{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object-detection-1/papers/5","list_of":"/task/object-detection-1","task":"object-detection","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":5,"pages_in_order":106,"rows_per_page":100,"rows":[401,500],"of":10514,"counts":{"archive_papers_tagged":10514,"with_a_code_link":4285,"where_syntology_ran_a_sample":1027,"not_listed_spam_title":0,"listed":10514,"listed_where_code_ran":1027,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":898,"every_run_a_failure_of_syntologys_instrument":129,"listed_with_a_run_with_no_instrument_failure":898,"listed_every_run_a_failure_of_syntologys_instrument":129,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object-detection-1","prev":"/task/object-detection-1/papers/4","next":"/task/object-detection-1/papers/6","papers":[{"url":"/paper/faster-r-cnn-features-for-instance-search","slug":"faster-r-cnn-features-for-instance-search","title":"Faster R-CNN Features for Instance Search","date":"2016-04-29","arxiv_id":"1604.08893","repositories_listed":3,"syntology":null},{"url":"/paper/synthetic-data-for-text-localisation-in","slug":"synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","date":"2016-04-22","arxiv_id":"1604.06646","repositories_listed":3,"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/synthetic-data-for-text-localisation-in#ran","syntology_url":"https://syntology.ai/paper/1604.06646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06646"}},"official":null}},{"url":"/paper/the-cityscapes-dataset-for-semantic-urban","slug":"the-cityscapes-dataset-for-semantic-urban","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","date":"2016-04-06","arxiv_id":"1604.01685","repositories_listed":3,"syntology":null},{"url":"/paper/exploring-models-and-data-for-image-question","slug":"exploring-models-and-data-for-image-question","title":"Exploring Models and Data for Image Question Answering","date":"2015-05-08","arxiv_id":"1505.02074","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/exploring-models-and-data-for-image-question#ran","syntology_url":"https://syntology.ai/paper/1505.02074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.02074"}},"official":{"repos":["renmengye/imageqa-public"],"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":["listed","official"]}}},{"url":"/paper/multi-view-face-detection-using-deep","slug":"multi-view-face-detection-using-deep","title":"Multi-view Face Detection Using Deep Convolutional Neural Networks","date":"2015-02-10","arxiv_id":"1502.02766","repositories_listed":3,"syntology":null},{"url":"/paper/seg-r1-segmentation-can-be-surprisingly","slug":"seg-r1-segmentation-can-be-surprisingly","title":"Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning","date":"2025-06-27","arxiv_id":"2506.22624","repositories_listed":2,"syntology":{"n":23,"n_ran":22,"n_constructed":0,"n_ran_checked":13,"n_instrument":9,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":4,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/seg-r1-segmentation-can-be-surprisingly#ran","syntology_url":"https://syntology.ai/paper/2506.22624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.22624"}},"official":{"repos":["geshang777/Seg-R1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/yolov13-real-time-object-detection-with","slug":"yolov13-real-time-object-detection-with","title":"YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception","date":"2025-06-21","arxiv_id":"2506.17733","repositories_listed":2,"syntology":null},{"url":"/paper/lecture-video-visual-objects-lvvo-dataset-a","slug":"lecture-video-visual-objects-lvvo-dataset-a","title":"Lecture Video Visual Objects (LVVO) Dataset: A Benchmark for Visual Object Detection in Educational Videos","date":"2025-06-16","arxiv_id":"2506.13657","repositories_listed":2,"syntology":null},{"url":"/paper/e-inmemo-enhanced-prompting-for-visual-in","slug":"e-inmemo-enhanced-prompting-for-visual-in","title":"E-InMeMo: Enhanced Prompting for Visual In-Context Learning","date":"2025-04-25","arxiv_id":"2504.18158","repositories_listed":2,"syntology":null},{"url":"/paper/saga-semantic-aware-gray-color-augmentation","slug":"saga-semantic-aware-gray-color-augmentation","title":"SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems","date":"2025-04-22","arxiv_id":"2504.15728","repositories_listed":2,"syntology":null},{"url":"/paper/lightweight-lidar-camera-3d-dynamic-object","slug":"lightweight-lidar-camera-3d-dynamic-object","title":"Lightweight LiDAR-Camera 3D Dynamic Object Detection and Multi-Class Trajectory Prediction","date":"2025-04-18","arxiv_id":"2504.13647","repositories_listed":2,"syntology":null},{"url":"/paper/spectral-adaptive-modulation-networks-for","slug":"spectral-adaptive-modulation-networks-for","title":"Spectral-Adaptive Modulation Networks for Visual Perception","date":"2025-03-31","arxiv_id":"2503.23947","repositories_listed":2,"syntology":null},{"url":"/paper/robust-object-detection-of-underwater-robot","slug":"robust-object-detection-of-underwater-robot","title":"Robust Object Detection of Underwater Robot based on Domain Generalization","date":"2025-03-18","arxiv_id":"2503.19929","repositories_listed":2,"syntology":null},{"url":"/paper/davimnet-ssms-based-domain-adaptive-object","slug":"davimnet-ssms-based-domain-adaptive-object","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","date":"2025-02-16","arxiv_id":"2502.11178","repositories_listed":2,"syntology":null},{"url":"/paper/pointobb-v3-expanding-performance-boundaries","slug":"pointobb-v3-expanding-performance-boundaries","title":"PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection","date":"2025-01-23","arxiv_id":"2501.13898","repositories_listed":2,"syntology":null},{"url":"/paper/improving-generalization-performance-of","slug":"improving-generalization-performance-of","title":"Improving Generalization Performance of YOLOv8 for Camera Trap Object Detection","date":"2024-12-18","arxiv_id":"2412.14211","repositories_listed":2,"syntology":null},{"url":"/paper/interpreting-object-level-foundation-models","slug":"interpreting-object-level-foundation-models","title":"Interpreting Object-level Foundation Models via Visual Precision Search","date":"2024-11-25","arxiv_id":"2411.16198","repositories_listed":2,"syntology":null},{"url":"/paper/indraeye-infrared-electro-optical-uav-based","slug":"indraeye-infrared-electro-optical-uav-based","title":"IndraEye: Infrared Electro-Optical UAV-based Perception Dataset for Robust Downstream Tasks","date":"2024-10-28","arxiv_id":"2410.20953","repositories_listed":2,"syntology":null},{"url":"/paper/optimizing-edge-offloading-decisions-for","slug":"optimizing-edge-offloading-decisions-for","title":"Optimizing Edge Offloading Decisions for Object Detection","date":"2024-10-24","arxiv_id":"2410.18919","repositories_listed":2,"syntology":null},{"url":"/paper/yolo-rd-introducing-relevant-and-compact","slug":"yolo-rd-introducing-relevant-and-compact","title":"YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary","date":"2024-10-20","arxiv_id":"2410.15346","repositories_listed":2,"syntology":null},{"url":"/paper/kpca-cam-visual-explainability-of-deep","slug":"kpca-cam-visual-explainability-of-deep","title":"KPCA-CAM: Visual Explainability of Deep Computer Vision Models using Kernel PCA","date":"2024-09-30","arxiv_id":"2410.00267","repositories_listed":2,"syntology":null},{"url":"/paper/towards-physically-realizable-adversarial","slug":"towards-physically-realizable-adversarial","title":"Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation","date":"2024-09-16","arxiv_id":"2409.10071","repositories_listed":2,"syntology":null},{"url":"/paper/when-to-extract-reid-features-a-selective","slug":"when-to-extract-reid-features-a-selective","title":"When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking","date":"2024-09-10","arxiv_id":"2409.06617","repositories_listed":2,"syntology":null},{"url":"/paper/padetbench-towards-benchmarking-physical","slug":"padetbench-towards-benchmarking-physical","title":"PADetBench: Towards Benchmarking Physical Attacks against Object Detection","date":"2024-08-17","arxiv_id":"2408.09181","repositories_listed":2,"syntology":null},{"url":"/paper/cas-vit-convolutional-additive-self-attention","slug":"cas-vit-convolutional-additive-self-attention","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","date":"2024-08-07","arxiv_id":"2408.03703","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cas-vit-convolutional-additive-self-attention#ran","syntology_url":"https://syntology.ai/paper/2408.03703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03703"}},"official":{"repos":["tianfang-zhang/cas-vit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/axiomvision-accuracy-guaranteed-adaptive","slug":"axiomvision-accuracy-guaranteed-adaptive","title":"AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics","date":"2024-07-29","arxiv_id":"2407.20124","repositories_listed":2,"syntology":null},{"url":"/paper/relation-detr-exploring-explicit-position","slug":"relation-detr-exploring-explicit-position","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","date":"2024-07-16","arxiv_id":"2407.11699","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/relation-detr-exploring-explicit-position#ran","syntology_url":"https://syntology.ai/paper/2407.11699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11699"}},"official":{"repos":["xiuqhou/relation-detr"],"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/sh17-a-dataset-for-human-safety-and-personal","slug":"sh17-a-dataset-for-human-safety-and-personal","title":"SH17: A Dataset for Human Safety and Personal Protective Equipment Detection in Manufacturing Industry","date":"2024-07-05","arxiv_id":"2407.04590","repositories_listed":2,"syntology":null},{"url":"/paper/comics-datasets-framework-mix-of-comics","slug":"comics-datasets-framework-mix-of-comics","title":"Comics Datasets Framework: Mix of Comics datasets for detection benchmarking","date":"2024-07-03","arxiv_id":"2407.03540","repositories_listed":2,"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/comics-datasets-framework-mix-of-comics#ran","syntology_url":"https://syntology.ai/paper/2407.03540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03540"}},"official":{"repos":["emanuelevivoli/cdf"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/advancing-grounded-multimodal-named-entity","slug":"advancing-grounded-multimodal-named-entity","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","date":"2024-06-11","arxiv_id":"2406.07268","repositories_listed":2,"syntology":null},{"url":"/paper/a-denoising-fpn-with-transformer-r-cnn-for","slug":"a-denoising-fpn-with-transformer-r-cnn-for","title":"A DeNoising FPN With Transformer R-CNN for Tiny Object Detection","date":"2024-06-09","arxiv_id":"2406.05755","repositories_listed":2,"syntology":null},{"url":"/paper/mamba-yolo-ssms-based-yolo-for-object","slug":"mamba-yolo-ssms-based-yolo-for-object","title":"Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","date":"2024-06-09","arxiv_id":"2406.05835","repositories_listed":2,"syntology":null},{"url":"/paper/lw-detr-a-transformer-replacement-to-yolo-for","slug":"lw-detr-a-transformer-replacement-to-yolo-for","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","date":"2024-06-05","arxiv_id":"2406.03459","repositories_listed":2,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lw-detr-a-transformer-replacement-to-yolo-for#ran","syntology_url":"https://syntology.ai/paper/2406.03459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03459"}},"official":{"repos":["atten4vis/lw-detr"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/grootvl-tree-topology-is-all-you-need-in","slug":"grootvl-tree-topology-is-all-you-need-in","title":"GrootVL: Tree Topology is All You Need in State Space Model","date":"2024-06-04","arxiv_id":"2406.02395","repositories_listed":2,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"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) · 5 unverified","sample_list":"/paper/grootvl-tree-topology-is-all-you-need-in#ran","syntology_url":"https://syntology.ai/paper/2406.02395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02395"}},"official":{"repos":["easonxiao-888/grootvl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unified-unsupervised-salient-object-detection","slug":"unified-unsupervised-salient-object-detection","title":"Unified Unsupervised Salient Object Detection via Knowledge Transfer","date":"2024-04-23","arxiv_id":"2404.14759","repositories_listed":2,"syntology":{"n":19,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/unified-unsupervised-salient-object-detection#ran","syntology_url":"https://syntology.ai/paper/2404.14759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14759"}},"official":{"repos":["I2-Multimedia-Lab/A2S-v3"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-embeddings-with-centroid-triplet","slug":"learning-embeddings-with-centroid-triplet","title":"Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping","date":"2024-04-09","arxiv_id":"2404.06277","repositories_listed":2,"syntology":null},{"url":"/paper/dq-detr-detr-with-dynamic-query-for-tiny","slug":"dq-detr-detr-with-dynamic-query-for-tiny","title":"DQ-DETR: DETR with Dynamic Query for Tiny Object Detection","date":"2024-04-04","arxiv_id":"2404.03507","repositories_listed":2,"syntology":null},{"url":"/paper/is-clip-the-main-roadblock-for-fine-grained","slug":"is-clip-the-main-roadblock-for-fine-grained","title":"Is CLIP the main roadblock for fine-grained open-world perception?","date":"2024-04-04","arxiv_id":"2404.03539","repositories_listed":2,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":17,"phrase":"15 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/is-clip-the-main-roadblock-for-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2404.03539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03539"}},"official":{"repos":["lorebianchi98/fg-clip"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/plainmamba-improving-non-hierarchical-mamba","slug":"plainmamba-improving-non-hierarchical-mamba","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","date":"2024-03-26","arxiv_id":"2403.17695","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/plainmamba-improving-non-hierarchical-mamba#ran","syntology_url":"https://syntology.ai/paper/2403.17695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17695"}},"official":{"repos":["chenhongyiyang/plainmamba"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/t-rex2-towards-generic-object-detection-via","slug":"t-rex2-towards-generic-object-detection-via","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","date":"2024-03-21","arxiv_id":"2403.14610","repositories_listed":2,"syntology":null},{"url":"/paper/mtp-advancing-remote-sensing-foundation-model","slug":"mtp-advancing-remote-sensing-foundation-model","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","date":"2024-03-20","arxiv_id":"2403.13430","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mtp-advancing-remote-sensing-foundation-model#ran","syntology_url":"https://syntology.ai/paper/2403.13430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13430"}},"official":{"repos":["vitae-transformer/mtp"],"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":["listed","official"]}}},{"url":"/paper/rar-retrieving-and-ranking-augmented-mllms","slug":"rar-retrieving-and-ranking-augmented-mllms","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","date":"2024-03-20","arxiv_id":"2403.13805","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rar-retrieving-and-ranking-augmented-mllms#ran","syntology_url":"https://syntology.ai/paper/2403.13805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13805"}},"official":{"repos":["liuziyu77/rar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/align-and-distill-unifying-and-improving","slug":"align-and-distill-unifying-and-improving","title":"Align and Distill: Unifying and Improving Domain Adaptive Object Detection","date":"2024-03-18","arxiv_id":"2403.12029","repositories_listed":2,"syntology":null},{"url":"/paper/lsknet-a-foundation-lightweight-backbone-for","slug":"lsknet-a-foundation-lightweight-backbone-for","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","date":"2024-03-18","arxiv_id":"2403.11735","repositories_listed":2,"syntology":null},{"url":"/paper/mca-moment-channel-attention-networks","slug":"mca-moment-channel-attention-networks","title":"MCA: Moment Channel Attention Networks","date":"2024-03-04","arxiv_id":"2403.01713","repositories_listed":2,"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":3,"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/mca-moment-channel-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2403.01713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01713"}},"official":{"repos":["csdllab/mca"],"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/dams-detr-dynamic-adaptive-multispectral","slug":"dams-detr-dynamic-adaptive-multispectral","title":"DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion","date":"2024-03-01","arxiv_id":"2403.00326","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dams-detr-dynamic-adaptive-multispectral#ran","syntology_url":"https://syntology.ai/paper/2403.00326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00326"}},"official":{"repos":["gjj45/dams-detr","gjj45/damsdet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/theoretically-achieving-continuous","slug":"theoretically-achieving-continuous","title":"Theoretically Achieving Continuous Representation of Oriented Bounding Boxes","date":"2024-02-29","arxiv_id":"2402.18975","repositories_listed":2,"syntology":null},{"url":"/paper/emiff-enhanced-multi-scale-image-feature","slug":"emiff-enhanced-multi-scale-image-feature","title":"EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection","date":"2024-02-23","arxiv_id":"2402.15272","repositories_listed":2,"syntology":null},{"url":"/paper/llms-as-bridges-reformulating-grounded","slug":"llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","repositories_listed":2,"syntology":null},{"url":"/paper/beam-beta-distribution-ray-denoising-for","slug":"beam-beta-distribution-ray-denoising-for","title":"Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection","date":"2024-02-06","arxiv_id":"2402.03634","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beam-beta-distribution-ray-denoising-for#ran","syntology_url":"https://syntology.ai/paper/2402.03634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03634"}},"official":{"repos":["liewfeng/beam","liewfeng/raydn"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-domain-few-shot-object-detection-via","slug":"cross-domain-few-shot-object-detection-via","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","date":"2024-02-05","arxiv_id":"2402.03094","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-domain-few-shot-object-detection-via#ran","syntology_url":"https://syntology.ai/paper/2402.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03094"}},"official":{"repos":["lovelyqian/CDFSOD-benchmark"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/spatio-temporal-prompting-network-for-robust-1","slug":"spatio-temporal-prompting-network-for-robust-1","title":"Spatio-temporal Prompting Network for Robust Video Feature Extraction","date":"2024-02-04","arxiv_id":"2402.02574","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-learning-of-lidar-3d-point","slug":"self-supervised-learning-of-lidar-3d-point","title":"Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration","date":"2024-01-23","arxiv_id":"2401.12452","repositories_listed":2,"syntology":{"n":26,"n_ran":24,"n_constructed":0,"n_ran_checked":18,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":26,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/self-supervised-learning-of-lidar-3d-point#ran","syntology_url":"https://syntology.ai/paper/2401.12452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12452"}},"official":{"repos":["eaphan/nclr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/agent-attention-on-the-integration-of-softmax","slug":"agent-attention-on-the-integration-of-softmax","title":"Agent Attention: On the Integration of Softmax and Linear Attention","date":"2023-12-14","arxiv_id":"2312.08874","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":19,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/agent-attention-on-the-integration-of-softmax#ran","syntology_url":"https://syntology.ai/paper/2312.08874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08874"}},"official":{"repos":["leaplabthu/agent-attention"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/am-radio-agglomerative-model-reduce-all","slug":"am-radio-agglomerative-model-reduce-all","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","date":"2023-12-10","arxiv_id":"2312.06709","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/am-radio-agglomerative-model-reduce-all#ran","syntology_url":"https://syntology.ai/paper/2312.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06709"}},"official":{"repos":["nvlabs/radio"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/scar-scaling-adversarial-robustness-for-lidar","slug":"scar-scaling-adversarial-robustness-for-lidar","title":"ScAR: Scaling Adversarial Robustness for LiDAR Object Detection","date":"2023-12-05","arxiv_id":"2312.03085","repositories_listed":2,"syntology":null},{"url":"/paper/aligning-and-prompting-everything-all-at-once","slug":"aligning-and-prompting-everything-all-at-once","title":"Aligning and Prompting Everything All at Once for Universal Visual Perception","date":"2023-12-04","arxiv_id":"2312.02153","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/aligning-and-prompting-everything-all-at-once#ran","syntology_url":"https://syntology.ai/paper/2312.02153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02153"}},"official":{"repos":["shenyunhang/ape"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/boosting-object-detection-with-zero-shot-day","slug":"boosting-object-detection-with-zero-shot-day","title":"Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation","date":"2023-12-02","arxiv_id":"2312.01220","repositories_listed":2,"syntology":null},{"url":"/paper/dyra-dynamic-resolution-adjustment-for-scale","slug":"dyra-dynamic-resolution-adjustment-for-scale","title":"DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors","date":"2023-11-28","arxiv_id":"2311.17098","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-vision-transformers-with-group-mix","slug":"advancing-vision-transformers-with-group-mix","title":"Advancing Vision Transformers with Group-Mix Attention","date":"2023-11-26","arxiv_id":"2311.15157","repositories_listed":2,"syntology":null},{"url":"/paper/vscode-general-visual-salient-and-camouflaged","slug":"vscode-general-visual-salient-and-camouflaged","title":"VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning","date":"2023-11-25","arxiv_id":"2311.15011","repositories_listed":2,"syntology":null},{"url":"/paper/point2rbox-combine-knowledge-from-synthetic","slug":"point2rbox-combine-knowledge-from-synthetic","title":"Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision","date":"2023-11-23","arxiv_id":"2311.14758","repositories_listed":2,"syntology":null},{"url":"/paper/akconv-convolutional-kernel-with-arbitrary","slug":"akconv-convolutional-kernel-with-arbitrary","title":"LDConv: Linear deformable convolution for improving convolutional neural networks","date":"2023-11-20","arxiv_id":"2311.11587","repositories_listed":2,"syntology":null},{"url":"/paper/battle-of-the-backbones-a-large-scale","slug":"battle-of-the-backbones-a-large-scale","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","date":"2023-10-30","arxiv_id":"2310.19909","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/battle-of-the-backbones-a-large-scale#ran","syntology_url":"https://syntology.ai/paper/2310.19909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19909"}},"official":{"repos":["hsouri/battle-of-the-backbones"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/salient-object-detection-in-rgb-d-videos","slug":"salient-object-detection-in-rgb-d-videos","title":"Salient Object Detection in RGB-D Videos","date":"2023-10-24","arxiv_id":"2310.15482","repositories_listed":2,"syntology":null},{"url":"/paper/memtrack-a-deep-learning-based-approach-to","slug":"memtrack-a-deep-learning-based-approach-to","title":"MEMTRACK: A Deep Learning-Based Approach to Microrobot Tracking in Dense and Low-Contrast Environments","date":"2023-10-13","arxiv_id":"2310.09441","repositories_listed":2,"syntology":null},{"url":"/paper/get-group-event-transformer-for-event-based-1","slug":"get-group-event-transformer-for-event-based-1","title":"GET: Group Event Transformer for Event-Based Vision","date":"2023-10-04","arxiv_id":"2310.02642","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":6,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/get-group-event-transformer-for-event-based-1#ran","syntology_url":"https://syntology.ai/paper/2310.02642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02642"}},"official":{"repos":["peterande/get-group-event-transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/detection-oriented-image-text-pretraining-for","slug":"detection-oriented-image-text-pretraining-for","title":"Region-centric Image-Language Pretraining for Open-Vocabulary Detection","date":"2023-09-29","arxiv_id":"2310.00161","repositories_listed":2,"syntology":null},{"url":"/paper/text-image-alignment-for-diffusion-based","slug":"text-image-alignment-for-diffusion-based","title":"Text-image Alignment for Diffusion-based Perception","date":"2023-09-29","arxiv_id":"2310.00031","repositories_listed":2,"syntology":null},{"url":"/paper/yolor-based-multi-task-learning","slug":"yolor-based-multi-task-learning","title":"YOLOR-Based Multi-Task Learning","date":"2023-09-29","arxiv_id":"2309.16921","repositories_listed":2,"syntology":null},{"url":"/paper/double-domain-guided-real-time-low-light","slug":"double-domain-guided-real-time-low-light","title":"Double Domain Guided Real-Time Low-Light Image Enhancement for Ultra-High-Definition Transportation Surveillance","date":"2023-09-15","arxiv_id":"2309.08382","repositories_listed":2,"syntology":null},{"url":"/paper/a-theoretical-and-practical-framework-for","slug":"a-theoretical-and-practical-framework-for","title":"A Theoretical and Practical Framework for Evaluating Uncertainty Calibration in Object Detection","date":"2023-09-01","arxiv_id":"2309.00464","repositories_listed":2,"syntology":null},{"url":"/paper/a-survey-on-self-supervised-representation","slug":"a-survey-on-self-supervised-representation","title":"A Survey on Self-Supervised Representation Learning","date":"2023-08-22","arxiv_id":"2308.11455","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-vrnet-an-exquisite-fusion-network","slug":"efficient-vrnet-an-exquisite-fusion-network","title":"ASY-VRNet: Waterway Panoptic Driving Perception Model based on Asymmetric Fair Fusion of Vision and 4D mmWave Radar","date":"2023-08-20","arxiv_id":"2308.10287","repositories_listed":2,"syntology":null},{"url":"/paper/frequency-perception-network-for-camouflaged","slug":"frequency-perception-network-for-camouflaged","title":"Frequency Perception Network for Camouflaged Object Detection","date":"2023-08-17","arxiv_id":"2308.08924","repositories_listed":2,"syntology":null},{"url":"/paper/point-aware-interaction-and-cnn-induced","slug":"point-aware-interaction-and-cnn-induced","title":"Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection","date":"2023-08-17","arxiv_id":"2308.08930","repositories_listed":2,"syntology":null},{"url":"/paper/improving-pseudo-labels-for-open-vocabulary","slug":"improving-pseudo-labels-for-open-vocabulary","title":"Taming Self-Training for Open-Vocabulary Object Detection","date":"2023-08-11","arxiv_id":"2308.06412","repositories_listed":2,"syntology":null},{"url":"/paper/objects-do-not-disappear-video-object","slug":"objects-do-not-disappear-video-object","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","date":"2023-08-09","arxiv_id":"2308.04770","repositories_listed":2,"syntology":null},{"url":"/paper/fsd-v2-improving-fully-sparse-3d-object","slug":"fsd-v2-improving-fully-sparse-3d-object","title":"FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels","date":"2023-08-07","arxiv_id":"2308.03755","repositories_listed":2,"syntology":null},{"url":"/paper/on-point-affiliation-in-feature-upsampling","slug":"on-point-affiliation-in-feature-upsampling","title":"On Point Affiliation in Feature Upsampling","date":"2023-07-17","arxiv_id":"2307.08198","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-point-affiliation-in-feature-upsampling#ran","syntology_url":"https://syntology.ai/paper/2307.08198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08198"}},"official":{"repos":["tiny-smart/sapa"],"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":["listed","official"]}}},{"url":"/paper/scale-aware-modulation-meet-transformer","slug":"scale-aware-modulation-meet-transformer","title":"Scale-Aware Modulation Meet Transformer","date":"2023-07-17","arxiv_id":"2307.08579","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 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) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/scale-aware-modulation-meet-transformer#ran","syntology_url":"https://syntology.ai/paper/2307.08579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08579"}},"official":{"repos":["afeng-x/smt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/focusing-on-what-to-decode-and-what-to-train","slug":"focusing-on-what-to-decode-and-what-to-train","title":"Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor","date":"2023-07-05","arxiv_id":"2307.02291","repositories_listed":2,"syntology":null},{"url":"/paper/mathbf-c-2-former-calibrated-and","slug":"mathbf-c-2-former-calibrated-and","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","date":"2023-06-28","arxiv_id":"2306.16175","repositories_listed":2,"syntology":null},{"url":"/paper/hyp-ow-exploiting-hierarchical-structure","slug":"hyp-ow-exploiting-hierarchical-structure","title":"Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection","date":"2023-06-25","arxiv_id":"2306.14291","repositories_listed":2,"syntology":null},{"url":"/paper/iterative-scale-up-expansioniou-and-deep","slug":"iterative-scale-up-expansioniou-and-deep","title":"Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports","date":"2023-06-22","arxiv_id":"2306.13074","repositories_listed":2,"syntology":null},{"url":"/paper/robust-semantic-segmentation-strong","slug":"robust-semantic-segmentation-strong","title":"Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models","date":"2023-06-22","arxiv_id":"2306.12941","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-semantic-segmentation-strong#ran","syntology_url":"https://syntology.ai/paper/2306.12941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.12941"}},"official":{"repos":["nmndeep/robust-segmentation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fha-kitchens-a-novel-dataset-for-fine-grained","slug":"fha-kitchens-a-novel-dataset-for-fine-grained","title":"Multi-Granularity Hand Action Detection","date":"2023-06-19","arxiv_id":"2306.10858","repositories_listed":2,"syntology":null},{"url":"/paper/multiclass-confidence-and-localization-1","slug":"multiclass-confidence-and-localization-1","title":"Multiclass Confidence and Localization Calibration for Object Detection","date":"2023-06-14","arxiv_id":"2306.08271","repositories_listed":2,"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":1,"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/multiclass-confidence-and-localization-1#ran","syntology_url":"https://syntology.ai/paper/2306.08271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08271"}},"official":{"repos":["bimsarapathiraja/mccl"],"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/where-does-my-model-underperform-a-human","slug":"where-does-my-model-underperform-a-human","title":"Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms","date":"2023-06-13","arxiv_id":"2306.08167","repositories_listed":2,"syntology":null},{"url":"/paper/fastervit-fast-vision-transformers-with","slug":"fastervit-fast-vision-transformers-with","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","date":"2023-06-09","arxiv_id":"2306.06189","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"4 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; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/fastervit-fast-vision-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2306.06189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06189"}},"official":{"repos":["NVlabs/FasterViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2d-object-detection-with-transformers-a","slug":"2d-object-detection-with-transformers-a","title":"Object Detection with Transformers: A Review","date":"2023-06-07","arxiv_id":"2306.04670","repositories_listed":2,"syntology":null},{"url":"/paper/weakly-supervised-conditional-embedding-for","slug":"weakly-supervised-conditional-embedding-for","title":"LRVS-Fashion: Extending Visual Search with Referring Instructions","date":"2023-06-05","arxiv_id":"2306.02928","repositories_listed":2,"syntology":null},{"url":"/paper/occ-bev-multi-camera-unified-pre-training-via","slug":"occ-bev-multi-camera-unified-pre-training-via","title":"UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving","date":"2023-05-30","arxiv_id":"2305.18829","repositories_listed":2,"syntology":null},{"url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/surgical-vqla-transformer-with-gated-vision","slug":"surgical-vqla-transformer-with-gated-vision","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-05-19","arxiv_id":"2305.11692","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/surgical-vqla-transformer-with-gated-vision#ran","syntology_url":"https://syntology.ai/paper/2305.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11692"}},"official":{"repos":["longbai1006/surgical-vqla"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tune-mode-convbn-blocks-for-efficient","slug":"tune-mode-convbn-blocks-for-efficient","title":"Efficient ConvBN Blocks for Transfer Learning and Beyond","date":"2023-05-19","arxiv_id":"2305.11624","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tune-mode-convbn-blocks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2305.11624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11624"}},"official":{"repos":["apple/ml-tune-mode-convbn"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/going-denser-with-open-vocabulary-part","slug":"going-denser-with-open-vocabulary-part","title":"Going Denser with Open-Vocabulary Part Segmentation","date":"2023-05-18","arxiv_id":"2305.11173","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/going-denser-with-open-vocabulary-part#ran","syntology_url":"https://syntology.ai/paper/2305.11173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11173"}},"official":{"repos":["facebookresearch/vlpart"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-flying-object-detection-with-yolov8","slug":"real-time-flying-object-detection-with-yolov8","title":"Real-Time Flying Object Detection with YOLOv8","date":"2023-05-17","arxiv_id":"2305.09972","repositories_listed":2,"syntology":null},{"url":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 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) · 3 unverified","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}},"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-bird-eye-view-representation-of","slug":"aligning-bird-eye-view-representation-of","title":"Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene Flow","date":"2023-05-04","arxiv_id":"2305.02909","repositories_listed":2,"syntology":null}],"record_sha256":"f03322cc4bbc3dabf25cda41e5e4ece648656deb944b79b9700d891ee0e377cd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}