Deep learning models have achieved excellent recognition results on large-scale video
benchmarks. However, they perform poorly when applied to videos with rare scenes or …

Action recognition in videos is a challenging task due to the complexity of the spatio-
temporal patterns to model and the difficulty to acquire and learn on large quantities of video …

Abstract Convolutional Neural Networks (CNNs) have been the dominant model for video
action recognition. Due to the huge memory and compute demand, popular action …

We study the task of robust feature representations, aiming to generalize well on multiple
datasets for action recognition. We build our method on Transformers for its efficacy …

Training an effective video action recognition model poses significant computational
challenges, particularly under limited resource budgets. Current methods primarily aim to …

In this dissertation, we explore different ways to perform human action recognition in video
clips. We focus on data efficiency, proposing new approaches that alleviate the need for …

Human activities often occur in specific scene contexts, eg, playing basketball on a
basketball court. Training a model using existing video datasets thus inevitably captures and …

Inspired by the observation that humans are able to process videos efficiently by only paying
attention where and when it is needed, we propose an interpretable and easy plug-in spatial …

The existing action recognition methods are mainly based on clip-level classifiers such as
two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and …

Most popular deep models for action recognition in videos generate independent
predictions for short clips, which are then pooled heuristically to assign an action label to the …