Publications by authors named "Dengpan Fu"
Improving Person Re-identification with Iterative Impression Aggregation.
IEEE Trans Image Process
October 2020
Article Synopsis
- Our understanding of a person evolves over time as we gather more information, similar to the concept of person re-identification (re-ID), where a query image's representation is updated with data from a candidate set.
- A new attention-based aggregation method is proposed, showcasing strong performance on major benchmarks like CUHK03, Market-1501, and DukeMTMC, rivaling advanced re-ranking techniques.
- This method is adaptable, allowing for the use of various representations and similarity metrics, which led to achieving state-of-the-art results in person re-ID and highlighting its broad applicability.
In this paper, we present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation.
View Article and Find Full Text PDF