Multi-modal services, typically integrated by visual, audio, and haptic signals, have been considered as promising killer services in 5G and beyond 5G era. However, due to essential difference among these signals, how to guarantee quality of multi-moda…
In this paper, we propose an iterative feature matching framework for self-supervised depth estimation in indoor scenes. Conventional methods usually leverage the structure-from-motion supervision to help the photometric optimization escape from the lo…
Traditional steganography methods are usually designed on a lossless channel; thus, messages are often not extracted correctly from an image transmitted over a lossy channel that includes attacks such as scaling. To address this issue, in recent years,…
The performance of stereo vision tasks degrades when haze exists in the input stereo image pair. Independently applying single image dehazing algorithm on left and right images is not optimal. To overcome the problem, we propose an effective framework,…
Self-supervised representation learning for videos has been very attractive recently because these methods exploit the information inherently obtained from the video itself instead of annotated labels that is quite time-consuming. However, existing met…
Recently, research on six-degree-of-freedom virtual reality (VR) systems based on a light field (LF) has been actively conducted. The LF-based approach is photorealistic and less prone to errors than the existing three-dimensional (3D) modeling-based a…
Image captioning is one of the primary goals in computer vision which aims to automatically generate natural descriptions for images. Intuitively, human visual system can notice some stimulating regions at first glance, and then volitionally focus on i…
In domain adaptation (DA), label-induced losses generally occupy a dominant position and most previous models regard hard or soft labels as their inputs. However, these two types of labels may mislead the modeling process of label-induced losses since …
Recently, most coverless image steganography (CIS) methods are based on robust mapping rules. However, due to the limited mapping expression relationship between secret information and hash sequence, it is a challenge to further improve the hiding abil…
Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle di…