Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection

07/25/2023
by   Yichao Cao, et al.
0

Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the challenges posed by the numerous interaction combinations, they also offer opportunities for multimodal learning of visual texts. In this paper, we present a systematic and unified framework (RmLR) that enhances HOI detection by incorporating structured text knowledge. Firstly, we qualitatively and quantitatively analyze the loss of interaction information in the two-stage HOI detector and propose a re-mining strategy to generate more comprehensive visual representation.Secondly, we design more fine-grained sentence- and word-level alignment and knowledge transfer strategies to effectively address the many-to-many matching problem between multiple interactions and multiple texts.These strategies alleviate the matching confusion problem that arises when multiple interactions occur simultaneously, thereby improving the effectiveness of the alignment process. Finally, HOI reasoning by visual features augmented with textual knowledge substantially improves the understanding of interactions. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on public benchmarks. We further analyze the effects of different components of our approach to provide insights into its efficacy.

READ FULL TEXT

page 2

page 4

page 7

page 13

page 14

research
10/17/2022

Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval

Image-sentence retrieval has attracted extensive research attention in m...
research
06/11/2021

Step-Wise Hierarchical Alignment Network for Image-Text Matching

Image-text matching plays a central role in bridging the semantic gap be...
research
09/18/2023

Unified Coarse-to-Fine Alignment for Video-Text Retrieval

The canonical approach to video-text retrieval leverages a coarse-graine...
research
06/23/2019

Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments

Description-based person re-identification (Re-id) is an important task ...
research
04/15/2016

Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

Semantic matching, which aims to determine the matching degree between t...
research
07/02/2022

Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review

The intelligent dialogue system, aiming at communicating with humans har...
research
10/26/2022

Visual Answer Localization with Cross-modal Mutual Knowledge Transfer

The goal of visual answering localization (VAL) in the video is to obtai...

Please sign up or login with your details

Forgot password? Click here to reset