{"url":"/method/fga","slug":"fga","name":"FGA","full_name":"Factor Graph Attention","full_name_withheld":false,"description_markdown":"A general multimodal attention unit for any number of modalities. Graphical models inspire it, i.e., it infers several attention beliefs via aggregated interaction messages.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Factor Graph Attention","paper":"/paper/factor-graph-attention","first_author":"Idan Schwartz","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/factor-graph-attention"},"source":{"url":"https://arxiv.org/abs/1904.05880v3","title":"Factor Graph Attention","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/idansc/fga/blob/master/atten.py","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Attention","url":"/methods/category/attention","pwc_aliases":[]}],"n_papers_tagged":9,"archive_num_papers":9,"papers_newest_first":[{"paper":"/paper/sad-net-a-full-spectral-self-attention-detail","title":"SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing","date":"2025-04-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models","date":"2024-07-25","arxiv_id":"2407.17797","n_code_links":0,"syntology":null},{"paper":null,"title":"FGA: Fourier-Guided Attention Network for Crowd Count Estimation","date":"2024-07-08","arxiv_id":"2407.06110","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi Loss-based Feature Fusion and Top Two Voting Ensemble Decision Strategy for Facial Expression Recognition in the Wild","date":"2023-11-06","arxiv_id":"2311.03478","n_code_links":0,"syntology":null},{"paper":"/paper/towards-fair-evaluation-of-dialogue-state","title":"Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances","date":"2022-04-07","arxiv_id":"2204.03375","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-baseline-for-audio-visual-scene-1","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","date":"2019-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-baseline-for-audio-visual-scene","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","date":"2019-04-11","arxiv_id":"1904.05876","n_code_links":1,"syntology":null},{"paper":"/paper/factor-graph-attention","title":"Factor Graph Attention","date":"2019-04-11","arxiv_id":"1904.05880","n_code_links":1,"syntology":null},{"paper":"/paper/high-order-attention-models-for-visual","title":"High-Order Attention Models for Visual Question Answering","date":"2017-11-12","arxiv_id":"1711.04323","n_code_links":1,"syntology":null}],"papers_shown":9,"tasks":[{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":2},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":2},{"task":"/task/crowd-counting","name":"Crowd Counting","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/dialogue-state-tracking","name":"Dialogue State Tracking","papers":1},{"task":"/task/facial-expression-recognition-1","name":"Facial Expression Recognition","papers":1},{"task":"/task/facial-expression-recognition","name":"Facial Expression Recognition (FER)","papers":1},{"task":"/task/graph-attention","name":"Graph Attention","papers":1},{"task":"/task/image-dehazing","name":"Image Dehazing","papers":1},{"task":"/task/model-selection","name":"Model Selection","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/scene-aware-dialogue","name":"Scene-Aware Dialogue","papers":1},{"task":"/task/single-image-dehazing","name":"Single Image Dehazing","papers":1},{"task":"/task/visual-dialogue","name":"Visual Dialog","papers":1},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":1},{"task":"/task/multimodal-interaction","name":"multimodal interaction","papers":1}],"tasks_shown":17,"n_tasks":17,"usage_by_year":[{"year":"2017","papers":1},{"year":"2019","papers":3},{"year":"2022","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":2},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/fga"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}