Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Jia-Run, Lin, Kun-Yu, Meng, Jingke, Zheng, Wei-Shi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909295191261184
author Du, Jia-Run
Lin, Kun-Yu
Meng, Jingke
Zheng, Wei-Shi
author_facet Du, Jia-Run
Lin, Kun-Yu
Meng, Jingke
Zheng, Wei-Shi
contents To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. They typically develop a category-agnostic action detector and combine it with the Contrastive Language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for \textit{unseen} categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposal-level objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the category-agnostic dynamic information of actions. Besides, we introduce a Static-Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., Thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13777
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization
Du, Jia-Run
Lin, Kun-Yu
Meng, Jingke
Zheng, Wei-Shi
Computer Vision and Pattern Recognition
To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. They typically develop a category-agnostic action detector and combine it with the Contrastive Language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for \textit{unseen} categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposal-level objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the category-agnostic dynamic information of actions. Besides, we introduce a Static-Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., Thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively.
title Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.13777