CVCLLGMLJan 22, 2020

Zero-Shot Activity Recognition with Videos

arXiv:2002.02265v1
AI Analysis

This work addresses the problem of recognizing unseen activities in videos for computer vision applications, representing an incremental advancement in zero-shot learning.

The paper tackled zero-shot activity recognition from videos by introducing an auto-encoder model to create a multimodal joint embedding space between visual and textual features, achieving results evaluated with top-n accuracy and mean Nearest Neighbor Overlap metrics.

In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual side, we used activity videos and a state-of-the-art 3D convolutional action recognition network to extract the features. On the textual side, we worked with GloVe word embeddings. The zero-shot recognition results are evaluated by top-n accuracy. Then, the manifold learning ability is measured by mean Nearest Neighbor Overlap. In the end, we provide an extensive discussion over the results and the future directions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes