Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Ye, He, Jixuan, Li, Wanhua, Kim, Junsik, Wei, Donglai, Pfister, Hanspeter, Chen, Chang Wen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2404.00801
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914878921375744
author Liu, Ye
He, Jixuan
Li, Wanhua
Kim, Junsik
Wei, Donglai
Pfister, Hanspeter
Chen, Chang Wen
author_facet Liu, Ye
He, Jixuan
Li, Wanhua
Kim, Junsik
Wei, Donglai
Pfister, Hanspeter
Chen, Chang Wen
contents Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent Tuning ($R^2$-Tuning), a parameter- and memory-efficient transfer learning framework for video temporal grounding. Our method learns a lightweight $R^2$ Block containing only 1.5% of the total parameters to perform progressive spatial-temporal modeling. Starting from the last layer of CLIP, $R^2$ Block recurrently aggregates spatial features from earlier layers, then refines temporal correlation conditioning on the given query, resulting in a coarse-to-fine scheme. $R^2$-Tuning achieves state-of-the-art performance across three VTG tasks (i.e., moment retrieval, highlight detection, and video summarization) on six public benchmarks (i.e., QVHighlights, Charades-STA, Ego4D-NLQ, TACoS, YouTube Highlights, and TVSum) even without the additional backbone, demonstrating the significance and effectiveness of the proposed scheme. Our code is available at https://github.com/yeliudev/R2-Tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00801
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle $R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding
Liu, Ye
He, Jixuan
Li, Wanhua
Kim, Junsik
Wei, Donglai
Pfister, Hanspeter
Chen, Chang Wen
Computer Vision and Pattern Recognition
Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent Tuning ($R^2$-Tuning), a parameter- and memory-efficient transfer learning framework for video temporal grounding. Our method learns a lightweight $R^2$ Block containing only 1.5% of the total parameters to perform progressive spatial-temporal modeling. Starting from the last layer of CLIP, $R^2$ Block recurrently aggregates spatial features from earlier layers, then refines temporal correlation conditioning on the given query, resulting in a coarse-to-fine scheme. $R^2$-Tuning achieves state-of-the-art performance across three VTG tasks (i.e., moment retrieval, highlight detection, and video summarization) on six public benchmarks (i.e., QVHighlights, Charades-STA, Ego4D-NLQ, TACoS, YouTube Highlights, and TVSum) even without the additional backbone, demonstrating the significance and effectiveness of the proposed scheme. Our code is available at https://github.com/yeliudev/R2-Tuning.
title $R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.00801