{"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/coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","arxiv_id":"2011.00597","date":"2020-11-01","proceeding":"NeurIPS 2020 12","authors":["Simon Ging","Mohammadreza Zolfaghari","Hamed Pirsiavash","Thomas Brox"],"abstract":"Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics. In this paper, we propose a Cooperative hierarchical Transformer (COOT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities. The method consists of three major components: an attention-aware feature aggregation layer, which leverages the local temporal context (intra-level, e.g., within a clip), a contextual transformer to learn the interactions between low-level and high-level semantics (inter-level, e.g. clip-video, sentence-paragraph), and a cross-modal cycle-consistency loss to connect video and text. The resulting method compares favorably to the state of the art on several benchmarks while having few parameters. All code is available open-source at https://github.com/gingsi/coot-videotext","url_abs":"https://arxiv.org/abs/2011.00597v1","url_pdf":"https://arxiv.org/pdf/2011.00597v1.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":"coot-cooperative-hierarchical-transformer-for","repo_url":"https://github.com/gingsi/coot-videotext","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"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/video-captioning-on-activitynet-captions","task":"Video Captioning","dataset":"ActivityNet Captions","model":"COOT (ae-test split) - Only Appearance features","rank_in_archive_order":4,"of":5,"metrics":{"BLEU-3":"17.43","BLEU4":"10.85","CIDEr":"28.19","METEOR":"15.99","ROUGE-L":"31.45"},"uses_additional_data":false},{"leaderboard":"/sota/video-captioning-on-youcook2","task":"Video Captioning","dataset":"YouCook2","model":"COOT","rank_in_archive_order":8,"of":14,"metrics":{"BLEU-3":"17.97","BLEU-4":"11.30","CIDEr":"0.57","METEOR":"19.85","ROUGE-L":"37.94"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset":"YouCook2","model":"COOT","rank_in_archive_order":10,"of":16,"metrics":{"text-to-video Median Rank":"9","text-to-video R@1":"16.7","text-to-video R@10":"52.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.00597","atlas_url":"https://app.syntology.ai/?focus=2011.00597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00597"}},"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":"deterministic:regex_extraction","url":"https://github.com/gingsi/coot-videotext","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"1e9fde4500b028fd","entry":"compute_mean_distance_l2","repo":"gingsi/coot-videotext","repo_kind":"official","path":"coot/loss_fn.py","file_url":"https://github.com/gingsi/coot-videotext/blob/HEAD/coot/loss_fn.py","link_basis":"first_harvest_node","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":"1e9fde4500b028fd"}},{"code_sha256_prefix":"80cb4c7392005f27","entry":"compute_mean_distance_negative_l2","repo":"gingsi/coot-videotext","repo_kind":"official","path":"coot/loss_fn.py","file_url":"https://github.com/gingsi/coot-videotext/blob/HEAD/coot/loss_fn.py","link_basis":"first_harvest_node","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":"80cb4c7392005f27"}},{"code_sha256_prefix":"041513be6fc3b19c","entry":"cosine_sim","repo":"gingsi/coot-videotext","repo_kind":"official","path":"coot/loss_fn.py","file_url":"https://github.com/gingsi/coot-videotext/blob/HEAD/coot/loss_fn.py","link_basis":"first_harvest_node","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":"041513be6fc3b19c"}},{"code_sha256_prefix":"bc3ba94eb992c7f0","entry":"get_ffprobe_streams","repo":"gingsi/coot-videotext","repo_kind":"official","path":"extract_frames_from_videos.py","file_url":"https://github.com/gingsi/coot-videotext/blob/HEAD/extract_frames_from_videos.py","link_basis":"first_harvest_node","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":"bc3ba94eb992c7f0"}},{"code_sha256_prefix":"cf593bdd0aacaace","entry":"get_video_info_from_ffprobe_result","repo":"gingsi/coot-videotext","repo_kind":"official","path":"extract_frames_from_videos.py","file_url":"https://github.com/gingsi/coot-videotext/blob/HEAD/extract_frames_from_videos.py","link_basis":"first_harvest_node","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":"cf593bdd0aacaace"}},{"code_sha256_prefix":"fc551850520ce58e","entry":"update_coot_config_from_args","repo":"gingsi/coot-videotext","repo_kind":"official","path":"coot/arguments_coot.py","file_url":"https://github.com/gingsi/coot-videotext/blob/HEAD/coot/arguments_coot.py","link_basis":"first_harvest_node","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":"fc551850520ce58e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}