In large-scale sensor networks, Multivariate Time Series Classification (MTSC) is a pivotal task for identifying events dependent on longitudinal data at the edge. However, existing methods focus on neither the inherent ability of convolutional networks to perceive subsequence features, nor the prolonged processing pipeline and the model deployment overhead brought by the highly parameterized models. To resolve these difficulties, we present EdgeMTSC, a lightweight large-kernel ConvNet for MTSC, which naturally extracts and learns features of diverse subsequences. Specifically, a novel module named Inter-channel Message Passing-driven Kernel Block (IMP-KB) is proposed, which maintains a learnable correlation matrix to propagate and merge inter-channel messages, and fuses miscellaneous patterns learned by parallel conv kernels of different sizes. EdgeMTSC sequences two modules of different receptive fields to aggregate local features using small kernels and study long-term representation provided by large kernels, respectively. For inference parameter reduction and accelerating inference without performance loss, the conv blocks in IMP-KBs are structurally reparameterizable. The performance of our model (76.2%) is benchmarked on 26 UEA MTSC datasets and is superior to the SOTA model (MPTSNet, 75%). At the same time, EdgeMTSC uses the fewest parameters and achieves the minimum inference time, applicable on any machine (8 devices ranging from large-scale distributed AI computing servers to resource-constrained edge devices) and in any application scenario.

The olfaction is hardly mentioned in the studies of multi-modal Large Language Models (LLMs). This demo presents a prototypical framework to embody prevalent LLMs with smelling ability using a plug-and-play olfactory signal processing service. To this end, we collect a dataset on Korean beers by self-developed electronic noses (e-noses) and an open-source dataset. An olfaction-related question-answering corpus is also generated to fine-tune LLMs. A gas classification model is applied to identify the smelling liquor upon the e-nose data. We then adopt and fine-tune LLMs on the generated datasets. The results show that LLMs under this framework can interact with the environment by its `nose' and provide olfaction-related answers augmented by our dataset. To the best of our knowledge, this is the first work on embodying LLMs with artificial olfaction. We additionally deployed the gas classification model and the trained LLM in a simple web-based system to show the feasibility of our prototype. Our demo video can be found at: https://bit.ly/4j8x6ZY.

Category-specific models are provenly valuable methods in 3D single object tracking (SOT) regardless of Siamese or motion-centric paradigms. However, such over-specialized model designs incur redundant parameters, thus limiting the broader applicability of 3D SOT task. This paper first introduces unified models that can simultaneously track objects across all categories using a single network with shared model parameters. Specifically, we propose to explicitly encode distinct attributes associated to different object categories, enabling the model to adapt to cross-category data. We find that the attribute variances of point cloud objects primarily occur from the varying size and shape (e.g., large and square vehicles v.s. small and slender humans). Based on this observation, we design a novel point set representation learning network inheriting transformer architecture, termed AdaFormer, which adaptively encodes the dynamically varying shape and size information from cross-category data in a unified manner. We further incorporate the size and shape prior derived from the known template targets into the model’s inputs and learning objective, facilitating the learning of unified representation. Equipped with such designs, we construct two category-unified models SiamCUT and MoCUT. Extensive experiments demonstrate that SiamCUT and MoCUT exhibit strong generalization and training stability. Furthermore, our category-unified models outperform the category-specific counterparts by a significant margin (e.g., on KITTI dataset, $\sim$12\% and $\sim$3\% performance gains on the Siamese and motion paradigms).

The explosive popularity of smart manufacturing has caught the attention of researchers in terms of intelligent mold processing and management. Machining mold components is a crucial step in the mold production process for many industries, which creates (e.g., cutting, drilling, and shaping a metal) the individual parts (e.g., core pins, ejector pins, cavities, slides, and lifters) that make up a mold used in manufacturing. We present IMPsys, an AI-based system that automatically explores machining jobs, infers their processing time and schedules them on machines, given numerous 3D modelling files of mold components. Our demo video can be found at: http://bit.ly/3EeKnyL.

Graphical User Interface (GUI) is unavoidable in modern software apps. It facilitates the interactions between the users and the apps. As shown on the Google play store, some apps with higher downloads often have higher-quality, well-designed and tested GUI. GUI testing has become a necessary step in the app development process, and related research become a hot spot in recent years. However, there isn’t a review about GUI testing of mobile apps, which brings obstacles to new researchers. In this paper, we systematically review publications between 2010 and 2020, to gain an insight into GUI testing for mobile apps. Even though the earliest research was published around 1997 but we believe the considered years are likely to include the advances in the field. Specifically, the paper aims to identify (i) the main objectives of GUI testing, (ii) the approaches applied (iii) the evaluation metrics (iv) the challenges and future research directions. To cover all relevant literature, following a predefined systematic literature review procedure, involving both the automatic and manual search strategies, we found 75 primary studies. Four research questions are proposed to analyze them. We found that functionality is the main objective of GUI testing. Model-based testing is the most common approach. Metrics such as error detection, execution time, and code coverage are often used to evaluate the performance of GUI testing techniques. Finally, we outline some key challenges as well as possible research directions. We believe our work would provide a clue for new researchers as well as more research in GUI testing.