Object and Action Classification with Latent Variables
نویسندگان
چکیده
In this paper we address the problem of classifying objects (e.g. person or car) and actions (e.g. hugging or eating) [2]. The more successful methods are based on a uniform pyramidal representation (SPM) built on a visual word vocabulary [1]. In this paper, we augment the classification by adding more flexible spatial information. This will be formulated more generally as inferring additional unobserved or ‘latent’ dependent parameters. In particular, we focus on two such types of parameters:
منابع مشابه
BILEN ET AL.: OBJECT AND ACTION CLASSIFICATION WITH LATENT VARIABLES 1 Object and Action Classification with Latent Variables
In this paper we propose a generic framework to incorporate unobserved auxiliary information for classifying objects and actions. This framework allows us to explicitly account for localisation and alignment of representations for generic object and action classes as latent variables. We approach this problem in the discriminative setting as learning a max-margin classifier that infers the clas...
متن کاملWeakly Supervised Object Detection with Posterior Regularization
Motivation: In weakly supervised object detection where only the presence or absence of an object category as a binary label is available for training, the common practice is to model the object location with latent variables and jointly learn them with the object appearance model [1, 5]. An ideal weakly supervised learning method for object detection is expected to guide the latent variables t...
متن کاملشناسایی نوع و مدل وسیله نقلیه با استفاده از مجموعه بخشهای متمایزکننده
In fine-grained recognition, the main category of object is well known and the goal is to determine the subcategory or fine-grained category. Vehicle make and model recognition (VMMR) is a fine-grained classification problem. It includes several challenges like the large number of classes, substantial inner-class and small inter-class distance. VMMR can be utilized when license plate numbers ca...
متن کاملObject-Based Classification of UltraCamD Imagery for Identification of Tree Species in the Mixed Planted Forest
This study is a contribution to assess the high resolution digital aerial imagery for semi-automatic analysis of tree species identification. To maximize the benefit of such data, the object-based classification was conducted in a mixed forest plantation. Two subsets of an UltraCam D image were geometrically corrected using aero-triangulation method. Some appropriate transformations were perfor...
متن کاملLatent Variable Uncertainty for Loss - based Learning
We consider the problem of parameter estimation using weakly supervised datasets, where a training sample consists of the input and a partially specified annotation, which we refer to as the output. The missing information in the annotation is modeled using latent variables. Traditional methods, such as expectation-maximization, overburden a single distribution with two separate tasks: (i) mode...
متن کامل