Text-Visual Prompting for Efficient 2D Temporal Video Grounding

TL;DR

This paper introduces a text-visual prompting framework for efficient 2D temporal video grounding, significantly reducing computational complexity while boosting performance on benchmark datasets.

Contribution

The authors propose a novel prompting approach that enables effective 2D TVG, replacing 3D CNNs, and introduce a new loss function for improved learning.

Findings

Achieves up to 30.77% performance improvement on ActivityNet Captions.

Provides 5x faster inference compared to 3D CNN-based methods.

Demonstrates effectiveness on Charades-STA and ActivityNet datasets.

Abstract

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call 'prompts') into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features. Further, we propose a Temporal-Distance IoU (TDIoU) loss for efficient learning of TVG. Experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement on Charades-STA and 30.77% improvement on ActivityNet Captions) and achieves 5x inference acceleration over TVG using 3D visual features. Codes are available at Open.Intel.