RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hannan, Tanveer, Islam, Md Mohaiminul, Seidl, Thomas, Bertasius, Gedas
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910525726654464
author Hannan, Tanveer
Islam, Md Mohaiminul
Seidl, Thomas
Bertasius, Gedas
author_facet Hannan, Tanveer
Islam, Md Mohaiminul
Seidl, Thomas
Bertasius, Gedas
contents Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply integrates clip retrieval and grounding into a single network capable of processing long videos into multiple granular levels, e.g., clips and frames. Its core component is a novel transformer encoder, RG-Encoder, that unifies the two stages through shared features and mutual optimization. The encoder incorporates a sparse attention mechanism and an attention loss to model both granularity jointly. Moreover, we introduce a contrastive clip sampling technique to mimic the long video paradigm closely during training. RGNet surpasses prior methods, showcasing state-of-the-art performance on long video temporal grounding (LVTG) datasets MAD and Ego4D.
format Preprint
id arxiv_https___arxiv_org_abs_2312_06729
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
Hannan, Tanveer
Islam, Md Mohaiminul
Seidl, Thomas
Bertasius, Gedas
Computer Vision and Pattern Recognition
Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply integrates clip retrieval and grounding into a single network capable of processing long videos into multiple granular levels, e.g., clips and frames. Its core component is a novel transformer encoder, RG-Encoder, that unifies the two stages through shared features and mutual optimization. The encoder incorporates a sparse attention mechanism and an attention loss to model both granularity jointly. Moreover, we introduce a contrastive clip sampling technique to mimic the long video paradigm closely during training. RGNet surpasses prior methods, showcasing state-of-the-art performance on long video temporal grounding (LVTG) datasets MAD and Ego4D.
title RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.06729