Browse Proceedings

Object detector based on CNN structure has been widely used in object detection, object classification and other tasks. The traditional CNN module usually adopts complex multi-branch design, which reduces the reasoning speed and memory ...

Event temporal relation extraction aims to automatically identify the temporal order between a pair of events, which is an essential step towards event-oriented natural language understanding and generation. For this task, impressive improvements ...

Detecting fraudulent nodes from topological graphs is important in many real applications, such as financial fraud detection. This task is challenging due to both the class imbalance issue and the camouflaged behaviors of anomalous nodes. Recently,...

In many real-world networks, such as co-authorship, etc., relationships are complex and go beyond pairwise associations. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. Detecting the set of critical ...

Existing supervised methods for error detection require access to clean labels to train the classification model. While the majority of error detection algorithms ignore the harm of noisy labels to detection models. In this paper, we design an ...

In order to improve the performance of cloud computing, the multi−objective optimization problems in this field need to be solved efficiently. This paper proposes a novel Dual−Population strategy based Multi−Objective Yin−Yang−Pair Optimization ...

High-dimensional and complex spectral structures make clustering of hyperspectral images (HSI) a challenging task. Subspace clustering has been shown to be an effective approach for addressing this problem. However, current subspace clustering ...

Knowledge graph (KG) contains rich semantic information and is widely used in recommendation systems. Knowledge graph is a heterogeneous graph, and entities are connected by multiple relations. Users have different preferences for different ...

Heterogeneous graphs are ubiquitous in the real world, such as online shopping networks, academic citation networks, etc. Heterogeneous Graph Neural Networks (HGNNs) have been widely used to capture rich semantic information on graph data, showing ...

Density-based clustering is a fundamental and effective tool for recognizing connectivity structure. The density peak, the data object with the maximum density within a predefined sphere, plays a critical role. However, Density Peak Estimation (...

Hierarchical topic modeling has been widely used in mining the latent topic hierarchy of documents. However, most of such models are limited to a one-shot scenario since they do not use the identified topic information to guide the subsequent ...

Sequential recommendation (SR) has become an important schema to assist people in rapidly finding their interest in the progressively growing data. Especially, long and short-term based methods capture user preferences and provide more precise ...

Multi-Object detection in traffic scenarios plays a crucial role in ensuring the safety of people and property, as well as facilitating the smooth flow of traffic on roads. However, the existing algorithms are inefficient in detecting real ...

The graph-based anomaly detection task aims to identify nodes with patterns that deviate from those of the majority nodes in a large graph, where only a limited subset of nodes is annotated. However, inadequate supervised knowledge and uncertainty ...

In the field of computer vision and stereo depth estimation, there has been little research in obtaining high-accuracy disparity change maps from two-dimensional images. This map offers information that fills the gap between optical flow and depth ...

Transformer plays a massive role in document image understanding. However, it has difficulty handling text in long document images due to the increasing quadratic complexity along the text length. To solve this problem, we propose the hierarchical ...

Locality-Sensitive Hashing (LSH) is a well-known method to solve the Approximate Nearest Neighbor (ANN) search problem. Query-Aware LSH (QALSH), a state-of-the-art LSH method, is a disk-based algorithm and suffers from high latency of disk I/O, ...

The recommendation system is now playing a more and more important role in our daily life. Recently, some scholars proposed that human behavior is governed by a complex web of causal models, and causal relationships are crucial in the ...

The fire spreads rapidly in the tunnel due to the narrow space and high sealing, which makes rescue hard and threatens the citizen’s lives. However, the lack of public fire datasets makes it challenging for networks to learn targeted ...

Nowadays on E-commerce platforms, products usually contain multi-modal descriptions. To search related products from user-generated texture queries, most previous works learn the multi-modal retrieval models by the historical query-product ...

Continual relation extraction (CRE) aims to continually learn new relations while maintaining knowledge of previous relations in the data streams. Recently, continual few-shot relation extraction (CFRE) is introduced, in which only the first step ...

As a standard method of side channel leak assessment, TVLA is a popular research direction of side channel attack. TVLA mainly conducts leak assessment based on Welch’s t-test or paired t-test, but in some evaluation scenarios, different leak ...

Session-based Recommendation aims at predicting the next item based on anonymous users’ behavior sequences. During a session, both the user’s global interest and local interest influence the decisions. However, due to their discrepancy, most ...

What knowledge should a student grasp before beginning a new MOOC course? To answer this question, it is essential to automatically discover prerequisite relations among course concepts. Although researchers have devoted intensive efforts to ...

Variational autoencoders (VAEs) have shown unique advantages as a generative model for sequence recommendation. The core of VAEs is the reconstruction of error targets through similarity metrics to provide a supervised signal for training. However,...

Category systems play an essential role in knowledge bases by groupings of semantically related entities. Category generation task aims to produce category suggestions which can help knowledge editors to expand a category system. Most past ...

The topic and embedding models are two of the most popular categories of techniques to learn the latent semantics from text. In the topic models, each word is generated according to its global context; while in the embedding models, each word ...

When traveling to a foreign city, we often find ourselves in dire need of an intelligent agent that can provide instant and informative responses to our various queries. Such an agent should have the ability to understand our queries and possess ...