Size-Modulated Deformable Attention in Spatio-Temporal Video Grounding Pipelines

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

Pattern Recognition - 27th International Conference, ICPR 2024, Proceedings, pp. 308-324, Lecture Notes in Computer Science ; Volume 15318

Abstract

The integration of attention mechanisms into computer vision tasks, inspired by the success of Transformers in natural language processing, has revolutionized various applications such as object detection and visual grounding. In this paper, we focus on spatio-temporal video grounding (STVG), a computer vision task that aims to jointly extract spatial and temporal regions from videos based on textual descriptions. Leveraging recent advancements in attention-based Transformer architectures, particularly in object detectors, and building upon a recent baseline model, we integrate two enhancements in attention modules: Width-Height Modulation and Deformable Attention units. These enhancements aim to improve the accuracy and efficiency of STVG techniques in two datasets, HC-STVG and VidSTG, by addressing challenges related to feature inconsistencies and prediction reliability across video frames. As a result, our study contributes to advancing the baseline models in spatio-temporal video grounding, bridging the gap between computer vision and natural language processing domains.

Description

Other note

Citation

Tiwari, H, Pehlivan Tort, S & Laaksonen, J 2024, Size-Modulated Deformable Attention in Spatio-Temporal Video Grounding Pipelines. in A Antonacopoulos, S Chaudhuri, R Chellappa, C-L Liu, S Bhattacharya & U Pal (eds), Pattern Recognition - 27th International Conference, ICPR 2024, Proceedings. Lecture Notes in Computer Science, vol. 15318, Springer, pp. 308-324, International Conference on Pattern Recognition, Kolkata, India, 01/12/2024. https://doi.org/10.1007/978-3-031-78456-9_20