{"url":"/dataset/kaist-multispectral-pedestrian-detection","name":"KAIST Multispectral Pedestrian Detection Benchmark","full_name":null,"description_markdown":"KAIST Multispectral Pedestrian Dataset\r\n\r\nThe KAIST Multispectral Pedestrian Dataset is imaging hardware consisting of a color camera, a thermal camera and a beam splitter to capture the aligned multispectral (RGB color + Thermal) images. With this hardware, we captured various regular traffic scenes at day and night time to consider changes in light conditions. and, consists of 95k color-thermal pairs (640x480, 20Hz) taken from a vehicle. All the pairs are manually annotated (person, people, cyclist) for the total of 103,128 dense annotations and 1,182 unique pedestrians. The annotation includes temporal correspondence between bounding boxes like Caltech Pedestrian Dataset.\r\n\r\nFor more information, read [Multispectral Pedestrian Detection: Benchmark Dataset and Baseline (CVPR 2015)](https://openaccess.thecvf.com/content_cvpr_2015/papers/Hwang_Multispectral_Pedestrian_Detection_2015_CVPR_paper.pdf) or visit [this website](https://soonminhwang.github.io/rgbt-ped-detection/)","description_withheld":null,"homepage":"https://soonminhwang.github.io/rgbt-ped-detection/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Multispectral Object Detection","url":"/task/multispectral-object-detection","datasets_with_task":"/datasets/task/multispectral-object-detection"}],"languages":[],"variants":["KAIST Multispectral Pedestrian Detection Benchmark"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multispectral-object-detection-on-kaist","task":"Multispectral Object Detection","dataset_variant":"KAIST Multispectral Pedestrian Detection Benchmark","rows":17,"metrics":["All Miss Rate","Reasonable Miss Rate"],"first_row_in_archive_order":{"model":"RSDet","paper":"/paper/removal-and-selection-improving-rgb-infrared","metrics":{"All Miss Rate":"24.79"},"code_links":[{"title":"Zhao-Tian-yi/RSDet","url":"https://github.com/Zhao-Tian-yi/RSDet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/unirgb-ir-a-unified-framework-for-visible","title":"UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter Tuning","date":"2024-04-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/insanet-intra-inter-spectral-attention","title":"INSANet: INtra-INter Spectral Attention Network for Effective Feature Fusion of Multispectral Pedestrian Detection","date":"2024-02-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/removal-and-selection-improving-rgb-infrared","title":"Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection","date":"2024-01-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mathbf-c-2-former-calibrated-and","title":"$\\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection","date":"2023-06-28","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/translation-scale-and-rotation-cross-modal","title":"Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection","date":"2022-09-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/confidence-aware-fusion-using-dempster-shafer","title":"Confidence-aware Fusion using Dempster-Shafer Theory for Multispectral Pedestrian Detection","date":"2022-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mlpd-multi-label-pedestrian-detector-in","title":"MLPD: Multi-Label Pedestrian Detector in Multispectral Domain","date":"2021-07-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/guided-attentive-feature-fusion-for","title":"Guided Attentive Feature Fusion for Multispectral Pedestrian Detection","date":"2021-01-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multispectral-fusion-for-object-detection","title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","date":"2020-09-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-multispectral-pedestrian-detection","title":"Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems","date":"2020-08-07","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/the-cross-modality-disparity-problem-in","title":"Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection","date":"2019-01-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cian-cross-image-affinity-net-for-weakly","title":"CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation","date":"2018-11-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multispectral-pedestrian-detection-via","title":"Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation","date":"2018-08-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/illumination-aware-faster-r-cnn-for-robust","title":"Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection","date":"2018-03-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fusion-of-multispectral-data-through","title":"Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection","date":"2018-02-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multispectral-deep-neural-networks-for","title":"Multispectral Deep Neural Networks for Pedestrian Detection","date":"2016-11-08","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-convolutional-networks-for-semantic-1","title":"Fully Convolutional Networks for Semantic Segmentation","date":"2014-11-14","rows_on_this_dataset":1,"code_links":51,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":11,"samples_ran":4,"samples_unverified":7,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}