Multi-label Learning with Missing Values using Combined Facial Action Unit Datasets

• URL: http://arxiv.org/abs/2008.07234v1
• Date: Mon, 17 Aug 2020 11:58:06 GMT
• Title: Multi-label Learning with Missing Values using Combined Facial Action Unit Datasets
• Authors: Jaspar Pahl, Ines Rieger, Dominik Seuss
• Abstract summary: Facial action units allow an objective, standardized description of facial micro movements which can be used to describe emotions in human faces. Annotating data for action units is an expensive and time-consuming task, which leads to a scarce data situation. We present our approach to create a combined database and an algorithm capable of learning under the presence of missing labels.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Facial action units allow an objective, standardized description of facial micro movements which can be used to describe emotions in human faces. Annotating data for action units is an expensive and time-consuming task, which leads to a scarce data situation. By combining multiple datasets from different studies, the amount of training data for a machine learning algorithm can be increased in order to create robust models for automated, multi-label action unit detection. However, every study annotates different action units, leading to a tremendous amount of missing labels in a combined database. In this work, we examine this challenge and present our approach to create a combined database and an algorithm capable of learning under the presence of missing labels without inferring their values. Our approach shows competitive performance compared to recent competitions in action unit detection.

Related papers

• Automatic Identification and Visualization of Group Training Activities Using Wearable Data [7.130450173185638]
  Human Activity Recognition (HAR) identifies daily activities from time-series data collected by wearable devices like smartwatches. This paper presents a comprehensive framework for imputing, analyzing, and identifying activities from wearable data. Our approach is based on data collected from 135 soldiers wearing Garmin 55 smartwatches over six months.
  arXiv  Detail & Related papers  (2024-10-07T19:35:15Z)
• The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks [4.971065912401385]
  We propose Dual-VCLIP, a unified approach for zero-shot multi-label action recognition. Dual-VCLIP enhances VCLIP, a zero-shot action recognition method, with the DualCoOp method for multi-label image classification. We validate our method on the Charades dataset that includes a majority of object-based actions.
  arXiv  Detail & Related papers  (2024-05-14T15:28:48Z)
• Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond [62.406687088097605]
  Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space. We show that MTL can be successful with classification tasks with little, or non-overlapping annotations. We propose a novel approach, where knowledge exchange is enabled between the tasks via distribution matching.
  arXiv  Detail & Related papers  (2024-01-02T14:18:11Z)
• Weakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables [2.398608007786179]
  We propose a weakly supervised multi-output siamese network that learns to map the data into multiple representation spaces. The representation of the data samples are positioned in the space such that the data with the same semantic meaning in that aspect are closely located to each other.
  arXiv  Detail & Related papers  (2023-08-06T08:20:07Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• Multi-dataset Training of Transformers for Robust Action Recognition [75.5695991766902]
  We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2.
  arXiv  Detail & Related papers  (2022-09-26T01:30:43Z)
• An Exploration of Active Learning for Affective Digital Phenotyping [4.790279027864381]
  Active learning is a paradigm for using algorithms to computationally select a useful subset of data points to label. We explore active learning for naturalistic computer vision emotion data, a particularly heterogeneous and complex data space. We find that active learning using information generated during gameplay slightly outperforms random selection of the same number of labeled frames.
  arXiv  Detail & Related papers  (2022-04-05T01:01:32Z)
• Audio-Visual Fusion Layers for Event Type Aware Video Recognition [86.22811405685681]
  We propose a new model to address the multisensory integration problem with individual event-specific layers in a multi-task learning scheme. We show that our network is formulated with single labels, but it can output additional true multi-labels to represent the given videos.
  arXiv  Detail & Related papers  (2022-02-12T02:56:22Z)
• Diverse Complexity Measures for Dataset Curation in Self-driving [80.55417232642124]
  We propose a new data selection method that exploits a diverse set of criteria that quantize interestingness of traffic scenes. Our experiments show that the proposed curation pipeline is able to select datasets that lead to better generalization and higher performance.
  arXiv  Detail & Related papers  (2021-01-16T23:45:02Z)
• Visual Imitation Made Easy [102.36509665008732]
  We present an alternate interface for imitation that simplifies the data collection process while allowing for easy transfer to robots. We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector. We experimentally evaluate on two challenging tasks: non-prehensile pushing and prehensile stacking, with 1000 diverse demonstrations for each task.
  arXiv  Detail & Related papers  (2020-08-11T17:58:50Z)
• Unique Class Group Based Multi-Label Balancing Optimizer for Action Unit Detection [0.0]
  We show how optimized balancing and then augmentation can improve Action Unit detection. We ranked third in the Affective Behavior Analysis in-the-wild (ABAW) challenge for the Action Unit detection task.
  arXiv  Detail & Related papers  (2020-03-05T15:34:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.