{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/multispectral-deep-neural-networks-for","title":"Multispectral Deep Neural Networks for Pedestrian Detection","arxiv_id":"1611.02644","date":"2016-11-08","proceeding":null,"authors":["Jingjing Liu","Shaoting Zhang","Shu Wang","Dimitris N. Metaxas"],"abstract":"Multispectral pedestrian detection is essential for around-the-clock\napplications, e.g., surveillance and autonomous driving. We deeply analyze\nFaster R-CNN for multispectral pedestrian detection task and then model it into\na convolutional network (ConvNet) fusion problem. Further, we discover that\nConvNet-based pedestrian detectors trained by color or thermal images\nseparately provide complementary information in discriminating human instances.\nThus there is a large potential to improve pedestrian detection by using color\nand thermal images in DNNs simultaneously. We carefully design four ConvNet\nfusion architectures that integrate two-branch ConvNets on different DNNs\nstages, all of which yield better performance compared with the baseline\ndetector. Our experimental results on KAIST pedestrian benchmark show that the\nHalfway Fusion model that performs fusion on the middle-level convolutional\nfeatures outperforms the baseline method by 11% and yields a missing rate 3.5%\nlower than the other proposed architectures.","url_abs":"http://arxiv.org/abs/1611.02644v1","url_pdf":"http://arxiv.org/pdf/1611.02644v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multispectral-deep-neural-networks-for","repo_url":"https://github.com/SoonminHwang/rgbt-ped-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multispectral-deep-neural-networks-for","repo_url":"https://github.com/xuez-phd/tfdet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"multispectral-object-detection","task_name":"Multispectral Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-object-detection-on-dronevehicle","task":"2D Object Detection","dataset":"DroneVehicle","model":"HalfwayFusion","rank_in_archive_order":11,"of":11,"metrics":{"Val/mAP50":"68.2"},"uses_additional_data":false},{"leaderboard":"/sota/multispectral-object-detection-on-kaist","task":"Multispectral Object Detection","dataset":"KAIST Multispectral Pedestrian Detection Benchmark","model":"Halfway Fusion","rank_in_archive_order":14,"of":17,"metrics":{"All Miss Rate":"49.18"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-eventped","task":"Object Detection","dataset":"EventPed","model":"Early-Fusion","rank_in_archive_order":5,"of":6,"metrics":{"AP":"47.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-inoutdoor","task":"Object Detection","dataset":"InOutDoor","model":"Early-Fusion","rank_in_archive_order":6,"of":6,"metrics":{"AP":"58.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-stcrowd","task":"Object Detection","dataset":"STCrowd","model":"Early-Fusion","rank_in_archive_order":5,"of":6,"metrics":{"AP":"54.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.02644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.02644"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuez-phd/tfdet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SoonminHwang/rgbt-ped-detection","reach":{"status":"unanswered"}}],"summary":{"ran_honours":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"86db6b7ab1646a7c","entry":"autopad","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"yolov5-master/models/common.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/yolov5-master/models/common.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86db6b7ab1646a7c"}},{"code_sha256_prefix":"16b023786dd03f82","entry":"custom","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"yolov5-master/hubconf.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/yolov5-master/hubconf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"16b023786dd03f82"}},{"code_sha256_prefix":"8ff99a6bd2ebf598","entry":"ordered_yaml_dump","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"mmdetection/.dev_scripts/gather_models.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/mmdetection/.dev_scripts/gather_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ff99a6bd2ebf598"}},{"code_sha256_prefix":"138e112e22b0314e","entry":"process_checkpoint","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"mmdetection/.dev_scripts/gather_models.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/mmdetection/.dev_scripts/gather_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"138e112e22b0314e"}},{"code_sha256_prefix":"386a04c4b6c96c88","entry":"smooth_BCE","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"yolov5-master/utils/loss.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/yolov5-master/utils/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"386a04c4b6c96c88"}},{"code_sha256_prefix":"7d089ddf10054753","entry":"yolov5n","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"yolov5-master/hubconf.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/yolov5-master/hubconf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d089ddf10054753"}},{"code_sha256_prefix":"12f3684bacb256cf","entry":"yolov5s","repo":"xuez-phd/tfdet","repo_kind":"listed","path":"yolov5-master/hubconf.py","file_url":"https://github.com/xuez-phd/tfdet/blob/HEAD/yolov5-master/hubconf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12f3684bacb256cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}