COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

TL;DR

COOT introduces a hierarchical transformer model that effectively captures multi-level semantics and cross-modal interactions in video-text tasks, achieving state-of-the-art results with fewer parameters.

Contribution

It proposes a novel hierarchical transformer architecture with attention-aware aggregation, inter-level interaction modeling, and cycle-consistency loss for improved video-text understanding.

Findings

Outperforms state-of-the-art on multiple benchmarks.

Uses fewer parameters than comparable models.

Demonstrates effective multi-level semantic modeling.

Abstract

Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics. In this paper, we propose a Cooperative hierarchical Transformer (COOT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities. The method consists of three major components: an attention-aware feature aggregation layer, which leverages the local temporal context (intra-level, e.g., within a clip), a contextual transformer to learn the interactions between low-level and high-level semantics (inter-level, e.g. clip-video, sentence-paragraph), and a cross-modal cycle-consistency loss to connect video and text. The resulting method compares favorably to the state of the art on several benchmarks while having few parameters. All code is available open-source at https://github.com/gingsi/coot-videotext