This paper presents a method of learning reconfigurable And-Or Tree (AOT) models discriminatively from weakly annotated data for object detection. To explore the appearance and geometry space of latent structures effectively, we first quantize the image lattice using an overcomplete set of shape primitives, and then organize them into a directed acyclic And-Or Graph (AOG) by exploiting their compositional relations. We allow overlaps between child nodes when combining them into a parent node, which is equivalent to introducing an appearance Or-node implicitly for the overlapped portion. The learning of an AOT model consists of three components: (i) Unsupervised sub-category learning (i.e., branches of an object Or-node) with the latent structures in AOG being integrated out. (ii) Weaklysupervised part configuration learning (i.e., seeking the globally optimal parse trees in AOG for each sub-category). To search the globally optimal parse tree in AOG efficiently, we propose a dynamic programming (DP) algorithm. (iii) Joint appearance and structural parameters training under latent structural SVM framework. In experiments, our method is tested on PASCAL VOC 2007 and 2010 detection benchmarks of 20 object classes and outperforms comparable state-of-the-art methods.

E-commerce offers an opportunity on web renounced in internet marketing, and the consumers' communication behavior has changed, which has taken the place of word of mouth (WOM). This study investigated consumers' motivational involvement in electronic word of mouth for online information adoption mediated by writers, motivations. Using a sample of 390 active Chinese internet users, it revealed that social tie and perceived risk are essential factors that influence consumers' behavior, occur unpleasant consequences, and the possibility of uncertainties during the decision making process. Online retailers should emphasize perceived risk mitigation enable to provide a quick response on the websites. Practitioners need to understand consumer behavior in the online shopping system for the expansion of the online marketplace to product varieties, online advertising, retail strategies, and market segmentation. Organizations should train their service provides to timely response, concentrate on monitoring the aspects of consumers' reviews, on creating choices among groups and individuals, which can improve the organization's business performance.

This paper first proposes a method of formulating model interpretability in visual understanding tasks based on the idea of unfolding latent structures. It then presents a case study in object detection using popular two-stage region-based convolutional network (i.e., R-CNN) detection systems (Girshick 2015;Ren et al. 2015;Dai et al. 2016;He et al. 2017). We focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. We utilize a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of regions of interest (RoIs). We propose an AOG-Parsing operator to substitute the RoIPooling operator widely used in R-CNN. In detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the qualitatively extractive rationale generated for interpreting detection. We propose a folding-unfolding method to train the AOG and convolutional networks endto-end. In experiments, we build on R-FCN (Dai et al. 2016) and test our method on the PASCAL VOC 2007 and 2012 datasets. We show that the method can unfold promising latent structures without hurting the performance.

Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs. The proposed architectures integrate compositionality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way. We utilize AND-OR Grammar (AOG) [55,75,74] as network generator in this paper and call the resulting networks AOGNets. An AOGNet consists of a number of stages each of which is composed of a number of AOG building blocks. An AOG building block splits its input feature map into N groups along feature channels and then treat it as a sentence of N words. It then jointly realizes a phrase structure grammar and a dependency grammar in bottom-up parsing the "sentence" for better feature exploration and reuse. It provides a unified framework for the best practices developed in state-of-the-art DNNs. In experiments, AOGNet is tested in the CIFAR-10, CIFAR-100 and ImageNet-1K classification benchmark and the MS-COCO object detection and segmentation benchmark. In CIFAR-10, CIFAR-100 and ImageNet-1K, AOGNet obtains better performance than ResNet [23] and most of its variants, ResNeXt [66] and its attention based variants such as SENet [27], DenseNet [29] and DualPathNet [7]. AOGNet also obtains the best model interpretability score using network dissection [4]. AOGNet further shows better potential in adversarial defense. In MS-COCO, AOGNet obtains better performance than the ResNet and ResNeXt backbones in Mask R-CNN [22].