Learn More
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(More)
Humans refer to objects in their environments all the time, especially in dialogue with other people. We explore generating and comprehending natural language referring expressions for objects in images. In particular, we focus on incorporating better measures of visual context into referring expression models and find that visual comparison to other(More)
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(More)
Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is composed of three modules: speaker, listener, and reinforcer. The speaker generates referring expressions, the listener(More)
With the rapid growth in demand of massive data processing and the limitation of process development in microprocessor, GPGPU gains more and more attentions to provide huge power of data parallelism. Tightly-coupled CPU and GPGPU that share the LLC (last level cache) enables fine-grained workload offload between CPU and GPGPU. In the paper, we focus on one(More)
Developing IC technology makes Network-on-Chip (NoC) an attractive architecture for future systems. Task migration is important for the overall performance of NoCs since the changing system state makes static task mapping improper for NoCs. The predictability of behaviors of applications makes it possible to use prediction to guide task migration. The(More)
Recently, the example-based super-resolution method has been extensively studied due to its vivid perception. However, this kind of method directly transfers the high-frequency details of the examples to the low-resolution image, incurring false structures and over-sharpness around the texture regions. In this paper, the problem in the example-based method(More)
In this paper, we propose an image super-resolution approach based on gradient enhancement. Local constraints are established to achieve enhanced gradient map, while the global sparsity constraints are imposed on the gradient field to reduce noise effects in super-resolution results. We can then formulate the image reconstruction problem as optimizing an(More)