We bring to bear the tools of convexity, margins and the newly proposed technique of monotone retargeting upon the task of learning permutations from examples. This leads to novel and efficient algorithms with guaranteed prediction performance in the online setting and on global optimality and the rate of convergence in the batch setting. Monotone retargeting efficiently optimizes over all poss...

For many years, retargeting of applications for new architectures has been a major headache for high performance computation. As new architectures have emerged at dizzying speed, we have moved from uniprocessors, to vector machines, symmetric multiprocessors, synchronous parallel arrays, distributed-memory parallel computers, and scalable clusters. Over the past year, clusters based on multicor...

We present a versatile model, FaceAnime, for various video generation tasks from still images. Video single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information the input sequence of sparse facial landmarks. However, generated images suffer quality loss, distortion, identity change, expression mismatching due weak ...

We present a high-efficiency approach to optimally enhance image composition using a crop-andwarp-based algorithm. We have designed a piecewise quadratic aesthetic energy function with linear inequality constraints that measures the distance between original positions and the aesthetic target positions of visual elements, to assess the target image composition. The target image is cropped by a ...

Detection of salient region detection is useful for several image processing applications such as security system for Airport, Medical imaging, Object reorganization, Criminal Investigation, Retrieval of image, filter design and Retargeting an Image. A novel approach to determine salient region of images is proposed in this paper. GMM if used for clustering the colour values in the L*a*b colour...

This technical report improves and extends existing methods in the research area of audio resynthesis and retargeting and extends its usage scopes. The existing approach analyzes a musical piece for possible cut points that allow the resynthesis of a novel soundtrack by lining up the source segments according to specified rules. For the improvement of matching harmonic and rhythmic structures d...

This paper presents a new approach to facilitate reuse and remixing in character animation. It demonstrates a method for automatically adapting existing skeletons to different characters. While the method can be applied to simple skeletons, it also proposes a new approach that is applicable to high quality animation as it is able to deal with complex skeletons that include control bones (those ...

The ball-and-socket joint model is used to represent articulations with three rotational degrees of freedom (DOF), such as the human shoulder and the hip. The goal of this paper is to discuss two related problems: the parametrization and the deÞnition of realistic joint boundaries for ball-andsocket joints. Doing this accurately is difÞcult, yet important for motion generators (such as inverse ...

Utilization of motion capture techniques is becoming more popular in the pipeline of articulated character animation. Based upon captured motion data, defining accurate joints position and joints orientation for the movement of a hierarchical human-like character without using a pre-defined skeleton is still a potential concern for motion capture studio. In this paper, we present a method for a...

Seam carving is a representative content-aware image retargeting approach to adjust the size of an image. To preserve visually prominent content, seam-carving algorithms first calculate connected path pixels, referred as seam, according defined cost function and then by removing or duplicating repeatedly calculated seams. actively exploited overcome diversity in resolution images between applic...