Automatic facial micro-expression recognition is challenging for the subtlety and transience in facial motion, and limited databases. Most researches focus on handcrafted techniques for facial micro-expression analysis on two-dimensional images. However, spatiotemporal facial feature representation is a critical issue for facial micro-expression recognition due to its short duration and subtle facial movement. To deeply extract the appearance characteristics and facial changes effectively from facial image sequences, a feature-wise deep learning model was proposed by applying temporal Convolutional Neural Network (3D-CNN) and Long Short-Term Memory (LSTM) to enhance temporal feature learning. There are two stages involved: (1) The CNN was extended to convolute along spatio and temporal simultaneously, to better represent the facial texture and motion. (2) The feature vector obtained by 3D-CNN was fed into LSTM for temporal enrichment. It was demonstrated that the proposed model achieved promising good performance on CASME II and SMIC databases on person-independent and cross-database experiments.

The online customer reviews provide important information for product improvement and redesign. However, many reviews are redundant with only several short sentences, which may even conflict with each other on the same aspect of a product. Thus it is usually a very challenging task to extract useful design information from the reviews and provide a clear description on the product’s various aspects amongst its competitors. In order to resolve this issue, we propose an approach to build hierarchical product profiles to describe a product’s kernel design aspects quantitatively. It is achieved via three main strategies: a double propagation strategy to achieve the associated features and customers’ escriptions; a deep text processing network to build the aspect hierarchy; an aspect ranking approach to quantify each kernel design aspect. Experimental results validate the effectiveness of the proposed approach on online reviews.

Facial micro-expression is momentary and subtle facial reactions, and it is still challenging to automatically recognize facial micro-expression with high accuracy in practical applications. Extracting spatiotemporal features from facial image sequences is essential for facial micro-expression recognition. In this paper, we employed 3D Convolutional Neural Networks (3D-CNNs) for self-learning feature extraction to represent facial micro-expression effectively, since the 3D-CNNs could well extract the spatiotemporal features from facial image sequences. Moreover, transfer learning was utilized to deal with the problem of insufficient samples in the facial micro-expression database. We primarily pre-trained the 3D-CNNs on normal facial expression database Oulu-CASIA by supervised learning, then the pre-trained model was effectively transferred to the target domain, which was the facial micro-expression recognition task. The proposed method was evaluated on two available facial micro-expression datasets, i.e. CASME II and SMIC-HS. We obtained the overall accuracy of 97.6% on CASME II, and 97.4% on SMIC, which were 3.4% and 1.6% higher than the 3D-CNNs model without transfer learning, respectively. And the experimental results demonstrated that our method achieved superior performance compared to state-of-the-art methods.

The online shopping has been much easier and popular, and meanwhile brings new challenges and opportunities to the field of product design and marketing sale. On one hand, product manufacturers find it challenging to produce new popularly accepted products to meet the customers' needs; on the other hand, end customers usually feel it difficult to buy ideal goods that they really want, even if navigating a huge amount of commodities. There are indeed a 'communication gap' between the customers and manufacturers.As an effort to partially resolve the issue, this paper proposes a novel product synthesis approach from 'voice of the customer' over product knowledge graphs. Here the voice of customers mainly refer to the buyers' product reviews from online shopping platforms or blogs, while the product knowledge graph is constructed containing professional hierarchical product knowledge on its properties based on ontological models. Using the technologies of natural language processing, we first extract the customs' polarities on each specific aspect of a product, which are then transited to design requirements on the product's design components. Based on the requirement extractions, and the pre-built product knowledge, semantic web and reasoning techniques are utilized to synthesize a novel product that meets more customer needs. Typical case studies on mobile phones from raw online data demonstrate the proposed approach's performance.