Search Results

Cyber-physical systems (CPSs) need to respond to each change of each monitored object in time. The entire response process can be divided into two stages: the update stage and the control stage. Tasks in CPSs can thus be divided into two kinds: update ...

In the field of machine learning, continual learning is a crucial concept that allows models to adapt to non-stationary data distributions. However, most of the existing works focus on uni-modal settings and ignore the multi-modal data. In this paper, to ...

In the burgeoning field of Audio-Visual Speech Recognition (AVSR), extant research has predominantly concentrated on the training paradigms tailored for high-quality resources. However, owing to the challenges inherent in real-world data collection, ...

Research on continual learning in multi-modal tasks has been receiving increasing attention. However, most existing work overlooks the explicit cross-modal and cross-task interactions. In this paper, we innovatively propose the Low-rank Prompt I...

Single image super-resolution (SR) reconstruction plays a crucial role in various fields, including surveillance and remote sensing. However, the majority of available SR reconstruction methods are designed primarily for visible images, making it ...

As image–text matching (a critical task in the field of computer vision) links cross-modal data, it has captured extensive attention. Most of the existing methods intended for matching images and texts explore the local similarity levels between ...

Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem. However, existing generative methods typically focus solely on either ...

Recent methods for video question answering (VideoQA), aiming to generate answers based on given questions and video content, have made significant progress in cross-modal interaction. From the perspective of video understating, these existing frameworks ...

Handling dynamic objects is a significant challenge in robotics, necessitating the development of grippers capable of safe and reliable manipulation without compromising speed. Traditional rigid grippers, when used in dynamic environments, often ...

Dueling bandits are widely used to model preferential feedback prevalent in many applications such as recommendation systems and ranking. In this paper, we study the Borda regret minimization problem for dueling bandits, which aims to identify the item ...

Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained unified spaces. In ...

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity of user-...

A simple yet effective material model was proposed by Zhao et al. (2019) and demonstrated to be capable of modeling the shape transformations of various planar and three-dimensional material samples programmed with the so-called “hard-magnetic ...

Public supervision, as a source of social behavioral norms and moral guidelines, exerts important guidance and influence on individuals. To maintain public order, in this study, we propose a reputation incentives mechanism with public supervision,...

• We propose a reputation incentives mechanism with public supervision.
• The dynamic process takes into account individual differences and incorporates diverse evaluation standards.
• We study on the impact of the evaluation intensity ...

Traditional line-tracking cars usually use wired transmission to perform real-time AD (Analog to Digital) signal sampling and control, which has many disadvantages, such as cumbersome steps, multiple constraints, poor real-time performance, and low time ...

In order to solve the problem of low accuracy of workers' assembly action recognition relying only on human skeletal data in complex background change environments, an assembly action recognition network based on dual stream fusion of skeleton and video ...

Adversarial learning has proven to be an effective method for capturing transferable features for unsupervised domain adaptation. However, some existing conditional adversarial domain adaptation methods assign equal importance to different ...

• The feature norms of each domain usually follow a complex distribution.
• Data transferability is precisely quantified by Gaussian-uniform mixture model.
• Mixed information can better guide features away from the decision boundary.

Conventional pipeline of multimodal learning consists of three stages, including encoding, fusion, and decoding. Most existing methods under missing modality condition focus on the first stage and aim to learn the modality invariant representation or ...

Millimeter wave radars can perceive through occlusions like dust, fog, smoke and clothes. But compared to cameras and lidars, their perception quality is orders of magnitude poorer. RadarHD [3] tackles this problem of poor quality by creating a machine ...

Negation is a fundamental grammatical construct that plays a crucial role in understanding QA tasks. It has been revealed that models trained with SQuAD1 still produce original responses when presented with negated sentences. To mitigate this ...