{"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/self-attention-fusion-for-audiovisual-emotion","title":"Self-attention fusion for audiovisual emotion recognition with incomplete data","arxiv_id":"2201.11095","date":"2022-01-26","proceeding":null,"authors":["Kateryna Chumachenko","Alexandros Iosifidis","Moncef Gabbouj"],"abstract":"In this paper, we consider the problem of multimodal data analysis with a use case of audiovisual emotion recognition. We propose an architecture capable of learning from raw data and describe three variants of it with distinct modality fusion mechanisms. While most of the previous works consider the ideal scenario of presence of both modalities at all times during inference, we evaluate the robustness of the model in the unconstrained settings where one modality is absent or noisy, and propose a method to mitigate these limitations in a form of modality dropout. Most importantly, we find that following this approach not only improves performance drastically under the absence/noisy representations of one modality, but also improves the performance in a standard ideal setting, outperforming the competing methods.","url_abs":"https://arxiv.org/abs/2201.11095v1","url_pdf":"https://arxiv.org/pdf/2201.11095v1.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":"self-attention-fusion-for-audiovisual-emotion","repo_url":"https://github.com/katerynaCh/multimodal-emotion-recognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"self-attention-fusion-for-audiovisual-emotion","repo_url":"https://github.com/shravan-18/AVTCA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"facial-emotion-recognition","task_name":"Facial Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-recognition-on-ravdess","task":"Emotion Recognition","dataset":"RAVDESS","model":"Intermediate-Attention-Fusion","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"81.58%"},"uses_additional_data":false},{"leaderboard":"/sota/facial-emotion-recognition-on-ravdess","task":"Facial Emotion Recognition","dataset":"RAVDESS","model":"Intermediate-Transformer-Fusion, visual branch only","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"74.92%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.11095","atlas_url":"https://app.syntology.ai/?focus=2201.11095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11095"}},"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/katerynaCh/multimodal-emotion-recognition","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shravan-18/AVTCA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1},"listed":{"samples":1,"ran":1,"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":"91215ba9fdfd75c0","entry":"calculate_accuracy","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"utils.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/utils.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":"91215ba9fdfd75c0"}},{"code_sha256_prefix":"b78f36e2a6b31a28","entry":"calculate_accuracy1","repo":"shravan-18/AVTCA","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/shravan-18/AVTCA/blob/HEAD/utils.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":"b78f36e2a6b31a28"}},{"code_sha256_prefix":"b9da06d4f527dd6c","entry":"channel_shuffle","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"models/efficientface.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/models/efficientface.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":"b9da06d4f527dd6c"}},{"code_sha256_prefix":"f5dfc77d5b10b99f","entry":"conv1d_block","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"models/multimodalcnn.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/models/multimodalcnn.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":"f5dfc77d5b10b99f"}},{"code_sha256_prefix":"c4e16f9f1a9c4648","entry":"conv1d_block_audio","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"models/multimodalcnn.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/models/multimodalcnn.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":"c4e16f9f1a9c4648"}},{"code_sha256_prefix":"39eace7e2822504f","entry":"drop_path","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"models/transformer_timm.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/models/transformer_timm.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"code_sha256_prefix":"ed1d9f245b263267","entry":"video_loader","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"datasets/ravdess.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/datasets/ravdess.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":"ed1d9f245b263267"}},{"code_sha256_prefix":"a3cf9b5f7f40034b","entry":"depthwise_conv","repo":"katerynaCh/multimodal-emotion-recognition","repo_kind":"official","path":"models/efficientface.py","file_url":"https://github.com/katerynaCh/multimodal-emotion-recognition/blob/HEAD/models/efficientface.py","link_basis":"harvester_set","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":"a3cf9b5f7f40034b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}