Situation Recognition with Graph Neural Networks Supplementary Material
نویسندگان
چکیده
We present additional analysis and results of our approach in the supplementary material. First, we analyze the verb prediction performance in Sec. 1. In Sec. 2, we present t-SNE [2] plots to visualize the verb and role embeddings. We present several examples of the influence of different roles on predicting the verb-frame correctly. This is visualized in Sec. 3 through propagation matrices similar to Fig. 7 of the main paper. Finally, in Sec. 4 we include several example predictions that our model makes. 1. Verb Prediction We present the verb prediction accuracies for our fully-connected model on the development set in Fig. 1. The random performance is close to 0.2% (504 verbs). About 22% of all verbs are classified correctly over 50% of the time. These include taxiing, erupting, flossing, microwaving, etc. On the other hand, verbs such as attaching, making, placing can have very different image representations, and show prediction accuracies of less than 10%. Our model helps improve the role-noun predictions by sharing information across all roles. Nevertheless, if the verb is predicted incorrectly, the whole situation is treated as incorrect. Thus, verb prediction performance plays a crucial role.
منابع مشابه
طراحی یک مدل مبتنی بر شبکه‌های عصبی برای شناسایی و تجزیه و تحلیل الگوهای غیرطبیعی در نمودارهای کنترل فرآیند
Neural networks because of their abilities are used to patterns recognition. In statistical process control charts, a common cause variation distort expected form of unnatural patterns and so detection of assignable causes efficiently and precisely in a real-time is difficult. Therefore it would be logical to propose models based neural networks for recognition and analysis of patterns in proce...
متن کاملMulti-Sensor Signal based Situation Recognition with Bayesian Networks
In this paper, we propose an intelligent situation recognition model by collecting and analyzing multiple sensor signals. Multiple sensor signals are collected for fixed time window. A training set of collected sensor data for each situation is provided to K2-learning algorithm to generate Bayesian networks representing causal relationship between sensors for the situation. Statistical characte...
متن کاملEffect of sound classification by neural networks in the recognition of human hearing
In this paper, we focus on two basic issues: (a) the classification of sound by neural networks based on frequency and sound intensity parameters (b) evaluating the health of different human ears as compared to of those a healthy person. Sound classification by a specific feed forward neural network with two inputs as frequency and sound intensity and two hidden layers is proposed. This process...
متن کاملEstimation of Hand Skeletal Postures by Using Deep Convolutional Neural Networks
Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017