Recent transformer-based models, especially patch-based methods, have shown huge potentiality in vision tasks. However, the split fixed-size patches divide the input features into the same size patches, which ignores the fact that vision elements are often various and thus may destroy the semantic information. Also, the vanilla patch-based transformer cannot guarantee the information communication between patches, which will prevent the extraction of attention information with a global view. To circumvent those problems, we propose the Efficient Attention Pyramid Transformer (EAPT) in this paper. More specifically, we first propose Deformable Attention, which learns an offset for each position in patches. Therefore, even with split fixed-size patches, our method can still obtain non-fixed attention information that can cover various vision elements. Then, we design the Encode-Decode Communication module (En-DeC module), which can obtain communication information between all patches to get more complete global attention information. Finally, we also proposed a position encoding specifically for vision transformers, which can be used for patches of any dimensions and any lengths. Extensive experiments on the vision tasks of image classification, object detection, semantic segmentation demonstrate the effectiveness of our proposed model. Furthermore, we also conduct rigorous ablation studies to evaluate the key components of the proposed structure.

Domestic waste classification was incorporated into legal provisions recently in China. However, relying on manpower to detect and classify domestic waste is highly inefficient. To that end, in this article, we propose a multimodel cascaded convolutional neural network (MCCNN) for domestic waste image detection and classification. MCCNN combined three subnetworks (DSSD, YOLOv4, and Faster-RCNN) to obtain the detections. Moreover, to suppress the false-positive predicts, we utilized a classification model cascaded with the detection part to judge whether the detection results are correct. To train and evaluate MCCNN, we designed a large-scale waste image dataset (LSWID), containing 30 000 domestic waste multilabeled images with 52 categories. To the best of our knowledge, the LSWID is the largest dataset on domestic waste images. Furthermore, a smart trash can is designed and applied to a Shanghai community, which helped to make waste recycling more efficient. Experimental results showed a state-of-the-art performance, with an average improvement of 10% in detection precision.

Emerging evidence suggests that modulation of gut microbiota by dietary fibre may offer solutions for metabolic disorders. In a randomized placebo-controlled crossover design trial (ChiCTR-TTRCC-13003333) in 37 participants with overweight or obesity, we test whether resistant starch (RS) as a dietary supplement influences obesity-related outcomes. Here, we show that RS supplementation for 8 weeks can help to achieve weight loss (mean −2.8 kg) and improve insulin resistance in individuals with excess body weight. The benefits of RS are associated with changes in gut microbiota composition. Supplementation with Bifidobacterium adolescentis, a species that is markedly associated with the alleviation of obesity in the study participants, protects male mice from diet-induced obesity. Mechanistically, the RS-induced changes in the gut microbiota alter the bile acid profile, reduce inflammation by restoring the intestinal barrier and inhibit lipid absorption. We demonstrate that RS can facilitate weight loss at least partially through B. adolescentis and that the gut microbiota is essential for the action of RS.

Modeling feature interactions is of crucial significance to high-quality feature engineering on multifiled sparse data. At present, a series of state-of-the-art methods extract cross features in a rather implicit bitwise fashion and lack enough comprehensive and flexible competence of learning sophisticated interactions among different feature fields. In this article, we propose a new broad attentive graph fusion network (BaGFN) to better model high-order feature interactions in a flexible and explicit manner. On the one hand, we design an attentive graph fusion module to strengthen high-order feature representation under graph structure. The graph-based module develops a new bilinear-cross aggregation function to aggregate the graph node information, employs the self-attention mechanism to learn the impact of neighborhood nodes, and updates the high-order representation of features by multihop fusion steps. On the other hand, we further construct a broad attentive cross module to refine high-order feature interactions at a bitwise level. The optimized module designs a new broad attention mechanism to dynamically learn the importance weights of cross features and efficiently conduct the sophisticated high-order feature interactions at the granularity of feature dimensions. The final experimental results demonstrate the effectiveness of our proposed model.

In this paper, we present a method (Action-Fusion) for human action recognition from depth maps and posture data using convolutional neural networks (CNNs). Two input descriptors are used for action representation. The first input is a depth motion image that accumulates consecutive depth maps of a human action, whilst the second input is a proposed moving joints descriptor which represents the motion of body joints over time. In order to maximize feature extraction for accurate action classification, three CNN channels are trained with different inputs. The first channel is trained with depth motion images (DMIs), the second channel is trained with both DMIs and moving joint descriptors together, and the third channel is trained with moving joint descriptors only. The action predictions generated from the three CNN channels are fused together for the final action classification. We propose several fusion score operations to maximize the score of the right action. The experiments show that the results of fusing the output of three channels are better than using one channel or fusing two channels only. Our proposed method was evaluated on three public datasets: 1) Microsoft action 3-D dataset (MSRAction3D); 2) University of Texas at Dallas-multimodal human action dataset; and 3) multimodal action dataset (MAD) dataset. The testing results indicate that the proposed approach outperforms most of existing state-of-the-art methods, such as histogram of oriented 4-D normals and Actionlet on MSRAction3D. Although MAD dataset contains a high number of actions (35 actions) compared to existing action RGB-D datasets, this paper surpasses a state-of-the-art method on the dataset by 6.84%.