereid-denoising-model-for#ran","syntology_url":"https://syntology.ai/paper/2406.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08773"}},"official":{"repos":["wangguanan/denoiserep"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":2,"n_ran_no_instrument_failure":17,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-evaluating-the-robustness-of-visual","slug":"towards-evaluating-the-robustness-of-visual","title":"Towards Evaluating the Robustness of Visual State Space Models","date":"2024-06-13","arxiv_id":"2406.09407","repositories_listed":1,"syntology":null},{"url":"/paper/visual-sketchpad-sketching-as-a-visual-chain","slug":"visual-sketchpad-sketching-as-a-visual-chain","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models","date":"2024-06-13","arxiv_id":"2406.09403","repositories_listed":1,"syntology":null},{"url":"/paper/ct3d-improving-3d-object-detection-with","slug":"ct3d-improving-3d-object-detection-with","title":"CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer","date":"2024-06-12","arxiv_id":"2406.08152","repositories_listed":1,"syntology":null},{"url":"/paper/dataset-enhancement-with-instance-level","slug":"dataset-enhancement-with-instance-level","title":"Dataset Enhancement with Instance-Level Augmentations","date":"2024-06-12","arxiv_id":"2406.08249","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/dataset-enhancement-with-instance-level#ran","syntology_url":"https://syntology.ai/paper/2406.08249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08249"}},"official":{"repos":["KupynOrest/instance_augmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mwirstd-a-mwir-small-target-detection-dataset","slug":"mwirstd-a-mwir-small-target-detection-dataset","title":"MWIRSTD: A MWIR Small Target Detection Dataset","date":"2024-06-12","arxiv_id":"2406.08063","repositories_listed":1,"syntology":null},{"url":"/paper/sense-less-generate-more-pre-training-lidar","slug":"sense-less-generate-more-pre-training-lidar","title":"Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensing","date":"2024-06-12","arxiv_id":"2406.07833","repositories_listed":1,"syntology":null},{"url":"/paper/a-semantic-aware-and-multi-guided-network-for","slug":"a-semantic-aware-and-multi-guided-network-for","title":"A Semantic-Aware and Multi-Guided Network for Infrared-Visible Image Fusion","date":"2024-06-11","arxiv_id":"2407.06159","repositories_listed":1,"syntology":null},{"url":"/paper/effocc-a-minimal-baseline-for-efficient","slug":"effocc-a-minimal-baseline-for-efficient","title":"EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network","date":"2024-06-11","arxiv_id":"2406.07042","repositories_listed":1,"syntology":null},{"url":"/paper/triple-domain-feature-learning-with-frequency","slug":"triple-domain-feature-learning-with-frequency","title":"Triple-domain Feature Learning with Frequency-aware Memory Enhancement for Moving Infrared Small Target Detection","date":"2024-06-11","arxiv_id":"2406.06949","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-visual-concepts-across-models","slug":"understanding-visual-concepts-across-models","title":"Understanding Visual Concepts Across Models","date":"2024-06-11","arxiv_id":"2406.07506","repositories_listed":1,"syntology":null},{"url":"/paper/uemm-air-a-synthetic-multi-modal-dataset-for","slug":"uemm-air-a-synthetic-multi-modal-dataset-for","title":"UEMM-Air: A Synthetic Multi-modal Dataset for Unmanned Aerial Vehicle Object Detection","date":"2024-06-10","arxiv_id":"2406.06230","repositories_listed":1,"syntology":null},{"url":"/paper/sam-pm-enhancing-video-camouflaged-object","slug":"sam-pm-enhancing-video-camouflaged-object","title":"SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention","date":"2024-06-09","arxiv_id":"2406.05802","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-graph-convolutions-for-mobile-vision","slug":"scaling-graph-convolutions-for-mobile-vision","title":"Scaling Graph Convolutions for Mobile Vision","date":"2024-06-09","arxiv_id":"2406.05850","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-graph-convolutions-for-mobile-vision#ran","syntology_url":"https://syntology.ai/paper/2406.05850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05850"}},"official":{"repos":["sldgroup/mobilevigv2"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/select-mosaic-data-augmentation-method-for","slug":"select-mosaic-data-augmentation-method-for","title":"Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes","date":"2024-06-08","arxiv_id":"2406.05412","repositories_listed":1,"syntology":null}],"record_sha256":"19ea1c3b45d01f09f04eb047e287119a6cd15dde266b2b7863f206ae0a9b37a1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}