The Chinese University of Hong Kong

About: The Chinese University of Hong Kong is a education organization based out in Hong Kong, China. It is known for research contribution in the topics: Population & Cancer. The organization has 43411 authors who have published 93672 publications receiving 3066651 citations.

Locally Aligned Feature Transforms across Views

Abstract: In this paper, we propose a new approach for matching images observed in different camera views with complex cross-view transforms and apply it to person re-identification. It jointly partitions the image spaces of two camera views into different configurations according to the similarity of cross-view transforms. The visual features of an image pair from different views are first locally aligned by being projected to a common feature space and then matched with softly assigned metrics which are locally optimized. The features optimal for recognizing identities are different from those for clustering cross-view transforms. They are jointly learned by utilizing sparsity-inducing norm and information theoretical regularization. This approach can be generalized to the settings where test images are from new camera views, not the same as those in the training set. Extensive experiments are conducted on public datasets and our own dataset. Comparisons with the state-of-the-art metric learning and person re-identification methods show the superior performance of our approach.

Video Frame Synthesis Using Deep Voxel Flow

Abstract: We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be highly complex. Traditional optical-flow-based solutions often fail where flow estimation is challenging, while newer neural-network-based methods that hallucinate pixel values directly often produce blurry results. We combine the advantages of these two methods by training a deep network that learns to synthesize video frames by flowing pixel values from existing ones, which we call deep voxel flow. Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. The technique is efficient, and can be applied at any video resolution. We demonstrate that our method produces results that both quantitatively and qualitatively improve upon the state-of-the-art.

CRM: conceptualization and scale development

Abstract: Purpose – To develop a reliable and valid measuring scale for customer relationship management (CRM).Design/methodology/approach – A series of studies were conducted for the development and validation of multiple measures for the dimensions of CRM. Once the dimensions of CRM were identified, data from study 1 (n=150 business executives attending a part‐time MBA program) were used to select items based on factor analysis. Then, confirmatory factor analyses was used on data obtained from a mail survey of Hong Kong financial firms in study 2 (n=215) to examine factor structure, as well as to provide evidence of dimensionality, scale reliability and validity. Finally, in study 3, data from 276 business executives attending a seminar on CRM were used to test the scale generalizability of CRM measures in various industries.Findings – A reliable and valid scale was developed to measure the four dimensions of CRM: key customer focus, CRM organization, knowledge management and technology‐based CRM.Research limitat...

Exploring Self-Attention for Image Recognition

Abstract: Recent work has shown that self-attention can serve as a basic building block for image recognition models. We explore variations of self-attention and assess their effectiveness for image recognition. We consider two forms of self-attention. One is pairwise self-attention, which generalizes standard dot-product attention and is fundamentally a set operator. The other is patchwise self-attention, which is strictly more powerful than convolution. Our pairwise self-attention networks match or outperform their convolutional counterparts, and the patchwise models substantially outperform the convolutional baselines. We also conduct experiments that probe the robustness of learned representations and conclude that self-attention networks may have significant benefits in terms of robustness and generalization.