Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Quan, Fang, Jinwei, Yuan, Rui, Tang, Xi, Qi, Yuxin, Zhang, Ke, Yuan, Chun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913884132081664
author Zhang, Quan
Fang, Jinwei
Yuan, Rui
Tang, Xi
Qi, Yuxin
Zhang, Ke
Yuan, Chun
author_facet Zhang, Quan
Fang, Jinwei
Yuan, Rui
Tang, Xi
Qi, Yuxin
Zhang, Ke
Yuan, Chun
contents Recent breakthroughs in Multimodal Large Language Models (MLLMs) have gained significant recognition within the deep learning community, where the fusion of the Video Foundation Models (VFMs) and Large Language Models(LLMs) has proven instrumental in constructing robust video understanding systems, effectively surmounting constraints associated with predefined visual tasks. These sophisticated MLLMs exhibit remarkable proficiency in comprehending videos, swiftly attaining unprecedented performance levels across diverse benchmarks. However, their operation demands substantial memory and computational resources, underscoring the continued importance of traditional models in video comprehension tasks. In this paper, we introduce a novel learning paradigm termed MLLM4WTAL. This paradigm harnesses the potential of MLLM to offer temporal action key semantics and complete semantic priors for conventional Weakly-supervised Temporal Action Localization (WTAL) methods. MLLM4WTAL facilitates the enhancement of WTAL by leveraging MLLM guidance. It achieves this by integrating two distinct modules: Key Semantic Matching (KSM) and Complete Semantic Reconstruction (CSR). These modules work in tandem to effectively address prevalent issues like incomplete and over-complete outcomes common in WTAL methods. Rigorous experiments are conducted to validate the efficacy of our proposed approach in augmenting the performance of various heterogeneous WTAL models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08466
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models
Zhang, Quan
Fang, Jinwei
Yuan, Rui
Tang, Xi
Qi, Yuxin
Zhang, Ke
Yuan, Chun
Computer Vision and Pattern Recognition
Recent breakthroughs in Multimodal Large Language Models (MLLMs) have gained significant recognition within the deep learning community, where the fusion of the Video Foundation Models (VFMs) and Large Language Models(LLMs) has proven instrumental in constructing robust video understanding systems, effectively surmounting constraints associated with predefined visual tasks. These sophisticated MLLMs exhibit remarkable proficiency in comprehending videos, swiftly attaining unprecedented performance levels across diverse benchmarks. However, their operation demands substantial memory and computational resources, underscoring the continued importance of traditional models in video comprehension tasks. In this paper, we introduce a novel learning paradigm termed MLLM4WTAL. This paradigm harnesses the potential of MLLM to offer temporal action key semantics and complete semantic priors for conventional Weakly-supervised Temporal Action Localization (WTAL) methods. MLLM4WTAL facilitates the enhancement of WTAL by leveraging MLLM guidance. It achieves this by integrating two distinct modules: Key Semantic Matching (KSM) and Complete Semantic Reconstruction (CSR). These modules work in tandem to effectively address prevalent issues like incomplete and over-complete outcomes common in WTAL methods. Rigorous experiments are conducted to validate the efficacy of our proposed approach in augmenting the performance of various heterogeneous WTAL models.
title Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.08466