As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for develo** new …

The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for
develo** colorectal cancer. However, polyp segmentation is a challenging task due to the …

Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality
rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be …

Recent image-to-image translation models have shown great success in map** local
textures between two domains. Existing approaches rely on a cycle-consistency constraint …

In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent
representation for controllable person image generation, which can produce realistic person …

Label assignment plays a significant role in modern object detection models. Detection
models may yield totally different performances with different label assignment strategies …

Fingerspelling in sign language has been the means of communicating technical terms and
proper nouns when they do not have dedicated sign language gestures. Automatic …

In this paper, we propose a simple while effective unsupervised deep feature transfer
algorithm for low resolution image classification. No fine-tuning on convenet filters is …

In the majority of object detection frameworks, the confidence of instance classification is
used as the quality criterion of predicted bounding boxes, like the confidence-based ranking …