The performance of visual question answering (VQA) has witnessed great progress over the
last few years. However, many current VQA models tend to rely on superficial linguistic …

Diabetic Retinopathy (DR) is a serious consequence of prolonged diabetic patients that
causes vision threatening issues and irreversible blindness problem. In the beginning stage …

Multiple object tracking (MOT), as a typical application scenario of computer vision, has
attracted significant attention from both academic and industrial communities. With its rapid …

Change captioning aims to describe the semantic change between a pair of images with
natural language while remaining immune to viewpoint change. Based on the encoder …

Tracking pedestrians in crowded scenes is a challenging task. Existing transformer-based
tracking methods integrate detection and tracking into a unified model, which simplifies the …

Human-centric perception is the core of diverse computer vision tasks and has been a long-
standing research focus. However, previous research studied these human-centric tasks …

Abstract Document Image Inpainting (DII) has been applied to degraded documents,
including financial and historical documents, to enhance the legibility of images for:(1) …

Nutrient stress can impose significant metabolic strain on plants, resulting in declining
agricultural productivity. Nitrogen, phosphorus, and potassium are essential growth-limiting …

In many sports, player re-identification is crucial for automatic video processing and
analysis. However, most of the current studies on player re-identification in multi-or single …

Despite the great progresses achieved by commonly-used 3D CNNs and two-stream
methods in action recognition, they cause heavy computational burden which are inefficient …