Historical information is crucial for resolving the challenges of the target state changes. Plenty of methods following memory network, which map the historical data and search areas into a unified embedding space to solve feature misalignment, have attained great performance in visual tracking. However, single-scale feature fusion of historical prompts and spatial features, without fully utilizing the rich information embedded in the prompt, struggles to handle complex scenarios such as low resolution and fast motion. To address the above problem, we propose the Adaptive Spatio-Temporal Information Fusion Module, which dynamically integrates spatio-temporal information from various embedding spaces during the inference process of each frame, unlocking the potential of the prompt. Additionally, to alleviate the issues of semantic bias in historical prompts, we propose Adaptive Triplet Attention to refine historical data through cross-dimensional interactions between channels. In the end, we built a novel tracker called ASTrack, which adaptively generates the task-relevant discriminative features through the fusion of spatio-temporal features. Our method is evaluated on six tracking benchmarks, and the results confirm the effectiveness and robustness of the proposed approach.

Recently, the topic of multi-view multi-label classification has aroused significant attention from scholars. Plenty of methods adopt an average weighting scheme to merge the features obtained from multiple views, which commonly ignore the quality difference of information provided by multiple views and thus limit the credibility of the fusion feature for the overall task. Besides, most of these methods assume the views and labels are complete while neglecting both views and labels may be incomplete. To solve these problems, we propose a quality-aware representation fusion network for partial multi-view incomplete multi-label classification, named QARF-net. Since assigning equal fusion weights for each view may be not in line with the actual contributions of individual views, a view quality-aware module is proposed to learn suitable weights for different views dynamically based on the quality of each view’s information, which provides a reliable guide for fusing the information of multiple views. In addition, considering the consistency characteristics of multi-view data, we impose a sample-level dual constraint to preserve the consistency property of the feature in multi-view space and constrain the sample structure in the fused feature space, respectively. Last but not least, QARF-net can not only deal with complete multi-view multi-label classification tasks but also tackle partial multi-view incomplete multi-label classification tasks. Experimental results on five real-world datasets indicate that our proposed method outperforms state-of-the-art methods.

As one of the key components in wavelength-division multiplexing (WDM) circuits, integrated WDM filters that are implemented on the silicon-on-insulator (SOI) platform provide a low-cost and compact solution for combining and separating multiple optical carrier signals. WDM filters are usually represented by their transmission characteristics in the frequency domain whereas their time-domain evaluation is of paramount importance for co-designing and co-optimizing with other electronic and photonic devices for achieving high-speed and high-capacity WDM circuits. This paper proposes an accurate and efficient time-domain modeling and simulation approach for WDM filters. The method starts with transmission parameters and allows for the comprehensive representation of all time-domain transmission and crosstalk characteristics within a single unified model. Notably, the built model could take into account dispersion and wavelength-dependent effects, which are often overlooked by some other modeling techniques. Through a single simulation of such model, transmission and crosstalk signals at all channels can be obtained simultaneously. To illustrate the advantages of our proposed approach, we have conducted a study involving three different types of WDM filters.