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 …
X Zhou, A Arnab, C Sun… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …
L Yang, Y Huang, Y Sugano… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …
J Zhou, Z Fu, Q Huang, Q Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
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 …
G Kapidis, R Poppe, E Van Dam… - Proceedings of the …, 2019 - openaccess.thecvf.com
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 …
A Deng, T Yang, C Chen - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
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 …