{"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/autoad-movie-description-in-context","title":"AutoAD: Movie Description in Context","arxiv_id":"2303.16899","date":"2023-03-29","proceeding":"CVPR 2023 1","authors":["Tengda Han","Max Bain","Arsha Nagrani","Gül Varol","Weidi Xie","Andrew Zisserman"],"abstract":"The objective of this paper is an automatic Audio Description (AD) model that ingests movies and outputs AD in text form. Generating high-quality movie AD is challenging due to the dependency of the descriptions on context, and the limited amount of training data available. In this work, we leverage the power of pretrained foundation models, such as GPT and CLIP, and only train a mapping network that bridges the two models for visually-conditioned text generation. In order to obtain high-quality AD, we make the following four contributions: (i) we incorporate context from the movie clip, AD from previous clips, as well as the subtitles; (ii) we address the lack of training data by pretraining on large-scale datasets, where visual or contextual information is unavailable, e.g. text-only AD without movies or visual captioning datasets without context; (iii) we improve on the currently available AD datasets, by removing label noise in the MAD dataset, and adding character naming information; and (iv) we obtain strong results on the movie AD task compared with previous methods.","url_abs":"https://arxiv.org/abs/2303.16899v1","url_pdf":"https://arxiv.org/pdf/2303.16899v1.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":"autoad-movie-description-in-context","repo_url":"https://github.com/Soldelli/MAD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.16899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16899"}},"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/Soldelli/MAD","reach":null}],"summary":{"ran":4,"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":13,"ran":5,"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":"ba17ac75274936c3","entry":"GCNeXt","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba17ac75274936c3"}},{"code_sha256_prefix":"d23597378a802956","entry":"TanLoss","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d23597378a802956"}},{"code_sha256_prefix":"d7c33caee240d767","entry":"create_mask","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7c33caee240d767"}},{"code_sha256_prefix":"a010bc0f83e92123","entry":"get_graph_feature","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a010bc0f83e92123"}},{"code_sha256_prefix":"0980190c56e21457","entry":"lstm_encoder","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0980190c56e21457"}},{"code_sha256_prefix":"aa1aad1627d524ed","entry":"BidirectionalGraphMatching","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"aa1aad1627d524ed"}},{"code_sha256_prefix":"36488aa50eb9254b","entry":"Graph_Matching_Module","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"36488aa50eb9254b"}},{"code_sha256_prefix":"1d9157325438f0a7","entry":"VLG","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"1d9157325438f0a7"}},{"code_sha256_prefix":"4d3a208217b72e98","entry":"get_graph_feature_plus_scores","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"4d3a208217b72e98"}},{"code_sha256_prefix":"b42d5a59b7ed000a","entry":"get_graph_feature_plus_scores_masked","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"b42d5a59b7ed000a"}},{"code_sha256_prefix":"579f3b13c6e1a270","entry":"knn","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"579f3b13c6e1a270"}},{"code_sha256_prefix":"f0f7bad439eb5f58","entry":"knn_plus_scores","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"f0f7bad439eb5f58"}},{"code_sha256_prefix":"de20b5b31b4f1a7c","entry":"knn_plus_scores_masked","repo":"Soldelli/MAD","repo_kind":"official","path":"baselines/VLG-Net/lib/modeling/model.py","file_url":"https://github.com/Soldelli/MAD/blob/HEAD/baselines/VLG-Net/lib/modeling/model.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":"de20b5b31b4f1a7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}