{"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/saliency-tubes-visual-explanations-for-spatio","title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","arxiv_id":"1902.01078","date":"2019-02-04","proceeding":null,"authors":["Alexandros Stergiou","Georgios Kapidis","Grigorios Kalliatakis","Christos Chrysoulas","Remco Veltkamp","Ronald Poppe"],"abstract":"Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets. Because of the high level of complexity of these methods, as the convolution operations are also extended to additional dimension in order to extract features from them as well, providing a visualization for the signals that the network interpret as informative, is a challenging task. An effective notion of understanding the network's inner-workings would be to isolate the spatio-temporal regions on the video that the network finds most informative. We propose a method called Saliency Tubes which demonstrate the foremost points and regions in both frame level and over time that are found to be the main focus points of the network. We demonstrate our findings on widely used datasets for third-person and egocentric action classification and enhance the set of methods and visualizations that improve 3D Convolutional Neural Networks (CNNs) intelligibility.","url_abs":"https://arxiv.org/abs/1902.01078v2","url_pdf":"https://arxiv.org/pdf/1902.01078v2.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":"saliency-tubes-visual-explanations-for-spatio","repo_url":"https://github.com/alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.01078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01078"}},"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/alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"8cd5287185382195","entry":"center_crop","repo":"alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions","repo_kind":"official","path":"heat_tubes_mfnet_pytorch.py","file_url":"https://github.com/alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions/blob/HEAD/heat_tubes_mfnet_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd5287185382195"}},{"code_sha256_prefix":"2f0f02510de1622d","entry":"frames_extractor","repo":"alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions","repo_kind":"official","path":"frames.py","file_url":"https://github.com/alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions/blob/HEAD/frames.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f0f02510de1622d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}