{"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/from-facial-expression-recognition-to","title":"From Facial Expression Recognition to Interpersonal Relation Prediction","arxiv_id":"1609.06426","date":"2016-09-21","proceeding":null,"authors":["Zhanpeng Zhang","Ping Luo","Chen Change Loy","Xiaoou Tang"],"abstract":"Interpersonal relation defines the association, e.g., warm, friendliness, and\ndominance, between two or more people. Motivated by psychological studies, we\ninvestigate if such fine-grained and high-level relation traits can be\ncharacterized and quantified from face images in the wild. We address this\nchallenging problem by first studying a deep network architecture for robust\nrecognition of facial expressions. Unlike existing models that typically learn\nfrom facial expression labels alone, we devise an effective multitask network\nthat is capable of learning from rich auxiliary attributes such as gender, age,\nand head pose, beyond just facial expression data. While conventional\nsupervised training requires datasets with complete labels (e.g., all samples\nmust be labeled with gender, age, and expression), we show that this\nrequirement can be relaxed via a novel attribute propagation method. The\napproach further allows us to leverage the inherent correspondences between\nheterogeneous attribute sources despite the disparate distributions of\ndifferent datasets. With the network we demonstrate state-of-the-art results on\nexisting facial expression recognition benchmarks. To predict inter-personal\nrelation, we use the expression recognition network as branches for a Siamese\nmodel. Extensive experiments show that our model is capable of mining mutual\ncontext of faces for accurate fine-grained interpersonal prediction.","url_abs":"http://arxiv.org/abs/1609.06426v3","url_pdf":"http://arxiv.org/pdf/1609.06426v3.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"cspdarknet53","method_name":"CSPDarknet53"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"cutmix","method_name":"CutMix"},{"method_slug":"dropblock","method_name":"DropBlock"},{"method_slug":"grid-sensitive","method_name":"Grid Sensitive"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pafpn","method_name":"PAFPN"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"yolov3","method_name":"YOLOv3"},{"method_slug":"yolov4","method_name":"YOLOv4"},{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[{"slug":"expw","name":"ExpW","full_name":"Expression in-the-Wild"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.06426","atlas_url":"https://app.syntology.ai/?focus=1609.06426","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}