No abstract

No abstract

To promote the sustainable development of society, it is important to develop methods for facile fabrication of bio‐based plastics that are mechanically robust and capable of recycling and completely degrading in soil. In this study, such bio‐based supramolecular plastics are conveniently and cost‐effectively fabricated by cross‐linking epoxidized soybean oil (ESO) and low‐molecular‐weight polylactic acid (PLA) (≈2 kDa) with dynamic boroxines. The bio‐based supramolecular plastic, which is denoted as ESO‐PLA, exhibits a tensile strength of ≈43 MPa and is highly flexible and water‐resistant. After being stored in an environment with a 100% relative humidity for 10 days, the tensile strength of the plastic remains higher than polyethylene. Due to the reversibility of boroxines, the ESO‐PLA plastic can be conveniently processed into different shapes and products. Meanwhile, the plastic can be recycled multiple times for repeated usage by either hot‐pressing or solvent‐assisted depolymerization/repolymerization methods. Benefiting from the easy degradation of ESO and low‐molecular‐weight PLA, the breakage of boroxine cross‐links enables rapid and complete degradation of the plastics in soil within 60 days. Additionally, in vitro and in vivo tests prove that the ESO‐PLA plastic exhibits satisfactory biocompatibility, which extends its application in medicine, food, and cosmetics industries.

No abstract

Although gait recognition has drawn increasing research attention recently, it remains challenging to learn discriminative temporal representation, since the silhouette differences are quite subtle in spatial domain. Inspired by the observation that human can distinguish gaits of different subjects by adaptively focusing on temporal clips with different time scales, we propose a context-sensitive temporal feature learning (CSTL) network for gait recognition. CSTL produces temporal features in three scales, and adaptively aggregates them according to the contextual information from local and global perspectives. Specifically, CSTL contains an adaptive temporal aggregation module that subsequently performs local relation modeling and global relation modeling to fuse the multi-scale features. Besides, in order to remedy the spatial feature corruption caused by temporal operations, CSTL incorporates a salient spatial feature learning (SSFL) module to select groups of discriminative spatial features. Particularly, we utilize transformers to implement the global relation modeling and the SSFL module. To the best of our knowledge, this is the first work that adopts transformer in gait recognition. Extensive experiments conducted on three datasets demonstrate the state-of-the-art performance. Concretely, we achieve rank-1 accuracies of 98.7%, 96.2% and 88.7% under normal-walking, bag-carrying and coat-wearing conditions on CASIA-B, 97.5% on OU-MVLP and 50.6% on GREW.