QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024

TL;DR

QueryMamba introduces a novel encoder-decoder architecture with a statistical verb-noun interaction module, significantly improving video action forecasting accuracy and achieving top rankings in the Ego4D Long-Term Action Anticipation Challenge 2024.

Contribution

It proposes a new Mamba-based encoder-decoder model with a statistical verb-noun interaction module for enhanced video action prediction.

Findings

Achieved second place in the Ego4D LTA challenge.

Ranked first in noun prediction accuracy.

Demonstrated improved forecasting performance.

Abstract

This report presents a novel Mamba-based encoder-decoder architecture, QueryMamba, featuring an integrated verb-noun interaction module that utilizes a statistical verb-noun co-occurrence matrix to enhance video action forecasting. This architecture not only predicts verbs and nouns likely to occur based on historical data but also considers their joint occurrence to improve forecast accuracy. The efficacy of this approach is substantiated by experimental results, with the method achieving second place in the Ego4D LTA challenge and ranking first in noun prediction accuracy.