Publications

Search for or Navigate to? Dual Adaptive Thinking for Object Navigation

Published in ICCV, 2023

This paper proposes a dual adaptive thinking (DAT) model, allowing the agent to adaptively adjust whether to use search thinking or navigation thinking in the process of object navigation.

Recommended citation: Dang, Ronghao, et al. "Search for or Navigate to? Dual Adaptive Thinking for Object Navigation." arXiv preprint arXiv:2208.00553 (2022). http://academicpages.github.io/files/Dual_Adaptive_Thinking_for_Object_Navigation.pdf

A Dual Semantic-Aware Recurrent Global-Adaptive Network for Vision-and-Language Navigation

Published in IJCAI, 2023

This work proposes a dual semantic-aware recurrent global-adaptive network (DSRG) to address two problems in VLN. (1) The explicit information mining for significant guiding semantics concealed in both vision and language is still under-explored; (2) The previously structured map method provides the average historical appearance of visited nodes, while it ignores distinctive contributions of various images and potent information retention in the reasoning process.

Recommended citation: Wang, Liuyi, et al. "A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation." arXiv preprint arXiv:2305.03602 (2023). http://academicpages.github.io/files/DSRG.pdf

DL-PCN: Differential learning and parallel convolutional network for action recognition

Published in AI COMMUNICATION, 2023

This paper introduces a lightweight network, a Differential Learning and Parallel Convolutional Networks (DL-PCN), to reduce the computational burden of GCN skeleton action recognition method.

Recommended citation: Zeng, Qinyang, et al. "DL-PCN: Differential learning and parallel convolutional network for action recognition." AI Communications Preprint (2023): 1-15. https://content.iospress.com/articles/ai-communications/aic220268

RES-StS: Referring Expression Speaker via Self-training with Scorer for Goal-Oriented Vision-Language Navigation

Published in TCSVT, 2023

This work aims to improve the robustness and generalization of the navigator by dynamically providing high-quality pseudo-instructions using a proposed RES-StS paradigm.

Recommended citation: L. Wang, Z. He, R. Dang, H. Chen, C. Liu and Q. Chen, "RES-StS: Referring Expression Speaker via Self-training with Scorer for Goal-Oriented Vision-Language Navigation," in IEEE Transactions on Circuits and Systems for Video Technology. http://academicpages.github.io/files/RES-STS.pdf

Unbiased Directed Object Attention Graph for Object Navigation

Published in ACMMM, 2022

This paper discovers the problem of object attention bias in visual object navigation tasks and solves it using directed object attention (DOA) graph.

Recommended citation: Dang, Ronghao, et al. "Unbiased Directed Object Attention Graph for Object Navigation." Proceedings of the 30th ACM International Conference on Multimedia. 2022. http://academicpages.github.io/files/Unbias_directed_object_attention_graph_for_object_navigation.pdf

Bionic Body Wave Control for an Eel-Like Robot Based on Segmented Soft Actuator Array

Published in CCC (oral), 2021

This paper develops the entire eel-like fish with a fully soft flexible body, which is composed of four fiber-reinforced, bidirectionally bending, fluidic elastomer actuators (FEAs) as its tail.

Recommended citation: Dang, Ronghao, et al. "Bionic Body Wave Control for an Eel-Like Robot Based on Segmented Soft Actuator Array." 2021 40th Chinese Control Conference (CCC). IEEE, 2021. http://academicpages.github.io/files/2021-7-26-Bionic Body Wave Control for an Eel-Like Robot Based on Segmented Soft Actuator Array.pdf