The global elderly population is increasing rapidly, and more and more countries are stepping into the aging society. Because of deterioration in gait-related functions, such as muscle activity, most elderly people have difficulty walking, which is one of the most basic activities of daily living. A wearable lower limb robot exoskeleton offers a viable solution to this issue. Rigid exoskeletons usually have fewer degrees of freedom and require a quite big power supply for actuation, resulting in difficulties during wearing and motion. Soft exoskeletons could be an alternative choice for elderly assistance, due to their advantages of lighter weight, simpler mechanism, and compliance. Therefore, this research proposed a soft array actuator for a lower limb assistive exoskeleton for elderly people. The fully compliant actuation mechanism was designed using flexible Thermoplastic Polyurethane fabric to power the soft exoskeleton, making it compact, light, and comfortable to wear. The proposed array actuator was modeled on kinematics, contacting force, output torque, and dynamics. Mechanical performance of the compliant actuation mechanism during inflation/deflation at different air pressures and during static force testing has been evaluated. The internal air pressure of the soft array actuator reaches 100 kPa in 0.2 s and fully deflates in 0.48 s. It can generate 53.7–55.7 N to output 8.1–11.2 N·m of torque at the endpoint, which is 13.5% –18.7% of the maximum human hip joint torque during natural walking. The proposed soft actuation mechanism, with good wearability and performance, could be a good fit for a robot exoskeleton that improves natural gait and reduces human metabolic consumption during walking among the elderly. Its lightweight design, good invisibility, and high power-to-weight ratio enable the proposed soft array actuator to provide compliant, continuous, and consistent gait assistance without imposing a psychological burden on the elderly.

Today, blockchain ledgers utilize concurrent deterministic execution schemes to scale up. However, ordering fairness is not preserved in these schemes: although they ensure all replicas achieve the same serial order, this order does not always align with the fair, consensus-established order when executing smart contracts with runtime-determined accesses. To preserve ordering fairness, an intuitive method is to concurrently execute transactions and re-execute any order-violating ones. This in turn increases unforeseen conflicts, leading to scaling bottlenecks caused by numerous costly aborts under contention. To address these issues, we propose Spectrum, a novel deterministic execution scheme for smart contract execution on blockchain ledgers. Spectrum preserves the consensus-established serial order (so-called strict determinism) with high performance. Specifically, we leverage a speculative deterministic concurrency control to execute transactions in speculation and enforce an agreed-upon serial order by aborting and re-executing any mis-speculated ones. To overcome the scaling bottleneck, we present two key optimizations based on speculative processing: operation-level rollback and predictive scheduling, for reducing both the overhead and the number of mis-speculations. We evaluate Spectrum by executing EVM-based smart contracts on popular benchmarks, showing that it realizes fair smart contract execution by preserving ordering fairness and outperforms competitive schemes in contended workloads by 1.4x to 4.1x.

The problem of sketch semantic segmentation is far from being solved. Despite existing methods exhibiting near-saturating performances on simple sketches with high recognisability, they suffer serious setbacks when the target sketches are products of an imaginative process with high degree of creativity. We hypothesise that human creativity, being highly individualistic, induces a significant shift in distribution of sketches, leading to poor model generalisation. Such hypothesis, backed by empirical evidences, opens the door for a solution that explicitly disentangles creativity while learning sketch representations. We materialise this by crafting a learnable creativity estimator that assigns a scalar score of creativity to each sketch. It follows that we introduce CreativeSeg, a learning-to-learn framework that leverages the estimator in order to learn creativity-agnostic representation, and eventually the downstream semantic segmentation task. We empirically verify the superiority of CreativeSeg on the recent "Creative Birds" and "Creative Creatures" creative sketch datasets. Through a human study, we further strengthen the case that the learned creativity score does indeed have a positive correlation with the subjective creativity of human. Codes are available at https://github.com/PRIS-CV/Sketch-CS.

General practice plays a prominent role in primary health care (PHC). However, evidence has shown that the quality of PHC is still unsatisfactory, and the accuracy of clinical diagnosis and treatment must be improved in China. Decision making tools based on artificial intelligence can help general practitioners diagnose diseases, but most existing research is not sufficiently scalable and explainable. An explainable and personalized cognitive reasoning model based on knowledge graph (CRKG) proposed in this article can provide personalized diagnosis, perform decision making in general practice, and simulate the mode of thinking of human beings utilizing patients' electronic health records (EHRs) and knowledge graph. Taking abdominal diseases as the application point, an abdominal disease knowledge graph is first constructed in a semiautomated manner. Then, the CRKG designed referring to dual process theory in cognitive science involves the update strategy of global graph representations and reasoning on a personal cognitive graph by adopting the idea of graph neural networks and attention mechanisms. For the diagnosis of diseases in general practice, the CRKG outperforms all the baselines with a precision@1 of 0.7873, recall@10 of 0.9020 and hits@10 of 0.9340. Additionally, the visualization of the reasoning process for each visit of a patient based on the knowledge graph enhances clinicians' comprehension and contributes to explainability. This study is of great importance for the exploration and application of decision making based on EHRs and knowledge graph.

Sketch is a well-researched topic in the vision community by now. Sketch semantic segmentation in particular, serves as a fundamental step towards finer-level sketch interpretation. Recent works use various means of extracting discriminative features from sketches and have achieved considerable improvements on segmentation accuracy. Common approaches for this include attending to the sketch-image as a whole, its stroke-level representation or the sequence information embedded in it. However, they mostly focus on only a part of such multi-facet information. In this paper, we for the first time demonstrate that there is complementary information to be explored across all these three facets of sketch data, and that segmentation performance consequently benefits as a result of such exploration of sketch-specific information. Specifically, we propose the Sketch-Segformer, a transformer-based framework for sketch semantic segmentation that inherently treats sketches as stroke sequences other than pixel-maps. In particular, Sketch-Segformer introduces two types of self-attention modules having similar structures that work with different receptive fields (i.e., whole sketch or individual stroke). The order embedding is then further synergized with spatial embeddings learned from the entire sketch as well as localized stroke-level information. Extensive experiments show that our sketch-specific design is not only able to obtain state-of-the-art performance on traditional figurative sketches (such as SPG, SketchSeg-150K datasets), but also performs well on creative sketches that do not conform to conventional object semantics (CreativeSketch dataset) thanks for our usage of multi-facet sketch information. Ablation studies, visualizations, and invariance tests further justifies our design choice and the effectiveness of Sketch-Segformer. Codes are available at https://github.com/PRIS-CV/Sketch-SF.

Sketch semantic segmentation serves as an important part of sketch interpretation. Recently, some researchers have obtained significant results using graph neural networks (GNN) for this task. However, existing GNN-based methods usually neglect the drawing order of sketches thus missing out the sequence information inherent to sketches. Towards solving this problem to achieve better performance on sketch semantic segmentation, we propose an encoder-decoder GNN framework named ENDE-GNN. Working with an auxiliary decoder, our ENDE-GNN guides the GNN backbone network to not only extract the inter-stroke and intra-stroke features, but also pays attention to the drawing order of sketches. This decoder acts during training only, preventing any additional overhead during testing. The proposed ENDE-GNN obtains state-of-the-art per-formances on three public sketch semantic segmentation datasets, namely SPG, SketchSeg-150K, and CreativeSketch. We further evaluate the effectiveness of ENDE-GNN via ablation studies and visualizations. Codes are available at https://github.com/PRIS-CV/ENDE_For_SSS.

Whether what you see in Figure 1 is a "flamingo" or a "bird", is the question we ask in this paper. While fine-grained visual classification (FGVC) strives to arrive at the former, for the majority of us non-experts just "bird" would probably suffice. The real question is therefore – how can we tailor for different fine-grained definitions under divergent levels of expertise. For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy – so that our answer becomes "bird" ⇒ "Phoenicopteriformes" ⇒ "Phoenicopteridae" ⇒ "flamingo".To approach this new problem, we first conduct a comprehensive human study where we confirm that most participants prefer multi-granularity labels, regardless whether they consider themselves experts. We then discover the key intuition that: coarse-level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse-level classifier. This discovery enables us to design a very simple albeit surprisingly effective solution to our new problem, where we (i) leverage level-specific classification heads to disentangle coarse-level features with fine-grained ones, and (ii) allow finer-grained features to participate in coarser-grained label predictions, which in turn helps with better disentanglement. Experiments show that our method achieves superior performance in the new FGVC setting, and performs better than state-of-the-art on the traditional single-label FGVC problem as well. Thanks to its simplicity, our method can be easily implemented on top of any existing FGVC frameworks and is parameter-free.

Object counting aims to estimate the number of objects in images. The leading counting approaches focus on single-category counting tasks and achieve impressive performance. Nevertheless, there are multiple categories of objects in real scenes. Multi-class object counting expands the scope of application of object counting tasks. The multi-target detection task can achieve multi-class object counting in some scenarios. However, it requires the dataset annotated with bounding boxes. Compared with the point-level annotations used in mainstream object counting issues, the box-level annotations are more difficult to be obtained. In this paper, we propose a simple yet efficient counting network based on point-level annotations. Specifically, we first change the traditional estimated density map from one to the number of categories to achieve multi-class object counting. Since all categories of objects use the same feature extractor, their features will interfere mutually in the shared feature space. We further design a multi-mask structure to suppress the negative interaction among objects. Extensive experiments on the challenging benchmarks demonstrate that the proposed method achieves state-of-the-art counting performance.The code is available athttps://github.com/PRIS-CV/DSACA.

A predominant viewpoint in previous works of fine-grained visual classification (FGVC) is to the localize discriminative parts by auxiliary networks and extract the part-based finegrained features for classification. In this paper, we propose a simple yet effective approach by introducing an intersection and union module (IU-Module). The IU-Module aims to capture more discriminative features by 1) dividing features into distinct groups, 2) sharing parts of interests within each group, and 3) adding a differentiation loss to reduce the similarity among those grouped feature channels. Without adding any new learnable parameters, the proposed approach imposes two straightforward operations, namely channel intersection (CI) and channel union (CU) operations, on the convolutional features and achieves competitive results compared with the state-of-the-art methods. Experimental results on three publicly available FGVC datasets show the effectiveness of the IU-Module. Ablation studies and visualizations are also provided to make further demonstrations.

Convolutional Neural Networks (CNNs) have been successfully applied in various image analysis tasks and gradually become one of the most powerful machine learning approaches. In order to improve the capability of the model generalization and performance in image classification, a new trend is to learn more discriminative features via CNNs. The main contribution of this paper is to increase the angles between the categories to extract discriminative features and enlarge the inter-class variance. To this end, we propose a loss function named focal inter-class angular loss (FICAL) which introduces the confusion rate-weighted cosine distance as the similarity measurement between categories. This measurement is dynamically evaluated during each iteration to adapt the model. Compared with other loss functions, experimental results demonstrate that the proposed FICAL achieved best performance among the referred loss functions on two image classificaton datasets.