The understanding of web images has been a hot research topic in both artificial intelligence and multimedia content analysis domains. The web images are composed of various complex foregrounds and backgrounds, which makes the design of an accurate and robust learning algorithm a challenging task. To solve the above significant problem, firstly, we learn a cross-modality bridging dictionary for the deep and complete understanding of vast quantity of web images. The proposed algorithm leverages the visual features into the semantic concept probability distribution, which can construct a global semantic description for images while preserving the local geometric structure. To discover and model the occurrence patterns between intra- and inter-categories, the multi-task learning is introduced for formulating the objective formulation with Capped- $\ell_{1}$ penally, which can obtain the optimal solution with a higher probability and outperform the traditional convex function based methods. Secondly, we propose a knowledge-based concept transferring algorithm to discover the underlying relations of different categories. This distribution probability transferring among categories can bring the more robust global feature representation, and enable the image semantic representation to generalize better as the scenario becomes larger. Experimental comparisons and performance discussion with classical methods on the ImageNet, Caltech-256, SUN397 and Scene15 datasets show the effectiveness of our proposed method at three traditional image understanding tasks.

We propose an image classification framework by leveraging the non-negative sparse coding, low-rank and sparse matrix decomposition techniques (LR-Sc⁺ SPM). First, we propose a new non-negative sparse coding along with max pooling and spatial pyramid matching method (Sc⁺ SPM) to extract local features' information in order to represent images, where non-negative sparse coding is used to encode local features. Max pooling along with spatial pyramid matching (SPM) is then utilized to get the feature vectors to represent images. Second, motivated by the observation that images of the same class often contain correlated (or common) items and specific (or noisy) items, we propose to leverage the low-rank and sparse matrix recovery technique to decompose the feature vectors of images per class into a low-rank matrix and a sparse error matrix. To incorporate the common and specific attributes into the image representation, we still adopt the idea of sparse coding to recode the Sc⁺ SPM representation of each image. In particular, we collect the columns of the both matrixes as the bases and use the coding parameters as the updated image representation by learning them through the locality-constrained linear coding (LLC). Finally, linear SVM classifier is leveraged for the final classification. Experimental results show that the proposed method achieves or outperforms the state-of-the-art results on several benchmarks.

Every bit matters in the hardware design of quantized neural networks. However, extremely-low-bit representation usually causes large accuracy drop. Thus, how to train extremely-low-bit neural networks with high accuracy is of central importance. Most existing network quantization approaches learn transformations (low-bit weights) as well as encodings (low-bit activations) simultaneously. This tight coupling makes the optimization problem difficult, and thus prevents the network from learning optimal representations. In this paper, we propose a simple yet effective Two-Step Quantization (TSQ) framework, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes. For the first step, we propose the sparse quantization method for code learning. The second step can be formulated as a non-linear least square regression problem with low-bit constraints, which can be solved efficiently in an iterative manner. Extensive experiments on CIFAR-10 and ILSVRC-12 datasets demonstrate that the proposed TSQ is effective and outperforms the state-of-the-art by a large margin. Especially, for 2-bit activation and ternary weight quantization of AlexNet, the accuracy of our TSQ drops only about 0.5 points compared with the full-precision counterpart, outperforming current state-of-the-art by more than 5 points.

Recent techniques have achieved remarkable improvements depended on mining subtle yet distinctive features for fine-grained visual classification (FGVC). While prior works directly combine discriminative features extracted from different parts, we argue that the potential interactions between different parts and their abilities to category predictions should be taken into consideration, which enables significant parts to contribute more to the decision of the sub-category. To this end, we present a Cross-Part Convolutional Neural Network (CP-CNN) in a weakly supervised manner to explore cross-learning among multi-regional features. Specifically, the context transformer is implemented to encourage joint feature learning across different parts under the guidance of a navigator. The part with the highest confidence is regarded as a navigator to deliver distinguishing characteristics to the others with lower confidence while the complementary information is retained. To locate discriminative but subtle parts precisely, a part proposal generator (PPG) is designed with the feature enhancement blocks, through which complex scale variations caused by the viewpoint diversity can be effectively alleviated. Extensive experiments on three benchmark datasets demonstrate that our proposed method consistently outperforms existing state-of-the-art methods.

3-D convolutional neural networks (3-D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-based action recognition. In this paper, we propose not to directly use the activations of fully connected layers of a 3-D CNN as the video feature, but to use selective convolutional layer activations to form a discriminative descriptor for video. It pools the feature on the convolutional layers under the guidance of body joint positions. Two schemes of mapping body joints into convolutional feature maps for pooling are discussed. The body joint positions can be obtained from any off-the-shelf skeleton estimation algorithm. The helpfulness of the body joint guided feature pooling with inaccurate skeleton estimation is systematically evaluated. To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously. In this model, the body joint guided feature pooling is conveniently formulated as a bilinear product operation. Experimental results on three real-world datasets demonstrate the effectiveness of body joint guided pooling which achieves promising performance.

Multi-view visual classification methods have been widely applied to use discriminative information of different views. This strategy has been proven very effective by many researchers. On the one hand, images are often treated independently without fully considering their visual and semantic correlations. On the other hand, view consistency is often ignored. To solve these problems, in this paper, we propose a novel multi-view image classification method with visual, semantic and view consistency (VSVC). For each image, we linearly combine multi-view information for image classification. The combination parameters are determined by considering both the classification loss and the visual, semantic and view consistency. Visual consistency is imposed by ensuring that visually similar images of the same view are predicted to have similar values. For semantic consistency, we impose the locality constraint that nearby images should be predicted to have the same class by multiview combination. View consistency is also used to ensure that similar images have consistent multi-view combination parameters. An alternative optimization strategy is used to learn the combination parameters. To evaluate the effectiveness of VSVC, we perform image classification experiments on several public datasets. The experimental results on these datasets show the effectiveness of the proposed VSVC method.