{"url":"/dataset/sjtu-multispectral-object-detection-smod","name":"SJTU Multispectral Object Detection (SMOD) Dataset","full_name":null,"description_markdown":"We present the SJTU Multispectral Object Detection (SMOD) dataset for detection.\r\nThe dataset has 8676 infrared visible image pairs. Within this dataset, 8042 pedestrians, 10478 riders, 6501 bicycles, and 6422 cars are annotated. The degree of occlusion of all objects is meticulously annotated. The dataset with low sampling rate has dense rider and pedestrian objects and contains rich illumination variations in its 3298 pairs of images of night scenarios.","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/zizhaochen6/sjtu-multispectral-object-detection-smod-dataset","introduced_date":"2024-05-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/amfd-distillation-via-adaptive-multimodal","title":"AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection","first_author":"Zizhao Chen","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"2D Object Detection","url":"/task/2d-object-detection","datasets_with_task":"/datasets/task/2d-object-detection"}],"languages":[],"variants":["SJTU Multispectral Object Detection (SMOD) Dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}