Weakly-Supervised Alignment of Video With Text - LEAR Access content directly
Conference Papers Year : 2015

Weakly-Supervised Alignment of Video With Text

Abstract

Suppose that we are given a set of videos, along with natural language descriptions in the form of multiple sentences (e.g., manual annotations, movie scripts, sport summaries etc.), and that these sentences appear in the same temporal order as their visual counterparts. We propose in this paper a method for aligning the two modalities, i.e., automatically providing a time stamp for every sentence. Given vectorial features for both video and text, we propose to cast this task as a temporal assignment problem, with an implicit linear mapping between the two feature modalities. We formulate this problem as an integer quadratic program, and solve its continuous convex relaxation using an efficient conditional gradient algorithm. Several rounding procedures are proposed to construct the final integer solution. After demonstrating significant improvements over the state of the art on the related task of aligning video with symbolic labels [7], we evaluate our method on a challenging dataset of videos with associated textual descriptions [36], using both bag-of-words and continuous representations for text.
Fichier principal
Vignette du fichier
main.pdf (5.28 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01154523 , version 1 (22-05-2015)
hal-01154523 , version 2 (01-12-2015)

Identifiers

Cite

Piotr Bojanowski, Rémi Lajugie, Edouard Grave, Francis Bach, Ivan Laptev, et al.. Weakly-Supervised Alignment of Video With Text. ICCV - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. pp.4462-4470, ⟨10.1109/ICCV.2015.507⟩. ⟨hal-01154523v2⟩
825 View
447 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More