{"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/bridging-text-and-video-a-universal","title":"Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog","arxiv_id":"2002.00163","date":"2020-02-01","proceeding":null,"authors":["Zekang Li","Zongjia Li","Jinchao Zhang","Yang Feng","Cheng Niu","Jie zhou"],"abstract":"Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multi-task learning method to learn joint representations among different modalities as well as generate informative and fluent responses. Our method extends the natural language generation pre-trained model to multimodal dialogue generation task. Our system achieves the best performance in both objective and subjective evaluations in the challenge.","url_abs":"https://arxiv.org/abs/2002.00163v1","url_pdf":"https://arxiv.org/pdf/2002.00163v1.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":"bridging-text-and-video-a-universal","repo_url":"https://github.com/ictnlp/DSTC8-AVSD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"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":"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.00163","atlas_url":"https://app.syntology.ai/?focus=2002.00163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00163"}},"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/ictnlp/DSTC8-AVSD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":5,"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":"d645589251b05e85","entry":"collate_fn","repo":"ictnlp/DSTC8-AVSD","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"d645589251b05e85"}},{"code_sha256_prefix":"8d23fbe2b99b840b","entry":"gelu","repo":"ictnlp/DSTC8-AVSD","repo_kind":"listed","path":"VideoGPT2.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/VideoGPT2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"code_sha256_prefix":"91592b72681a74a3","entry":"get_dataset","repo":"ictnlp/DSTC8-AVSD","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"91592b72681a74a3"}},{"code_sha256_prefix":"6a891e00701aa131","entry":"tokenize","repo":"ictnlp/DSTC8-AVSD","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"6a891e00701aa131"}},{"code_sha256_prefix":"695eaa24be6f2a1d","entry":"top_filtering","repo":"ictnlp/DSTC8-AVSD","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/generate.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"695eaa24be6f2a1d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}