Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversa…
In this paper, based on the double strip silicon nitride platform, we designed and fabricated a low loss continuously tunable broadband optical delay line, which contains a 5-bit optical switched d…
Object attention maps generated by image classifiers are usually used as priors for weakly supervised semantic segmentation. However, attention maps usually locate the most discriminative object pa…
We present the first systematic study on concealed object detection (COD), which aims to identify objects that are visually embedded in their background. The high intrinsic similarities between the…
Imitation learning has recently been applied to mimic the operation of a cameraman in existing autonomous camera systems. To imitate a certain demonstration video, existing methods require users to…
In this article, we conduct a comprehensive study on the co-salient object detection (CoSOD) problem for images. CoSOD is an emerging and rapidly growing extension of salient object detection (SOD)…
The achievement of cylindrical vector beam (CVB) multiplexing has shown advantages in enlarging communication capacities and all-optical interconnections. While various mode transformation technolo…
In recent decades, recommender systems have been well studied and widely applied. However, most recommenders unilaterally optimize the results from the buying customers’ views without considering…
Optical vortex beams (VBs) carrying orbital angular momentum (OAM) have shown significant multiplexing ability in radio-over-fiber communication by virtue of their intrinsic mode orthogonality. How…
A compact mode converter (MC) has been demonstrated based on tapered hole-assisted dual-core fiber (HADCF). The MC is fabricated by splicing single mode fiber (SMF) and a piece of HADCF that is com…