Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) …
Learning to classify video data from classes not included in the training data, ie video-based zero-shot learning, is challenging. We conjecture that the natural alignment between the …
We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR). Our model employs a conceptually …
Abstract Zero-Shot Learning (ZSL) has rapidly advanced in recent years. Towards overcoming the annotation bottleneck in the Dynamic Hand Gesture Recognition (DHGR) …
This paper tackles the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign classes to recognize the instances of …
Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we …
In this paper, we study current and upcoming frontiers across the landscape of skeleton- based human action recognition. To study skeleton-action recognition in the wild, we …
K Doshi, Y Yilmaz - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
While video action recognition has been an active area of research for several years, zero- shot action recognition has only recently started gaining traction. In this work, we propose a …
S Pu, K Zhao, M Zheng - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Most methods tackle zero-shot video classification by aligning visual-semantic representations within seen classes, which limits generalization to unseen classes. To …