{"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/7","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":7,"pages_in_order":110,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/object-detection/papers/8","papers":[{"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},{"url":"/paper/samrs-scaling-up-remote-sensing-segmentation","slug":"samrs-scaling-up-remote-sensing-segmentation","title":"SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model","date":"2023-05-03","arxiv_id":"2305.02034","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/samrs-scaling-up-remote-sensing-segmentation#ran","syntology_url":"https://syntology.ai/paper/2305.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02034"}},"official":{"repos":["vitae-transformer/samrs"],"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/once-detected-never-lost-surpassing-human","slug":"once-detected-never-lost-surpassing-human","title":"Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection","date":"2023-04-24","arxiv_id":"2304.12315","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/once-detected-never-lost-surpassing-human#ran","syntology_url":"https://syntology.ai/paper/2304.12315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12315"}},"official":{"repos":["tusen-ai/sst"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/point-supervised-single-cell-segmentation-via","slug":"point-supervised-single-cell-segmentation-via","title":"Point-supervised Single-cell Segmentation via Collaborative Knowledge Sharing","date":"2023-04-20","arxiv_id":"2304.10671","repositories_listed":2,"syntology":null},{"url":"/paper/radar-camera-fusion-for-object-detection-and","slug":"radar-camera-fusion-for-object-detection-and","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","date":"2023-04-20","arxiv_id":"2304.10410","repositories_listed":2,"syntology":null},{"url":"/paper/bevsimdet-simulated-multi-modal-distillation","slug":"bevsimdet-simulated-multi-modal-distillation","title":"SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection","date":"2023-03-29","arxiv_id":"2303.16818","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bevsimdet-simulated-multi-modal-distillation#ran","syntology_url":"https://syntology.ai/paper/2303.16818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16818"}},"official":{"repos":["vitae-transformer/bevsimdet","vitae-transformer/simdistill"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-wildlife-image-classification-an","slug":"automated-wildlife-image-classification-an","title":"Automated wildlife image classification: An active learning tool for ecological applications","date":"2023-03-28","arxiv_id":"2303.15823","repositories_listed":2,"syntology":null},{"url":"/paper/dense-distinct-query-for-end-to-end-object","slug":"dense-distinct-query-for-end-to-end-object","title":"Dense Distinct Query for End-to-End Object Detection","date":"2023-03-22","arxiv_id":"2303.12776","repositories_listed":2,"syntology":null},{"url":"/paper/epro-pnp-generalized-end-to-end-probabilistic-1","slug":"epro-pnp-generalized-end-to-end-probabilistic-1","title":"EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation","date":"2023-03-22","arxiv_id":"2303.12787","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/epro-pnp-generalized-end-to-end-probabilistic-1#ran","syntology_url":"https://syntology.ai/paper/2303.12787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12787"}},"official":{"repos":["tjiiv-cprg/epro-pnp-v2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/rigidity-aware-detection-for-6d-object-pose","slug":"rigidity-aware-detection-for-6d-object-pose","title":"Rigidity-Aware Detection for 6D Object Pose Estimation","date":"2023-03-22","arxiv_id":"2303.12396","repositories_listed":2,"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/rigidity-aware-detection-for-6d-object-pose#ran","syntology_url":"https://syntology.ai/paper/2303.12396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12396"}},"official":{"repos":["yanghai-1218/radet"],"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/spherical-transformer-for-lidar-based-3d","slug":"spherical-transformer-for-lidar-based-3d","title":"Spherical Transformer for LiDAR-based 3D Recognition","date":"2023-03-22","arxiv_id":"2303.12766","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":5,"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) · 4 unverified","sample_list":"/paper/spherical-transformer-for-lidar-based-3d#ran","syntology_url":"https://syntology.ai/paper/2303.12766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12766"}},"official":{"repos":["dvlab-research/sphereformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-feature-distillation-for-zero-shot","slug":"efficient-feature-distillation-for-zero-shot","title":"Efficient Feature Distillation for Zero-shot Annotation Object Detection","date":"2023-03-21","arxiv_id":"2303.12145","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-object-centric-temporal-modeling","slug":"exploring-object-centric-temporal-modeling","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","date":"2023-03-21","arxiv_id":"2303.11926","repositories_listed":2,"syntology":null},{"url":"/paper/vimi-vehicle-infrastructure-multi-view","slug":"vimi-vehicle-infrastructure-multi-view","title":"VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection","date":"2023-03-20","arxiv_id":"2303.10975","repositories_listed":2,"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/vimi-vehicle-infrastructure-multi-view#ran","syntology_url":"https://syntology.ai/paper/2303.10975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10975"}},"official":{"repos":["bosszhe/vimi"],"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/voxelnext-fully-sparse-voxelnet-for-3d-object-1","slug":"voxelnext-fully-sparse-voxelnet-for-3d-object-1","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","date":"2023-03-20","arxiv_id":"2303.11301","repositories_listed":2,"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/voxelnext-fully-sparse-voxelnet-for-3d-object-1#ran","syntology_url":"https://syntology.ai/paper/2303.11301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11301"}},"official":{"repos":["dvlab-research/VoxelNeXt"],"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/cape-camera-view-position-embedding-for-multi","slug":"cape-camera-view-position-embedding-for-multi","title":"CAPE: Camera View Position Embedding for Multi-View 3D Object Detection","date":"2023-03-17","arxiv_id":"2303.10209","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":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/cape-camera-view-position-embedding-for-multi#ran","syntology_url":"https://syntology.ai/paper/2303.10209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10209"}},"official":{"repos":["kaixinbear/CAPE","PaddlePaddle/Paddle3D"],"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/a-framework-for-real-time-object-detection","slug":"a-framework-for-real-time-object-detection","title":"Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy","date":"2023-03-16","arxiv_id":"2303.09190","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-model-ensemble-in-transfer-based","slug":"rethinking-model-ensemble-in-transfer-based","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","date":"2023-03-16","arxiv_id":"2303.09105","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/rethinking-model-ensemble-in-transfer-based#ran","syntology_url":"https://syntology.ai/paper/2303.09105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09105"}},"official":{"repos":["huanranchen/AdversarialAttacks"],"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/surroundocc-multi-camera-3d-occupancy","slug":"surroundocc-multi-camera-3d-occupancy","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","date":"2023-03-16","arxiv_id":"2303.09551","repositories_listed":2,"syntology":{"n":24,"n_ran":18,"n_constructed":0,"n_ran_checked":8,"n_instrument":10,"n_unverified":6,"n_honours":4,"n_violates":0,"n_no_contract":4,"n_pointer_only":21,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/surroundocc-multi-camera-3d-occupancy#ran","syntology_url":"https://syntology.ai/paper/2303.09551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09551"}},"official":{"repos":["weiyithu/surroundocc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-linguistic-causal-intervention-for","slug":"visual-linguistic-causal-intervention-for","title":"Cross-Modal Causal Intervention for Medical Report Generation","date":"2023-03-16","arxiv_id":"2303.09117","repositories_listed":2,"syntology":null},{"url":"/paper/v2v4real-a-real-world-large-scale-dataset-for","slug":"v2v4real-a-real-world-large-scale-dataset-for","title":"V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception","date":"2023-03-14","arxiv_id":"2303.07601","repositories_listed":2,"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/v2v4real-a-real-world-large-scale-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2303.07601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07601"}},"official":{"repos":["ucla-mobility/v2v4real"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/diffusion-based-hierarchical-multi-label","slug":"diffusion-based-hierarchical-multi-label","title":"Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rays","date":"2023-03-11","arxiv_id":"2303.06500","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":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/diffusion-based-hierarchical-multi-label#ran","syntology_url":"https://syntology.ai/paper/2303.06500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06500"}},"official":{"repos":["ibrahimethemhamamci/hierarchicaldet"],"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/tau-a-framework-for-video-based-traffic","slug":"tau-a-framework-for-video-based-traffic","title":"TAU: A Framework for Video-Based Traffic Analytics Leveraging Artificial Intelligence and Unmanned Aerial Systems","date":"2023-03-01","arxiv_id":"2303.00337","repositories_listed":2,"syntology":null},{"url":"/paper/memory-aided-contrastive-consensus-learning","slug":"memory-aided-contrastive-consensus-learning","title":"Memory-aided Contrastive Consensus Learning for Co-salient Object Detection","date":"2023-02-28","arxiv_id":"2302.14485","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/memory-aided-contrastive-consensus-learning#ran","syntology_url":"https://syntology.ai/paper/2302.14485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14485"}},"official":{"repos":["zhengpeng7/mccl"],"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/divotrack-a-novel-dataset-and-baseline-method","slug":"divotrack-a-novel-dataset-and-baseline-method","title":"DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes","date":"2023-02-15","arxiv_id":"2302.07676","repositories_listed":2,"syntology":null},{"url":"/paper/cfnet-cascade-fusion-network-for-dense","slug":"cfnet-cascade-fusion-network-for-dense","title":"CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction","date":"2023-02-13","arxiv_id":"2302.06052","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":12,"phrase":"10 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cfnet-cascade-fusion-network-for-dense#ran","syntology_url":"https://syntology.ai/paper/2302.06052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06052"}},"official":{"repos":["zhanggang001/cednet","zhanggang001/cfnet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-aware-ab3dmot-by-variational-3d","slug":"uncertainty-aware-ab3dmot-by-variational-3d","title":"Uncertainty-Aware AB3DMOT by Variational 3D Object Detection","date":"2023-02-12","arxiv_id":"2302.05923","repositories_listed":2,"syntology":null},{"url":"/paper/local-contrast-and-global-contextual","slug":"local-contrast-and-global-contextual","title":"Local Contrast and Global Contextual Information Make Infrared Small Object Salient Again","date":"2023-01-28","arxiv_id":"2301.12093","repositories_listed":2,"syntology":null},{"url":"/paper/cut-and-learn-for-unsupervised-object","slug":"cut-and-learn-for-unsupervised-object","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","date":"2023-01-26","arxiv_id":"2301.11320","repositories_listed":2,"syntology":null},{"url":"/paper/object-detection-performance-variation-on","slug":"object-detection-performance-variation-on","title":"Object Detection performance variation on compressed satellite image datasets with iquaflow","date":"2023-01-14","arxiv_id":"2301.05892","repositories_listed":2,"syntology":null},{"url":"/paper/wildfire-smoke-detection-with-computer-vision","slug":"wildfire-smoke-detection-with-computer-vision","title":"Wildfire Smoke Detection with Computer Vision","date":"2023-01-12","arxiv_id":"2301.05070","repositories_listed":2,"syntology":null},{"url":"/paper/designing-bert-for-convolutional-networks","slug":"designing-bert-for-convolutional-networks","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","date":"2023-01-09","arxiv_id":"2301.03580","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"13 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/designing-bert-for-convolutional-networks#ran","syntology_url":"https://syntology.ai/paper/2301.03580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.03580"}},"official":{"repos":["keyu-tian/spark"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/the-cropandweed-dataset-a-multi-modal","slug":"the-cropandweed-dataset-a-multi-modal","title":"The CropAndWeed Dataset: A Multi-Modal Learning Approach for Efficient Crop and Weed Manipulation","date":"2023-01-06","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/super-sparse-3d-object-detection","slug":"super-sparse-3d-object-detection","title":"Super Sparse 3D Object Detection","date":"2023-01-05","arxiv_id":"2301.02562","repositories_listed":2,"syntology":null},{"url":"/paper/motion-based-post-processing-using-kalman","slug":"motion-based-post-processing-using-kalman","title":"Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles","date":"2023-01-04","arxiv_id":"2301.01482","repositories_listed":2,"syntology":null},{"url":"/paper/cross-modal-transformer-via-coordinates","slug":"cross-modal-transformer-via-coordinates","title":"Cross Modal Transformer: Towards Fast and Robust 3D Object Detection","date":"2023-01-03","arxiv_id":"2301.01283","repositories_listed":2,"syntology":null},{"url":"/paper/enhanced-training-of-query-based-object","slug":"enhanced-training-of-query-based-object","title":"Enhanced Training of Query-Based Object Detection via Selective Query Recollection","date":"2022-12-15","arxiv_id":"2212.07593","repositories_listed":2,"syntology":null},{"url":"/paper/gpvit-a-high-resolution-non-hierarchical","slug":"gpvit-a-high-resolution-non-hierarchical","title":"GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation","date":"2022-12-13","arxiv_id":"2212.06795","repositories_listed":2,"syntology":null},{"url":"/paper/comparison-of-deep-object-detectors-on-a-new","slug":"comparison-of-deep-object-detectors-on-a-new","title":"Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset","date":"2022-12-12","arxiv_id":"2212.06218","repositories_listed":2,"syntology":null},{"url":"/paper/x-paste-revisit-copy-paste-at-scale-with-clip","slug":"x-paste-revisit-copy-paste-at-scale-with-clip","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","date":"2022-12-07","arxiv_id":"2212.03863","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/x-paste-revisit-copy-paste-at-scale-with-clip#ran","syntology_url":"https://syntology.ai/paper/2212.03863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03863"}},"official":{"repos":["yoctta/xpaste"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/conv2former-a-simple-transformer-style","slug":"conv2former-a-simple-transformer-style","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","date":"2022-11-22","arxiv_id":"2211.11943","repositories_listed":2,"syntology":null},{"url":"/paper/nerf-rpn-a-general-framework-for-object","slug":"nerf-rpn-a-general-framework-for-object","title":"NeRF-RPN: A general framework for object detection in NeRFs","date":"2022-11-21","arxiv_id":"2211.11646","repositories_listed":2,"syntology":null},{"url":"/paper/pointclip-v2-adapting-clip-for-powerful-3d","slug":"pointclip-v2-adapting-clip-for-powerful-3d","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","date":"2022-11-21","arxiv_id":"2211.11682","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pointclip-v2-adapting-clip-for-powerful-3d#ran","syntology_url":"https://syntology.ai/paper/2211.11682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11682"}},"official":{"repos":["yangyangyang127/pointclip_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/simultaneous-multiple-object-detection-and","slug":"simultaneous-multiple-object-detection-and","title":"Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision","date":"2022-11-21","arxiv_id":"2211.11188","repositories_listed":2,"syntology":null},{"url":"/paper/domain-adaptive-self-supervised-pre-training","slug":"domain-adaptive-self-supervised-pre-training","title":"Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings","date":"2022-11-19","arxiv_id":"2211.10641","repositories_listed":2,"syntology":null},{"url":"/paper/matrixvt-efficient-multi-camera-to-bev","slug":"matrixvt-efficient-multi-camera-to-bev","title":"MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception","date":"2022-11-19","arxiv_id":"2211.10593","repositories_listed":2,"syntology":null},{"url":"/paper/internvideo-ego4d-a-pack-of-champion","slug":"internvideo-ego4d-a-pack-of-champion","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","date":"2022-11-17","arxiv_id":"2211.09529","repositories_listed":2,"syntology":null},{"url":"/paper/smiletrack-similarity-learning-for-multiple","slug":"smiletrack-similarity-learning-for-multiple","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","date":"2022-11-16","arxiv_id":"2211.08824","repositories_listed":2,"syntology":null},{"url":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","slug":"pp-yoloe-r-an-efficient-anchor-free-rotated","title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","date":"2022-11-04","arxiv_id":"2211.02386","repositories_listed":2,"syntology":null},{"url":"/paper/towards-few-shot-open-set-object-detection","slug":"towards-few-shot-open-set-object-detection","title":"Towards Generalized Few-Shot Open-Set Object Detection","date":"2022-10-28","arxiv_id":"2210.15996","repositories_listed":2,"syntology":null},{"url":"/paper/latency-aware-spatial-wise-dynamic-networks","slug":"latency-aware-spatial-wise-dynamic-networks","title":"Latency-aware Spatial-wise Dynamic Networks","date":"2022-10-12","arxiv_id":"2210.06223","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/latency-aware-spatial-wise-dynamic-networks#ran","syntology_url":"https://syntology.ai/paper/2210.06223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06223"}},"official":{"repos":["leaplabthu/lasnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-granularity-cross-modal-alignment-for","slug":"multi-granularity-cross-modal-alignment-for","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","date":"2022-10-12","arxiv_id":"2210.06044","repositories_listed":2,"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/multi-granularity-cross-modal-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2210.06044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06044"}},"official":{"repos":["fuying-wang/mgca"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/does-thermal-really-always-matter-for-rgb-t","slug":"does-thermal-really-always-matter-for-rgb-t","title":"Does Thermal Really Always Matter for RGB-T Salient Object Detection?","date":"2022-10-09","arxiv_id":"2210.04266","repositories_listed":2,"syntology":null},{"url":"/paper/bridged-transformer-for-vision-and-point-1","slug":"bridged-transformer-for-vision-and-point-1","title":"Bridged Transformer for Vision and Point Cloud 3D Object Detection","date":"2022-10-04","arxiv_id":"2210.01391","repositories_listed":2,"syntology":null},{"url":"/paper/moat-alternating-mobile-convolution-and","slug":"moat-alternating-mobile-convolution-and","title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","date":"2022-10-04","arxiv_id":"2210.01820","repositories_listed":2,"syntology":null},{"url":"/paper/dotie-detecting-objects-through-temporal","slug":"dotie-detecting-objects-through-temporal","title":"DOTIE -- Detecting Objects through Temporal Isolation of Events using a Spiking Architecture","date":"2022-10-03","arxiv_id":"2210.00975","repositories_listed":2,"syntology":null},{"url":"/paper/mobilevitv3-mobile-friendly-vision","slug":"mobilevitv3-mobile-friendly-vision","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features","date":"2022-09-30","arxiv_id":"2209.15159","repositories_listed":2,"syntology":null},{"url":"/paper/dpnet-dual-path-network-for-real-time-object","slug":"dpnet-dual-path-network-for-real-time-object","title":"DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention","date":"2022-09-28","arxiv_id":"2209.13933","repositories_listed":2,"syntology":null},{"url":"/paper/obj2seq-formatting-objects-as-sequences-with","slug":"obj2seq-formatting-objects-as-sequences-with","title":"Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks","date":"2022-09-28","arxiv_id":"2209.13948","repositories_listed":2,"syntology":null},{"url":"/paper/sapa-similarity-aware-point-affiliation-for","slug":"sapa-similarity-aware-point-affiliation-for","title":"SAPA: Similarity-Aware Point Affiliation for Feature Upsampling","date":"2022-09-26","arxiv_id":"2209.12866","repositories_listed":2,"syntology":null},{"url":"/paper/tad-a-large-scale-benchmark-for-traffic","slug":"tad-a-large-scale-benchmark-for-traffic","title":"TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance","date":"2022-09-26","arxiv_id":"2209.12386","repositories_listed":2,"syntology":null},{"url":"/paper/iou-enhanced-attention-for-end-to-end-task","slug":"iou-enhanced-attention-for-end-to-end-task","title":"IoU-Enhanced Attention for End-to-End Task Specific Object Detection","date":"2022-09-21","arxiv_id":"2209.10391","repositories_listed":2,"syntology":null},{"url":"/paper/a-dataset-for-analysing-complex-document","slug":"a-dataset-for-analysing-complex-document","title":"A Dataset for Analysing Complex Document Layouts in the Digital Humanities and Its Evaluation with Krippendorff’s Alpha","date":"2022-09-20","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-graph-message-passing-networks-for","slug":"dynamic-graph-message-passing-networks-for","title":"Dynamic Graph Message Passing Networks for Visual Recognition","date":"2022-09-20","arxiv_id":"2209.09760","repositories_listed":2,"syntology":null},{"url":"/paper/rgb-event-fusion-for-moving-object-detection","slug":"rgb-event-fusion-for-moving-object-detection","title":"RGB-Event Fusion for Moving Object Detection in Autonomous Driving","date":"2022-09-17","arxiv_id":"2209.08323","repositories_listed":2,"syntology":null}],"record_sha256":"80e02531ed78bb441a4645aca837a59664e2ff3339e77c40253bf5bf725304ca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}