{"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/tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","arxiv_id":"2203.16434","date":"2022-03-30","proceeding":"CVPR 2022 1","authors":["Antoine Yang","Antoine Miech","Josef Sivic","Ivan Laptev","Cordelia Schmid"],"abstract":"We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To address this task, we propose TubeDETR, a transformer-based architecture inspired by the recent success of such models for text-conditioned object detection. Our model notably includes: (i) an efficient video and text encoder that models spatial multi-modal interactions over sparsely sampled frames and (ii) a space-time decoder that jointly performs spatio-temporal localization. We demonstrate the advantage of our proposed components through an extensive ablation study. We also evaluate our full approach on the spatio-temporal video grounding task and demonstrate improvements over the state of the art on the challenging VidSTG and HC-STVG benchmarks. Code and trained models are publicly available at https://antoyang.github.io/tubedetr.html.","url_abs":"https://arxiv.org/abs/2203.16434v2","url_pdf":"https://arxiv.org/pdf/2203.16434v2.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":"tubedetr-spatio-temporal-video-grounding-with","repo_url":"https://github.com/antoyang/TubeDETR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-based-temporal-localization","task_name":"Language-Based Temporal Localization"},{"task_slug":"natural-language-visual-grounding","task_name":"Natural Language Visual Grounding"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"person-centric-visual-grounding","task_name":"Person-centric Visual Grounding"},{"task_slug":"spatio-temporal-video-grounding","task_name":"Spatio-Temporal Video Grounding"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"video-grounding","task_name":"Video Grounding"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/spatio-temporal-video-grounding-on-hc-stvg1","task":"Spatio-Temporal Video Grounding","dataset":"HC-STVG1","model":"TubeDETR","rank_in_archive_order":3,"of":3,"metrics":{"m_vIoU":"32.4","vIoU@0.3":"49.8","vIoU@0.5":"23.5"},"uses_additional_data":false},{"leaderboard":"/sota/spatio-temporal-video-grounding-on-hc-stvg2","task":"Spatio-Temporal Video Grounding","dataset":"HC-STVG2","model":"TubeDETR","rank_in_archive_order":4,"of":4,"metrics":{"Val m_vIoU":"36.4","Val vIoU@0.3":"58.8","Val vIoU@0.5":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/spatio-temporal-video-grounding-on-vidstg","task":"Spatio-Temporal Video Grounding","dataset":"VidSTG","model":"TubeDETR","rank_in_archive_order":3,"of":3,"metrics":{"Declarative m_vIoU":"30.4","Declarative vIoU@0.3":"42.5","Declarative vIoU@0.5":"28.2","Interrogative m_vIoU":"25.7","Interrogative vIoU@0.3":"35.7","Interrogative vIoU@0.5":"23.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.16434","atlas_url":"https://app.syntology.ai/?focus=2203.16434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16434"}},"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/antoyang/TubeDETR","reach":null}],"summary":{"ran":3},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"8a09b495672367c2","entry":"MLP","repo":"antoyang/TubeDETR","repo_kind":"official","path":"models/tubedetr.py","file_url":"https://github.com/antoyang/TubeDETR/blob/HEAD/models/tubedetr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8a09b495672367c2"}},{"code_sha256_prefix":"db74b3e6e32586fb","entry":"NestedTensor","repo":"antoyang/TubeDETR","repo_kind":"official","path":"models/tubedetr.py","file_url":"https://github.com/antoyang/TubeDETR/blob/HEAD/models/tubedetr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"db74b3e6e32586fb"}},{"code_sha256_prefix":"a0312f1fa47cb07e","entry":"TubeDETR","repo":"antoyang/TubeDETR","repo_kind":"official","path":"models/tubedetr.py","file_url":"https://github.com/antoyang/TubeDETR/blob/HEAD/models/tubedetr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0312f1fa47cb07e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}