{"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/mobile-video-object-detection-with-temporally","title":"Mobile Video Object Detection with Temporally-Aware Feature Maps","arxiv_id":"1711.06368","date":"2017-11-17","proceeding":"CVPR 2018 6","authors":["Mason Liu","Menglong Zhu"],"abstract":"This paper introduces an online model for object detection in videos designed\nto run in real-time on low-powered mobile and embedded devices. Our approach\ncombines fast single-image object detection with convolutional long short term\nmemory (LSTM) layers to create an interweaved recurrent-convolutional\narchitecture. Additionally, we propose an efficient Bottleneck-LSTM layer that\nsignificantly reduces computational cost compared to regular LSTMs. Our network\nachieves temporal awareness by using Bottleneck-LSTMs to refine and propagate\nfeature maps across frames. This approach is substantially faster than existing\ndetection methods in video, outperforming the fastest single-frame models in\nmodel size and computational cost while attaining accuracy comparable to much\nmore expensive single-frame models on the Imagenet VID 2015 dataset. Our model\nreaches a real-time inference speed of up to 15 FPS on a mobile CPU.","url_abs":"http://arxiv.org/abs/1711.06368v2","url_pdf":"http://arxiv.org/pdf/1711.06368v2.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":"mobile-video-object-detection-with-temporally","repo_url":"https://github.com/kyscg/tf-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"mobile-video-object-detection-with-temporally","repo_url":"https://github.com/vikrant7/mobile-vod-bottleneck-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mobile-video-object-detection-with-temporally","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"video-object-detection","task_name":"Video Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.06368","atlas_url":"https://app.syntology.ai/?focus=1711.06368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.06368"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/tensorflow/models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vikrant7/mobile-vod-bottleneck-lstm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kyscg/tf-models","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1,"ran_honours":2},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"b8e70c44fecf1dde","entry":"group_annotation_by_class","repo":"vikrant7/mobile-vod-bottleneck-lstm","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/vikrant7/mobile-vod-bottleneck-lstm/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8e70c44fecf1dde"}},{"code_sha256_prefix":"bc785e3bb3be8a15","entry":"val","repo":"vikrant7/mobile-vod-bottleneck-lstm","repo_kind":"listed","path":"train_mvod_basenet.py","file_url":"https://github.com/vikrant7/mobile-vod-bottleneck-lstm/blob/HEAD/train_mvod_basenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc785e3bb3be8a15"}},{"code_sha256_prefix":"0450965c711c906d","entry":"val","repo":"vikrant7/mobile-vod-bottleneck-lstm","repo_kind":"listed","path":"train_mvod_lstm1.py","file_url":"https://github.com/vikrant7/mobile-vod-bottleneck-lstm/blob/HEAD/train_mvod_lstm1.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0450965c711c906d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}