Semantic segmentation aims to classify every pixel of an input image. Considering the
difficulty of acquiring dense labels, researchers have recently been resorting to weak labels …

Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels
usually results in inferior model performance. Existing state-of-the-art methods primarily …

With the recent development of deep learning technology comes the wide use of artificial
intelligence (AI) models in various domains. AI shows good performance for definite …

Scene Graph Generation (SGG) aims to detect the objects and their pairwise predicates in
an image. Existing SGG methods mainly fulfil the challenging predicate prediction task that …

One-shot semantic image segmentation aims to segment the object regions for the novel
class with only one annotated image. Recent works adopt the episodic training strategy to …

Due to the existence of label noise in web images and the high memorization capacity of
deep neural networks, training deep fine-grained (FG) models directly through web images …

Most existing action recognition approaches directly leverage the video-level features to
recognize human actions from videos. Although these methods have made remarkable …

Labeling objects at a subordinate level typically requires expert knowledge, which is not
always available when using random annotators. As such, learning directly from web …

The lack of sufficient training data has been one obstacle to fine-grained visual classification
research because labeling subcategories generally requires specialist knowledge. As one …

Humans predominantly use verbal utterances and nonverbal gestures (eg, eye gaze and
pointing gestures) in their natural interactions. For instance, pointing gestures and verbal …