{"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/on-vision-features-in-multimodal-machine-1","title":"On Vision Features in Multimodal Machine Translation","arxiv_id":"2203.09173","date":"2022-03-17","proceeding":"ACL 2022 5","authors":["Bei Li","Chuanhao Lv","Zefan Zhou","Tao Zhou","Tong Xiao","Anxiang Ma","Jingbo Zhu"],"abstract":"Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular in computer vision, we experiment with various strong models (such as Vision Transformer) and enhanced features (such as object-detection and image captioning). We develop a selective attention model to study the patch-level contribution of an image in MMT. On detailed probing tasks, we find that stronger vision models are helpful for learning translation from the visual modality. Our results also suggest the need of carefully examining MMT models, especially when current benchmarks are small-scale and biased. Our code could be found at \\url{https://github.com/libeineu/fairseq_mmt}.","url_abs":"https://arxiv.org/abs/2203.09173v1","url_pdf":"https://arxiv.org/pdf/2203.09173v1.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":"on-vision-features-in-multimodal-machine-1","repo_url":"https://github.com/libeineu/fairseq_mmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"on-vision-features-in-multimodal-machine-1","repo_url":"https://github.com/libeineu/mmt-vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multimodal-machine-translation","task_name":"Multimodal Machine Translation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"translation","task_name":"Translation"},{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.09173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09173"}},"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":"deterministic:regex_extraction","url":"https://github.com/libeineu/fairseq_mmt","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"0aea38188350e4a6","entry":"FairseqIncrementalState","repo":"libeineu/fairseq_mmt","repo_kind":"official","path":"fairseq/modules/selective_attention.py","file_url":"https://github.com/libeineu/fairseq_mmt/blob/HEAD/fairseq/modules/selective_attention.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":"0aea38188350e4a6"}},{"code_sha256_prefix":"1c080baa3e6b2197","entry":"with_incremental_state","repo":"libeineu/fairseq_mmt","repo_kind":"official","path":"fairseq/modules/selective_attention.py","file_url":"https://github.com/libeineu/fairseq_mmt/blob/HEAD/fairseq/modules/selective_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c080baa3e6b2197"}},{"code_sha256_prefix":"67a11ef05c68a35c","entry":"SelectiveAttention","repo":"libeineu/fairseq_mmt","repo_kind":"official","path":"fairseq/modules/selective_attention.py","file_url":"https://github.com/libeineu/fairseq_mmt/blob/HEAD/fairseq/modules/selective_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":"67a11ef05c68a35c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}