Main observation and conclusion Polymer‐supramolecular double‐network hydrogels (PS‐DN hydrogels) often show much improved recovery rates than conventional double‐network hydrogels because of the fast self‐assembling properties, making them attractive candidates for tissue engineering and flexible electronics. However, as the supramolecular network is dynamic and susceptible to break under low strains, the overall mechanical properties of PS‐DN hydrogels are still limited. Here, we report the mechanical properties for PS‐DN hydrogels can be significantly improved by tuning the supramolecular network structures. A single amino acid change of the self‐assembling peptide can tune the assembled structures from nanofiber to nanoribbon. Such a microscopic structural change can greatly increase the Young's modulus (107.4 kPa), fracture stress (0.48 MPa), and toughness (0.38 MJ·m–3) of the PS‐DN hydrogels. Moreover, the structural change also leads to slightly faster recovery rates (< 1 s). We propose that such dramatically different mechanical properties can be understood by the impact of individual peptide rupture events on the overall network connectivity in the two scenarios. Our study may provide new inspirations for combining high mechanical strength and fast recovery in double network hydrogels by tuning the supramolecular network structures.

User-generated contents play an important role in the Internet video-sharing activities. Techniques for summarizing the user-generated videos (UGVs) into short representative clips are useful in many applications. This paper introduces an approach for UGV summarization based on semantic recognition. Different from other types of videos like movies or broadcasting news, where the semantic contents may vary greatly across different shots, most UGVs have only a single long shot with relatively consistent high-level semantics. Therefore, a few semantically representative segments are generally sufficient for a UGV summary, which can be selected based on the distribution of semantic recognition scores. In addition, due to the poor shooting quality of many UGVs, factors such as camera shaking and lighting condition are also considered to achieve more pleasant summaries. Experiments on over 100 UGVs with both subjective and objective evaluations show that our approach clearly outperforms several alternative methods and is highly efficient. Using a regular laptop, it can produce a summary for a 2-minute video in just 10 seconds.

No abstract

Railway plug defects impact the safety of a railway system. To detect railway plug defects, we establish the framework of a visual inspection system (VIS), which is the first system that can perform railway plug inspection automatically and intelligently. Using the idea of change detection, the framework includes three algorithm modules, which are named the object location, image alignment and similarity measurement modules. After the image acquisition system captures a rail image as the input, the three algorithm modules process the image in order. First, in the object location module, a deep convolutional neural network is used to perform plug location. Second, in the image alignment module, a simple and fast method is designed to align key images using histogram of oriented gradients features. Third, in the similarity measurement module, the χ2 distance is used to compute the similarity between the two plug regions in an inspection image and in an aligned ground-truth image. The results of the similarity measurement are sorted when all inspection images are processed. Therefore, the inspection images with smaller similarity values are ranked higher and the plugs in the images have larger probabilities of defects. The framework has passed the practice tests, and the visual inspection system using this framework has already been authorized by the China Railway Corporation and will be equipped in many inspection trains belonging to local railway corporations.