We propose and address a new generalisation problem: can a model trained for action
recognition successfully classify actions when they are performed within a previously …

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 …

In the world of action recognition research, one primary focus has been on how to construct
and train networks to model the spatial-temporal volume of an input video. These methods …

Current state-of-the-art video models process a video clip as a long sequence of spatio-
temporal tokens. However, they do not explicitly model objects, their interactions across the …

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 …

This work addresses the task of action recognition in video sequences. In real world
applications, this task is quite challenging due to the complex background of video content …

In this work we employ multitask learning to capitalize on the structure that exists in related
supervised tasks to train complex neural networks. It allows training a network for multiple …

The canonical approach to video action recognition dictates a neural network model to do a
classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of …

The goal of building a benchmark (suite of datasets) is to provide a unified protocol for fair
evaluation and thus facilitate the evolution of a specific area. Nonetheless, we point out that …

We describe a novel cross-modal embedding space for actions, named Action2Vec, which
combines linguistic cues from class labels with spatio-temporal features derived from video …