SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2012.05689 · 2020

Interactive Fusion of Multi-level Features for Compositional Activity Recognition

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

To understand a complex action, multiple sources of information, including appearance, positional, and semantic features, need to be integrated. However, these features are difficult to be fused since they often differ significantly in modality and dimensionality. In this paper, we present a novel framework that accomplishes this goal by interactive fusion, namely, projecting features across different spaces and guiding it using an auxiliary prediction task. Specifically, we implement the framework in three steps, namely, positional-to-appearance feature extraction, semantic feature interaction, and semantic-to-positional prediction. We evaluate our approach on two action recognition datasets, Something-Something and Charades. Interactive fusion achieves consistent accuracy gain beyond off-the-shelf action recognition algorithms. In particular, on Something-Else, the compositional setting of Something-Something, interactive fusion reports a remarkable gain of 2.9% in terms of top-1 accuracy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2012.05689")
get_code_for_paper("2012.05689")
have("2012.05689")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2012.05689.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2012.05689.svg)](https://syntology.ai/paper/2012.05689)

Connect an agent — have() is free.