Comparing to image-based person re-identification (re-ID) problems, video-based person re-ID can take advantage of more cues from appearance and temporal information, and therefore receives widespread attention recently. However, due to the different pose, occlusion, misalignment and multi-granularity in video sequences, those consequent inter-sequence variations and intra-sequence variations, inevitably makes the feature learning and matching in videos more difficult. Under this circumstance, it is necessary to design an effective discriminative representation learning mechanism, as well as a matching solution, to tackle these variations in video-based person re-ID. To this end, this paper introduces a multi-granularity temporal convolution network and a mutual distance matching measurement, aiming at alleviating the intra-sequence variation and the inter-sequence variation, respectively. Particularly, in the feature learning stage, we model different temporal granularities by hierarchically stacking temporal convolution blocks with different dilation factors. In the feature matching stage, we propose a clip-level probe-gallery mutual distance measurement and consider the most convincing clip pairs by top-k selection. We validate that our proposed method can achieve state-of-the-art results on three video-based person re-ID benchmarks, more than that, we conduct extensive ablation study to demonstrate conciseness and effectiveness of our method in video re-ID tasks.

This paper focuses on energy model based structured output prediction. Though inheriting the benefits from energy-based models to handle the sophisticated cases, previous deep energy-based methods suffered from the substantial computation cost introduced by the enormous amounts of gradient steps in the inference process. To boost the efficiency and accuracy of the energy-based models on structured output prediction, we propose a novel method analogous to the adversarial learning framework. Specifically, in our proposed framework, the generator consists of an inference network while the discriminator is comprised of an energy network. The two sub-modules, i.e., the inference network and the energy network, can benefit each other mutually during the whole computation process. On the one hand, our modified inference network can boost the efficiency by predicting good initializations and reducing the searching space for the inference process; On the other hand, inheriting the benefits of the energy network, the energy module in our network can evaluate the quality of the generated output from the inference network and correspondingly provides a resourceful guide to the training of the inference network. In the ideal case, the adversarial learning strategy makes sure the two sub-modules can achieve an equilibrium state after steps. We conduct extensive experiments to verify the effectiveness and efficiency of our proposed method.

This work focuses on the extremely low-light image enhancement, which aims to improve image brightness and reveal hidden information in darken areas. Recently, image enhancement approaches have yielded impressive progress. However, existing methods still suffer from three main problems: (1) low-light images usually are high-contrast. Existing methods may fail to recover images details in extremely dark or bright areas; (2) current methods cannot precisely correct the color of low-light images; (3) when the object edges are unclear, the pixel-wise loss may treat pixels of different objects equally and produce blurry images. In this paper, we propose a two-stage method called Edge-Enhanced Multi-Exposure Fusion Network (EEMEFN) to enhance extremely low-light images. In the first stage, we employ a multi-exposure fusion module to address the high contrast and color bias issues. We synthesize a set of images with different exposure time from a single image and construct an accurate normal-light image by combining well-exposed areas under different illumination conditions. Thus, it can produce realistic initial images with correct color from extremely noisy and low-light images. Secondly, we introduce an edge enhancement module to refine the initial images with the help of the edge information. Therefore, our method can reconstruct high-quality images with sharp edges when minimizing the pixel-wise loss. Experiments on the See-in-the-Dark dataset indicate that our EEMEFN approach achieves state-of-the-art performance.

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this with weight regularisation. Functional regularisation, although computationally expensive, is expected to perform better, but rarely does so in practice. In this paper, we fix this issue by using a new functional-regularisation approach that utilises a few memorable past examples crucial to avoid forgetting. By using a Gaussian Process formulation of deep networks, our approach enables training in weight-space while identifying both the memorable past and a functional prior. Our method achieves state-of-the-art performance on standard benchmarks and opens a new direction for life-long learning where regularisation and memory-based methods are naturally combined.

In this paper, we focus on generating realistic images from text descriptions. Current methods first generate an initial image with rough shape and color, and then refine the initial image to a high-resolution one. Most existing text-to-image synthesis methods have two main problems. (1) These methods depend heavily on the quality of the initial images. If the initial image is not well initialized, the following processes can hardly refine the image to a satisfactory quality. (2) Each word contributes a different level of importance when depicting different image contents, however, unchanged text representation is used in existing image refinement processes. In this paper, we propose the Dynamic Memory Generative Adversarial Network (DM-GAN) to generate high-quality images. The proposed method introduces a dynamic memory module to refine fuzzy image contents, when the initial images are not well generated. A memory writing gate is designed to select the important text information based on the initial image content, which enables our method to accurately generate images from the text description. We also utilize a response gate to adaptively fuse the information read from the memories and the image features. We evaluate the DM-GAN model on the Caltech-UCSD Birds 200 dataset and the Microsoft Common Objects in Context dataset. Experimental results demonstrate that our DM-GAN model performs favorably against the state-of-the-art approaches.

In this work, we consider the problem of robust principal component analysis (RPCA) for streaming noisy data that has been highly compressed. This problem is prominent when one deals with high-dimensional and large-scale data and data compression is necessary. To solve this problem, we propose an online compressed RPCA algorithm to efficiently recover the low-rank components of raw data. Though data compression incurs severe information loss, we provide deep analysis on the proposed algorithm and prove that the low-rank component can be asymptotically recovered under mild conditions. Compared with other recent works on compressed RPCA, our algorithm reduces the memory cost significantly by processing data in an online fashion and reduces the communication cost by accepting sequential compressed data as input.

Recently, deep learning approach, especially deep Convolutional Neural Networks (ConvNets), have achieved overwhelming accuracy with fast processing speed for image classification. Incorporating temporal structure with deep ConvNets for video representation becomes a fundamental problem for video content analysis. In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos. Compared to recent video representation inference approaches, this paper makes the following three contributions. First, our HRNE is able to efficiently exploit video temporal structure in a longer range by reducing the length of input information flow, and compositing multiple consecutive inputs at a higher level. Second, computation operations are significantly lessened while attaining more non-linearity. Third, HRNE is able to uncover temporal tran-sitions between frame chunks with different granularities, i.e. it can model the temporal transitions between frames as well as the transitions between segments. We apply the new method to video captioning where temporal information plays a crucial role. Experiments demonstrate that our method outperforms the state-of-the-art on video captioning benchmarks.