Abstract Person Re-Identification (Re-ID) is a critical aspect of visual surveillance systems,
which aims to automatically recognize and locate individuals across a multi-camera network …

Visual representation learning is ubiquitous in various real-world applications, including
visual comprehension, video understanding, multi-modal analysis, human-computer …

Thanks for the cross-modal retrieval techniques, visible-infrared (RGB-IR) person re-
identification (Re-ID) is achieved by projecting them into a common space, allowing person …

Due to the limited utilization of temporal relations in video re-id, the frame-level attention
regions of mainstream methods are partial and highly similar. To address this problem, we …

Video person re-identification (V-ReID) can leverage rich spatial-temporal information
embedded in sequence data to achieve better accuracy. However, it is vulnerable to the …

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at
least few task-relevant target domain training data are available for adaptation from the …

When compared to the image classification models, black-box adversarial attacks against
video classification models have been largely understudied. This could be possible …

Video object re-identification (reID) aims at re-identifying the same object under non-
overlapping cameras by matching the video tracklets with cropped video frames. The key …

The majority of methods for crafting adversarial attacks have focused on scenes with a
single dominant object (eg, images from ImageNet). On the other hand, natural scenes …

In recent years, the Transformer architecture has shown its superiority in the video-based
person re-identification task. Inspired by video representation learning, these methods …