Trajectory data is crucial for various applications but often suffers from incompleteness due to device limitations and diverse collection scenarios. Existing imputation methods rely on sparse trajectory or travel information, such as velocity, to infer missing points. However, these approaches assume that sparse trajectories retain essential behavioral patterns, which place significant demands on data acquisition and overlook the potential of large-scale human trajectory embeddings. To address this, we propose ProDiff, a trajectory imputation framework that uses only two endpoints as minimal information. It integrates prototype learning to embed human movement patterns and a denoising diffusion probabilistic model for robust spatiotemporal reconstruction. Joint training with a tailored loss function ensures effective imputation. ProDiff outperforms state-of-the-art methods, improving accuracy by 6.28\% on FourSquare and 2.52\% on WuXi. Further analysis shows a 0.927 correlation between generated and real trajectories, demonstrating the effectiveness of our approach.

Collaborative perception in multi-agent system enhances overall perceptual capabilities by facilitating the exchange of complementary information among agents. Current mainstream collaborative perception methods rely on discretized feature maps to conduct fusion, which however, lacks flexibility in extracting and transmitting the informative features and can hardly focus on the informative features during fusion. To address these problems, this paper proposes a novel Anchor-Centric paradigm for Collaborative Object detection (ACCO). It avoids grid precision issues and allows more flexible and efficient anchor-centric communication and fusion. ACCO is composed by three main components: (1) Anchor featuring block (AFB) that targets to generate anchor proposals and projects prepared anchor queries to image features. (2) Anchor confidence generator (ACG) is designed to minimize communication by selecting only the features in the confident anchors to transmit. (3) A local-global fusion module, in which local fusion is anchor alignment-based fusion (LAAF) and global fusion is conducted by spatial-aware cross-attention (SACA). LAAF and SACA run in multilayers, so agents conduct anchor-centric fusion iteratively to adjust the anchor proposals. Comprehensive experiments are conducted to evaluate ACCO on OPV2V and Dair-V2x datasets, which demonstrate ACCO's superiority in reducing the communication volume, and in improving the perception range and detection performances. Code can be found at: https://github.com/sidiangongyuan/ACCO.

Continual Relation Extraction (CRE) has found widespread web applications (e.g., search engines) in recent times. One significant challenge in this task is the phenomenon of catastrophic forgetting, where models tend to forget earlier information. Existing approaches in this field predominantly rely on memory-based methods to alleviate catastrophic forgetting, which overlooks the inherent challenge posed by the varying memory requirements of different relations and the need for a suitable memory refreshing strategy. Drawing inspiration from the mechanisms of Dynamic Random Access Memory (DRAM), our study introduces a novel CRE architecture with an asynchronous refreshing strategy to tackle these challenges. We first design a DRAM-like architecture, comprising three key modules: perceptron, controller, and refresher. This architecture dynamically allocates memory, enabling the consolidation of well-remembered relations while allocating additional memory for revisiting poorly learned relations. Furthermore, we propose a compromising asynchronous refreshing strategy to find the pivot between over-memorization and overfitting, which focuses on the current learning task and mixed-memory data asynchronously. Additionally, we explain the existing refreshing strategies in CRE from the DRAM perspective. Our proposed method has experimented on two benchmarks and overall outperforms ConPL (the SOTA method) by an average of 1.50% on accuracy, which demonstrates the efficiency of the proposed architecture and refreshing strategy.

Healthy dietary intake has a broad influence on the quality of life, and nutrition prediction plays a great role in the auxiliary decision-making of diet. Given a food image, existing nutrition prediction methods directly regress the nutrition content. However, due to the complex variations in food images, such as differences in viewpoint and lighting conditions, directly regressing the nutrition content faces significant challenges. The complexity of the food image data results in a high-dimensional and feature-rich input space, which poses difficulties for traditional regression models to efficiently navigate and optimize. Consequently, the direct regression paradigm usually generates inaccurate nutrition predictions. To alleviate the ambiguity challenge in the prediction progress, we propose to narrow the searchable space for the model's predictions by decomposing the direct regression into two steps: first coarsely selecting the nutrition scope and then finely refining the prediction value, forming a coarse-to-fine nutrition prediction paradigm. Although the process of coarse prediction which selects a bin from a series of scope bins can be formulated as a standard classification problem, it exhibits a distinguishable characteristic, i.e. the closer to the ground truth bin, the less punishment in the training phase. However, most of the current methods have ignored this phenomenon, thus, we specially design the linearly smoothed label in the nutrition prediction task to reveal the relative distance to the ground truth bin, leading to extraordinary improvements. Furthermore, we conduct a pair-wise comparison among all bins by extending the 1D label into 2D space and propose the structure loss to guide the bin selection process effectively. Due to the narrowed decision space, the nutrition prediction problem can be effectively optimized, and the proposed method achieves promising results on three benchmarks ECUSTFD, VFD and Nutrition5K, demonstrating the efficiency of the coarse-to-fine paradigm equipped with the linear-smoothed structure loss.