Exploiting Negative Evidence for Deep Latent Structured Models
نویسندگان
چکیده
منابع مشابه
Posterior Regularization for Structured Latent Varaible Models
We present posterior regularization, a probabilistic framework for structured, weakly supervised learning. Our framework efficiently incorporates indirect supervision via constraints on posterior distributions of probabilistic models with latent variables. Posterior regularization separates model complexity from the complexity of structural constraints it is desired to satisfy. By directly impo...
متن کاملPosterior Regularization for Structured Latent Variable Models
We present posterior regularization, a probabilistic framework for structured, weakly supervised learning. Our framework efficiently incorporates indirect supervision via constraints on posterior distributions of probabilistic models with latent variables. Posterior regularization separates model complexity from the complexity of structural constraints it is desired to satisfy. By directly impo...
متن کاملProximal Deep Structured Models
Many problems in real-world applications involve predicting continuous-valued random variables that are statistically related. In this paper, we propose a powerful deep structured model that is able to learn complex non-linear functions which encode the dependencies between continuous output variables. We show that inference in our model using proximal methods can be efficiently solved as a fee...
متن کاملLearning Deep Structured Models
Many problems in real-world applications involve predicting several random variables that are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such dependencies. The goal of this paper is to combine MRFs with deep learning to estimate complex representations while taking into account the dependencies between the output random variables. Towards this goa...
متن کاملDeep Structured Models For Group Activity Recognition
Event understanding in videos is a key element of computer vision systems in the context of visual surveillance, human-computer interaction, sports interpretation, and video search and retrieval. The standard and yet state-of-the-art pipeline for activity recognition and interaction description consists of extracting hand-crafted local feature descriptors either densely or at a sparse set of in...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2019
ISSN: 0162-8828,2160-9292,1939-3539
DOI: 10.1109/tpami.2017.2788435