Related papers: Complex Handwriting Trajectory Recovery: Evaluatio…

Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences. In this paper, we exploit the outstanding capability of…

Trajectories that capture object movement have numerous applications, in which similarity computation between trajectories often plays a key role. Traditionally, the similarity between two trajectories is quantified by means of heuristic…

Graph Edit Distance (GED) is a fundamental, albeit NP-hard, metric for structural graph similarity. Recent neural graph matching architectures approximate GED by first encoding graphs with a Graph Neural Network (GNN) and then applying…

Three-dimensional feature extraction is a critical component of autonomous driving systems, where perception tasks such as 3D object detection, bird's-eye-view (BEV) semantic segmentation, and occupancy prediction serve as important…

The rapid development of large language models and AI agents has triggered a paradigm shift in academic literature retrieval, putting forward new demands for fine-grained, time-aware, and programmable retrieval. Existing graph-vector fusion…

Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns and benefits numerous downstream applications. Existing approaches using classic machine learning or deep learning embed trajectories…

Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency and high computational cost limit their application in…

Handwriting recognition is a challenging and critical problem in the fields of pattern recognition and machine learning, with applications spanning a wide range of domains. In this paper, we focus on the specific issue of recognizing…

Process consistency checking (PCC), an interdiscipline of natural language processing (NLP) and business process management (BPM), aims to quantify the degree of (in)consistencies between graphical and textual descriptions of a process.…

Recent researches introduced fast, compact and efficient convolutional neural networks (CNNs) for offline handwritten Chinese character recognition (HCCR). However, many of them did not address the problem of network interpretability. We…

GPS trajectories are the essential foundations for many trajectory-based applications, such as travel time estimation, traffic prediction and trajectory similarity measurement. Most applications require a large amount of high sample rate…

Accurate Defect detection is crucial for ensuring the trustworthiness of intelligent railway systems. Current approaches rely on single deep-learning models, like CNNs, which employ a large amount of data to capture underlying patterns.…

Human demonstrations of trajectories are an important source of training data for many machine learning problems. However, the difficulty of collecting human demonstration data for complex tasks makes learning efficient representations of…

This paper proposes a pedestrian detection and re-identification (re-id) integration net (I-Net) in an end-to-end learning framework. The I-Net is used in real-world video surveillance scenarios, where the target person needs to be searched…

Event Detection (ED) aims to recognize instances of specified types of event triggers in text. Different from English ED, Chinese ED suffers from the problem of word-trigger mismatch due to the uncertain word boundaries. Existing approaches…

Separating overlapped nuclei is a major challenge in histopathology image analysis. Recently published approaches have achieved promising overall performance on nuclei segmentation; however, their performance on separating overlapped nuclei…

The encoder-decoder network is widely used to learn deep feature representations from pixel-wise annotations in biomedical image analysis. Under this structure, the performance profoundly relies on the effectiveness of feature extraction…

Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…

We evaluate the performance of various text embedding models and pipeline configurations for AI-driven search systems. We compare sentence-transformer and generative embedding models (e.g., All-MPNet, BGE, GTE, and Qwen) at different…

Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned…