Unsupervised domain adaptive video action recognition aims to recognize actions of a
target domain using a model trained with only out-of-domain (source) annotations. The …

Video-text retrieval is an emerging stream in both computer vision and natural language
processing communities, which aims to find relevant videos given text queries. In this paper …

First person action recognition is becoming an increasingly researched area thanks to the
rising popularity of wearable cameras. This is bringing to light cross-domain issues that are …

Multi-modal learning has gained significant attention due to its ability to enhance machine
learning algorithms. However, it brings challenges related to modality heterogeneity and …

Predicting future action locations is vital for applications like human-robot collaboration.
While some computer vision tasks have made progress in predicting human actions …

We propose a novel domain adaptive action detection approach and a new adaptation
protocol that leverages the recent advancements in image-level unsupervised domain …

Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving
videos based on their relevance to an unseen text query. To compensate for the lack of …

With the advent of collaborative manipulators, the community is pushing the limits of human-
robot interaction with novel control, planning, and task allocation strategies. For a purposeful …

We have witnessed impressive advances in video action understanding. Increased dataset
sizes, variability, and computation availability have enabled leaps in performance and task …

Existing video-based action recognition systems typically require dense annotation and
struggle in environments when there is significant distribution shift relative to the training …