Focused Evaluation for Image Description with Binary Forced-Choice Tasks
نویسندگان
چکیده
Current evaluation metrics for image description may be too coarse. We therefore propose a series of binary forced-choice tasks that each focus on a different aspect of the captions. We evaluate a number of different off-the-shelf image description systems. Our results indicate strengths and shortcomings of both generation and ranking based approaches.
منابع مشابه
The Effect of Different Task Types on Learning Prepositions in Form–Focused and Meaning–Focused Interaction Enhancement-Based Classes
The current study examines the impact of different task types on learning prepositions in form and meaning- focused interaction enhancement- based classes. The participants were 57 second Year University students enrolled in three intact lab classes at Tabriz Islamic Azad University. The first group was provided with form-focused interaction enhancement, the second with the meaning-focused int...
متن کاملComparing Point and Block Representation in Computer Vision and Image Processing Tasks
The description of a digital image in terms of simple geometrical shapes, such as polygonal shapes, is a well established methodology that often proves useful for several image processing tasks, mainly to speed up image processing operations. The representation of binary images using rectangular blocks as primitives has been applied with great success to several computer vision and image proces...
متن کاملVisual Madlibs: Fill in the blank Image Generation and Question Answering
In this paper, we introduce a new dataset consisting of 360,001 focused natural language descriptions for 10,738 images. This dataset, the Visual Madlibs dataset, is collected using automatically produced fill-in-the-blank templates designed to gather targeted descriptions about: people and objects, their appearances, activities, and interactions, as well as inferences about the general scene o...
متن کاملClassification image analysis: estimation and statistical inference for two-alternative forced-choice experiments.
We consider estimation and statistical hypothesis testing on classification images obtained from the two-alternative forced-choice experimental paradigm. We begin with a probabilistic model of task performance for simple forced-choice detection and discrimination tasks. Particular attention is paid to general linear filter models because these models lead to a direct interpretation of the class...
متن کاملResearch of Blind Signals Separation with Genetic Algorithm and Particle Swarm Optimization Based on Mutual Information
Blind source separation technique separates mixed signals blindly without any information on the mixing system. In this paper, we have used two evolutionary algorithms, namely, genetic algorithm and particle swarm optimization for blind source separation. In these techniques a novel fitness function that is based on the mutual information and high order statistics is proposed. In order to evalu...
متن کامل