Search Results

A classifier with the ability to handle continuous streams of opinion information on the Internet should have good lifelong learning ability. However, deep neural networks face the challenge of catastrophic forgetting when continuously ...

Pedestrian re-recognition refers to the search and analysis of surveillance objects from video or images. However, this task faces multiple challenges. Firstly, in the case of cross-camera and cross-environment, the characteristics of pedestrian images ...

Document-level relational extraction requires reading, memorization, and reasoning to discover relevant factual information in multiple sentences. It is difficult for the current hierarchical network and graph network methods to fully capture the ...

Social media produces large amounts of content every day. How to predict the potential influences of the contents from a social reply feedback perspective is a key issue that has not been explored. Thus, we propose a novel task named reply keyword ...

Large language models have emerged as a promising approach towards achieving general-purpose AI agents. The thriving open-source LLM community has greatly accelerated the development of agents that support human-machine dialogue interaction through ...

Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Recent studies leverage the advantage of self-...

Set-based face recognition (SFR) aims to recognize the face sets in the unconstrained scenario, where the appearance of same identity may change dramatically with extreme variances (e.g., illumination, pose, expression). We argue that the two crucial ...

Visual place recognition (VPR) aims to estimate the geographical location of a query image by finding its nearest reference images from a large geo-tagged database. Most of the existing methods adopt convolutional neural networks to extract feature maps ...

For face presentation attack detection (PAD), most of the spoofing cues are subtle, local image patterns (e.g., local image distortion, 3D mask edge and cut photo edges). The representations of existing PAD works with simple global pooling method, ...

Knowledge graphs (KGs) have proven to be effective to improve the performance of recommendation. However, with the tremendous increase of users and items, existing methods still face several challenging problems: (1) path-based methods rely ...

In the process of visual perception, humans perceive not only the appearance of objects existing in a place but also their relationships (e.g. spatial layout). However, the dominant works on visual place recognition are always based on the assumption ...

In order to deal with the context dilution problem introduced in the lossless compression of M-ary sources, a lossless compression algorithm based on a context tree model is proposed. By making use of the principle that conditioning reduces entropy, the ...

In recent years, deep neural networks have been widely applied to recommender systems. Although there are extensive explorations of deep neural networks on the collaborative filtering problem in item recommendation, most of the existing methods ...

Discriminative local features obtained from activations of convolutional neural networks have proven to be essential for image retrieval. To improve retrieval performance, many recent works aim to obtain more powerful and discriminative features. In this ...

Attributed network embedding, which aims to map structural and attribute information into a latent vector space jointly, has attracted a surge of research attention in recent years. However, existing methods mostly concentrate on either the local ...

Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task. The intrinsic challenges in place recognition exist that the confusing objects such as cars and trees frequently occur in the ...

A MEMS inertial switch with flexible electrodes to contact-enhanced is designed and fabricated. ANSYS software is used to simulate the displacement of the mass, deformation of the flexible electrode and contact time of the switch. A high-speed video ...

Travelling by taxi is more convenient and effective. With an overcrowding population and a much terrible traffic, the traditional way of hailing a taxi encounters many challenges like where to pick-up/drop-off passengers reasonably and where to find ...

The prediction of water influx intensity is much important to the development of aquifer gas reservoir. In this paper, according to water activity and categorizing the type of gas reservoirs with reservoir types, we can use geologic and producing test ...

Virtual testing (VT) technology has been widely applied into current mechanical engineering field, it has many advantages, including comparative low requirement of hardware, simplification experiment process, testing cost reduction, etc. As an important ...