Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog

TL;DR

This paper introduces an iterative search and reasoning framework for video-grounded dialog, improving understanding of dialog history and video content to generate more accurate responses.

Contribution

It proposes a novel framework combining textual and visual encoders with iterative reasoning, enhancing comprehension for video-grounded dialog tasks.

Findings

Effective in understanding complex dialog history

Improves visual content comprehension through iterative reasoning

Demonstrates superior performance on three public datasets

Abstract

In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response generation. Despite commendable progress made by existing approaches, they still face the challenges of incrementally understanding complex dialog history and assimilating video information. In response to these challenges, we present an iterative search and reasoning framework, which consists of a textual encoder, a visual encoder, and a generator. Specifically, we devise a path search and aggregation strategy in the textual encoder, mining core cues from dialog history that are pivotal to understanding the posed questions. Concurrently, our visual encoder harnesses an iterative reasoning network to extract and emphasize critical visual markers from videos, enhancing the depth of visual comprehension. Finally, we utilize the pre-trained GPT-2 model as our answer generator to decode the mined hidden clues into coherent and contextualized answers. Extensive experiments on three public datasets demonstrate the effectiveness and generalizability of our proposed framework.