Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic temporal structure and then properly integrating that information into a natural language description. In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions. First, our approach incorporates a spatial temporal 3-D convolutional neural network (3-D CNN) representation of the short temporal dynamics. The 3-D CNN representation is trained on video action recognition tasks, so as to produce a representation that is tuned to human motion and behavior. Second we propose a temporal attention mechanism that allows to go beyond local temporal modeling and learns to automatically select the most relevant temporal segments given the text-generating RNN. Our approach exceeds the current state-of-art for both BLEU and METEOR metrics on the Youtube2Text dataset. We also present results on a new, larger and more challenging dataset of paired video and natural language descriptions.

The exploration of efficient electrocatalysts for energy conversion is important for green energy development. Owing to their high surface areas and unusual electronic structure, 2D electrocatalysts have attracted increasing interest. Among them, non‐van der Waals (non‐vdW) 2D materials with numerous chemical bonds in all three dimensions and novel chemical and electronic properties beyond those of vdW 2D materials have been studied increasingly over the past decades. Herein, the progress of non‐vdW 2D electrocatalysts is critically reviewed, with a special emphasis on electronic structure modulation. Strategies for heteroatom doping, vacancy engineering, pore creation, alloying, and heterostructure engineering are analyzed for tuning electronic structures and achieving intrinsically enhanced electrocatalytic performances. Lastly, a roadmap for the future development of non‐vdW 2D electrocatalysts is provided from material, mechanism, and performance viewpoints.

Mid-level visual element discovery aims to find clusters of image patches that are both representative and discriminative. In this work, we study this problem from the prospective of pattern mining while relying on the recently popularized Convolutional Neural Networks (CNNs). Specifically, we find that for an image patch, activations extracted from the first fully-connected layer of CNNs have two appealing properties which enable its seamless integration with pattern mining. Patterns are then discovered from a large number of CNN activations of image patches through the wellknown association rule mining. When we retrieve and visualize image patches with the same pattern (See Fig. 1), surprisingly, they are not only visually similar but also semantically consistent. We apply our approach to scene and object classification tasks, and demonstrate that our approach outperforms all previous works on mid-level visual element discovery by a sizeable margin with far fewer elements being used. Our approach also outperforms or matches recent works using CNN for these tasks. Source code of the complete system is available online.

No abstract

Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and timeconsuming. Web images and their labels are, in comparison, much easier to obtain, but direct training on such automatically harvested images can lead to unsatisfactory performance, because the noisy labels of Web images adversely affect the learned recognition models. To address this drawback we propose an end-to-end weakly-supervised deep learning framework which is robust to the label noise in Web images. The proposed framework relies on two unified strategies -random grouping and attention -to effectively reduce the negative impact of noisy web image annotations. Specifically, random grouping stacks multiple images into a single training instance and thus increases the labeling accuracy at the instance level. Attention, on the other hand, suppresses the noisy signals from both incorrectly labeled images and less discriminative image regions. By conducting intensive experiments on two challenging datasets, including a newly collected fine-grained dataset with Web images of different car models, the superior performance of the proposed methods over competitive baselines is clearly demonstrated.