Search Results

While margin-based deep face recognition models, such as ArcFace and AdaFace, have achieved remarkable successes over recent years, they may suffer from degraded performances when encountering training sets corrupted with noises. This is often inevitable ...

Explaining what part of the input images primarily contributed to the predicted classification results by deep models has been widely researched over the years and many effective methods have been reported in the literature, for which deep Taylor ...

Various types of software artifacts are produced in the software life cycle processes. Although traceability between different artifacts is beneficial for software development, the actual practice of modeling and maintaining traceability is not ...

Generative Artificial Intelligence (AI) has revolutionized image generation in the realm of consumer electronics, which has illustrated its significant impact on product development and user experiences. In this paper, we propose a class conditioned GAN ...

Currently, weakly supervised semantic segmentation approaches adopt the Class Activation Map (CAM) to generate the initial attention maps from the standard classification backbone network, with only image-level class labels as training ...

Display Omitted

• A novel “destruction learning” method via self-supervised manner.
• The MDC module is with stronger sensitivity to the Mid-Level local parts.
• The LD Module explores the local feature details from the original images.

Owing to the rapid development of emerging 360<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula> panoramic imaging techniques, indoor 360<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula> ...

With the rapid development of high-resolution 3D vision applications, the traditional way of manipulating surface detail requires considerable memory and computing time. To address these problems, we introduce an efficient surface detail processing ...

In this paper, we propose a stereoscopic image thumbnail generation method guided by the stereoscopic image saliency. Specifically, we utilize an uncertain-weighted fusion mechanism to combine the spatial saliency information with the saliency ...

Domain adaptation techniques learn transferable knowledge from a source domain to a target domain and train models that generalize well in the target domain. Unfortunately, a majority of the existing techniques are only applicable to scenarios that the ...

• Our method takes the ordering of pairwise distance as the supervisory signal to learn the similarity score function.

Unsupervised clustering categorizes a sample set into several groups, where the samples in the same group share high-level concepts. As the clustering performances are heavily determined by the metric to assess the similarity between ...

To guarantee the safety and security of a real-time mobile system such as an intelligent transportation system, it is necessary to model and analyze its behaviors prior to actual development. In particular, the mobile objects in such systems must be ...

Generative learning in pixel domain has achieved great success in exploiting their correlations in processing images towards desired objectives, yet learning in frequency domain could provide added benefits in exploiting pixel correlations ...

In this paper, we propose a portrait relighting method based on deep reinforcement learning (called PR-RL). Our PR-RL model could conduct portrait relighting by sequentially predicting local light editing strokes, and use strokes to conduct dodge and burn ...

Being able to predict the salient object is of fundamental importance in image processing and computer vision. With numerous approaches proposed for automatic image and video salient object detection, much less work has been dedicated to detecting and ...

This paper proposes a collaborative deep reinforcement learning model for automatic image cropping (called CDRL-IC). By modeling image cropping as a decision-making process of reinforcement learning, our model could generate optimal cropping result in a ...

While current research on multimedia is essentially dealing with the information derived from our observations of the world, internal activities inside human brains, such as imaginations and memories of past events etc., could become a brand new concept ...

Essentially, the current concept of multimedia is limited to presenting what people see in their eyes. What people think inside brains, however, remains a rich source of multimedia, such as imaginations of paradise and memories of good old days etc. In ...

Zero-shot domain adaptation (ZSDA) is a category of domain adaptation problems where neither data sample nor label is available for parameter learning in the target domain. With the hypothesis that the shift between a given pair of domains is ...

Functional decomposition is the process of resolving a functional relationship into its constituent parts in such a way that the original function can be recomposed from those parts by functional composition. Perfect decomposition requires the ...

• Based on spectral analysis, we propose a novel deep learning framework, SA-Net for deep image clustering.

Although supervised deep representation learning has attracted enormous attentions across areas of pattern recognition and computer vision, little progress has been made towards unsupervised deep representation learning for image ...