With the recent renaissance of deep convolutional neural networks (CNNs), encouraging
breakthroughs have been achieved on the supervised recognition tasks, where each class …

Due to the complementary benefits of visible (RGB) and thermal infrared (T) data, RGB-T
object tracking attracts more and more attention recently for boosting the performance under …

Noisy training set usually leads to the degradation of generalization and robustness of
neural networks. In this paper, we propose using a theoretically guaranteed noisy label …

Recently, learning with soft labels has been shown to achieve better performance than
learning with hard labels in terms of model generalization, calibration, and robustness …

Emotion is a key element in user-generated video. However, it is difficult to understand
emotions conveyed in such videos due to the complex and unstructured nature of user …

A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation
model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the …

Deep learning based models have excelled in many computer vision tasks and appear to
surpass humans' performance. However, these models require an avalanche of expensive …

With the recent renaissance of deep convolution neural networks, encouraging
breakthroughs have been achieved on the supervised recognition tasks, where each class …

The existing graph-based RGBT tracking methods mainly focus on assigning a weight to
each local image patch to suppress background influence in target bounding box, but the …

We propose a scalable Bayesian preference learning method for jointly predicting the
preferences of individuals as well as the consensus of a crowd from pairwise labels …