Text-Enhanced Zero-Shot Action Recognition: A training-free approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bosetti, Massimo, Zhang, Shibingfeng, Liberatori, Benedetta, Zara, Giacomo, Ricci, Elisa, Rota, Paolo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912022428385280
author Bosetti, Massimo
Zhang, Shibingfeng
Liberatori, Benedetta
Zara, Giacomo
Ricci, Elisa
Rota, Paolo
author_facet Bosetti, Massimo
Zhang, Shibingfeng
Liberatori, Benedetta
Zara, Giacomo
Ricci, Elisa
Rota, Paolo
contents Vision-language models (VLMs) have demonstrated remarkable performance across various visual tasks, leveraging joint learning of visual and textual representations. While these models excel in zero-shot image tasks, their application to zero-shot video action recognition (ZSVAR) remains challenging due to the dynamic and temporal nature of actions. Existing methods for ZS-VAR typically require extensive training on specific datasets, which can be resource-intensive and may introduce domain biases. In this work, we propose Text-Enhanced Action Recognition (TEAR), a simple approach to ZS-VAR that is training-free and does not require the availability of training data or extensive computational resources. Drawing inspiration from recent findings in vision and language literature, we utilize action descriptors for decomposition and contextual information to enhance zero-shot action recognition. Through experiments on UCF101, HMDB51, and Kinetics-600 datasets, we showcase the effectiveness and applicability of our proposed approach in addressing the challenges of ZS-VAR.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text-Enhanced Zero-Shot Action Recognition: A training-free approach
Bosetti, Massimo
Zhang, Shibingfeng
Liberatori, Benedetta
Zara, Giacomo
Ricci, Elisa
Rota, Paolo
Computer Vision and Pattern Recognition
Vision-language models (VLMs) have demonstrated remarkable performance across various visual tasks, leveraging joint learning of visual and textual representations. While these models excel in zero-shot image tasks, their application to zero-shot video action recognition (ZSVAR) remains challenging due to the dynamic and temporal nature of actions. Existing methods for ZS-VAR typically require extensive training on specific datasets, which can be resource-intensive and may introduce domain biases. In this work, we propose Text-Enhanced Action Recognition (TEAR), a simple approach to ZS-VAR that is training-free and does not require the availability of training data or extensive computational resources. Drawing inspiration from recent findings in vision and language literature, we utilize action descriptors for decomposition and contextual information to enhance zero-shot action recognition. Through experiments on UCF101, HMDB51, and Kinetics-600 datasets, we showcase the effectiveness and applicability of our proposed approach in addressing the challenges of ZS-VAR.
title Text-Enhanced Zero-Shot Action Recognition: A training-free approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.16412