Image-based visual-language (I-VL) pre-training has shown great success for learning joint
visual-textual representations from large-scale web data, revealing remarkable ability for …

We aim to understand how actions are performed and identify subtle differences, such as'
fold firmly'vs.'fold gently'. To this end, we propose a method which recognizes adverbs …

Most methods tackle zero-shot video classification by aligning visual-semantic
representations within seen classes, which limits generalization to unseen classes. To …

Zero-shot action recognition (ZSAR) aims to learn an alignment model between videos and
class descriptions of seen actions that is transferable to unseen actions. The text queries …

This paper presents a novel approach to Zero-Shot Action Recognition. Recent works have
explored the detection and classification of objects to obtain semantic information from …

Zero-shot action recognition (ZSAR) aims to recognize unseen action categories in the test
set without corresponding training examples. Most existing zero-shot methods follow the …

Video moment retrieval (VMR) is a cutting-edge vision-language task locating a segment in
a video according to the query. Though the methods have achieved significant performance …

The leverage of large volumes of web videos paired with the query (short phrase for
searching the video) or surrounding text (long textual description, eg, video title) offers an …

Video attributes, which leverage video contents to instantiate class semantics, play a critical
role in diversifying semantics in zero-shot video classification, thereby facilitating semantic …

This paper investigates the problem of zero-shot action recognition, in the setting where no
training videos with seen actions are available. For this challenging scenario, the current …