Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning - PaRis AI Research InstitutE Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Résumé

In this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale. The Vid2Seq architecture augments a language model with special time tokens, allowing it to seamlessly predict event boundaries and textual descriptions in the same output sequence. Such a unified model requires large-scale training data, which is not available in current annotated datasets. We show that it is possible to leverage unlabeled narrated videos for dense video captioning, by reformulating sentence boundaries of transcribed speech as pseudo event boundaries, and using the transcribed speech sentences as pseudo event captions. The resulting Vid2Seq model pretrained on the YT-Temporal-1B dataset improves the state of the art on a variety of dense video captioning benchmarks including YouCook2, ViTT and ActivityNet Captions. Vid2Seq also generalizes well to the tasks of video paragraph captioning and video clip captioning, and to few-shot settings.
Fichier principal
Vignette du fichier
vid2seq.pdf (5.55 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04039246 , version 1 (21-03-2023)

Identifiants

Citer

Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo, Antoine Miech, Jordi Pont-Tuset, et al.. Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning. CVPR 2023 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2023, Vancouver, Canada. ⟨hal-04039246⟩
179 Consultations
50 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More