{"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/a-better-use-of-audio-visual-cues-dense-video","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","arxiv_id":"2005.08271","date":"2020-05-17","proceeding":null,"authors":["Vladimir Iashin","Esa Rahtu"],"abstract":"Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a few prior works have utilized both modalities, yet they show poor results or demonstrate the importance on a dataset with a specific domain. In this paper, we introduce Bi-modal Transformer which generalizes the Transformer architecture for a bi-modal input. We show the effectiveness of the proposed model with audio and visual modalities on the dense video captioning task, yet the module is capable of digesting any two modalities in a sequence-to-sequence task. We also show that the pre-trained bi-modal encoder as a part of the bi-modal transformer can be used as a feature extractor for a simple proposal generation module. The performance is demonstrated on a challenging ActivityNet Captions dataset where our model achieves outstanding performance. The code is available: v-iashin.github.io/bmt","url_abs":"https://arxiv.org/abs/2005.08271v2","url_pdf":"https://arxiv.org/pdf/2005.08271v2.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":"a-better-use-of-audio-visual-cues-dense-video","repo_url":"https://github.com/v-iashin/BMT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-better-use-of-audio-visual-cues-dense-video","repo_url":"https://github.com/v-iashin/video_features","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dense-video-captioning","task_name":"Dense Video Captioning"},{"task_slug":"temporal-action-proposal-generation","task_name":"Temporal Action Proposal Generation"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"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":"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":"relu","method_name":"ReLU"},{"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/dense-video-captioning-on-activitynet","task":"Dense Video Captioning","dataset":"ActivityNet Captions","model":"BMT","rank_in_archive_order":9,"of":12,"metrics":{"BLEU-3":"3.84","BLEU-4":"1.88","METEOR":"8.44"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-proposal-generation-on-1","task":"Temporal Action Proposal Generation","dataset":"ActivityNet Captions","model":"BMT","rank_in_archive_order":1,"of":1,"metrics":{"Average F1":"60.27","Average Precision":"48.23","Average Recall":"80.31"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.08271","atlas_url":"https://app.syntology.ai/?focus=2005.08271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08271"}},"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/v-iashin/video_features","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/v-iashin/BMT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"c695e53ea4b93d41","entry":"attention","repo":"v-iashin/BMT","repo_kind":"official","path":"model/multihead_attention.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/model/multihead_attention.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":"c695e53ea4b93d41"}},{"code_sha256_prefix":"ef3fdeeb802b1518","entry":"clone","repo":"v-iashin/BMT","repo_kind":"official","path":"model/blocks.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/model/blocks.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":"ef3fdeeb802b1518"}},{"code_sha256_prefix":"451d121f2b589006","entry":"crop_a_segment","repo":"v-iashin/BMT","repo_kind":"official","path":"datasets/load_features.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/datasets/load_features.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":"451d121f2b589006"}},{"code_sha256_prefix":"ab36dd74263d9df3","entry":"fill_missing_features","repo":"v-iashin/BMT","repo_kind":"official","path":"datasets/load_features.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/datasets/load_features.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":"ab36dd74263d9df3"}},{"code_sha256_prefix":"05c96f6971669d61","entry":"mask","repo":"v-iashin/BMT","repo_kind":"official","path":"model/masking.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/model/masking.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":"05c96f6971669d61"}},{"code_sha256_prefix":"609f389f389b3641","entry":"pad_segment","repo":"v-iashin/BMT","repo_kind":"official","path":"datasets/load_features.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/datasets/load_features.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":"609f389f389b3641"}},{"code_sha256_prefix":"34de23e6c8ad136c","entry":"subsequent_mask","repo":"v-iashin/BMT","repo_kind":"official","path":"model/masking.py","file_url":"https://github.com/v-iashin/BMT/blob/HEAD/model/masking.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":"34de23e6c8ad136c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}