no code implementations • 5 May 2024 • Mengxian Hu, Minghao Zhu, Xun Zhou, Qingqing Yan, Shu Li, Chengju Liu, Qijun Chen
Motion diffusion models have recently proven successful for text-driven human motion generation.
1 code implementation • 16 Apr 2024 • Liuyi Wang, Zongtao He, Ronghao Dang, Mengjiao Shen, Chengju Liu, Qijun Chen
In the pursuit of robust and generalizable environment perception and language understanding, the ubiquitous challenge of dataset bias continues to plague vision-and-language navigation (VLN) agents, hindering their performance in unseen environments.
no code implementations • 6 Mar 2024 • Liuyi Wang, Zongtao He, Ronghao Dang, Huiyi Chen, Chengju Liu, Qijun Chen
Vision-and-Language Navigation (VLN) has gained significant research interest in recent years due to its potential applications in real-world scenarios.
no code implementations • 24 Feb 2024 • Xiao Lin, Minghao Zhu, Ronghao Dang, Guangliang Zhou, Shaolong Shu, Feng Lin, Chengju Liu, Qijun Chen
Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities.
no code implementations • 25 Oct 2023 • Xiao Lin, Deming Wang, Guangliang Zhou, Chengju Liu, Qijun Chen
To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information.
1 code implementation • 8 Oct 2023 • Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, Yibing Song
In order to encompass common detection expressions, we involve emerging vision-language model (VLM) and large language model (LLM) to generate instructions guided by text prompts and object bbxs, as the generalizations of foundation models are effective to produce human-like expressions (e. g., describing object property, category, and relationship).
1 code implementation • 1 Sep 2023 • Minghao Zhu, Xiao Lin, Ronghao Dang, Chengju Liu, Qijun Chen
As the most essential property in a video, motion information is critical to a robust and generalized video representation.
no code implementations • 19 May 2023 • Liuyi Wang, Chengju Liu, Zongtao He, Shu Li, Qingqing Yan, Huiyi Chen, Qijun Chen
The experimental results demonstrate that PASTS outperforms all existing speaker models and successfully improves the performance of previous VLN models, achieving state-of-the-art performance on the standard Room-to-Room (R2R) dataset.
1 code implementation • 5 May 2023 • Liuyi Wang, Zongtao He, Jiagui Tang, Ronghao Dang, Naijia Wang, Chengju Liu, Qijun Chen
Vision-and-Language Navigation (VLN) is a realistic but challenging task that requires an agent to locate the target region using verbal and visual cues.
1 code implementation • 2 Mar 2023 • Zongtao He, Liuyi Wang, Shu Li, Qingqing Yan, Chengju Liu, Qijun Chen
For a better performance in continuous VLN, we design a multi-level instruction understanding procedure and propose a novel model, Multi-Level Attention Network (MLANet).
no code implementations • 3 Feb 2023 • Ronghao Dang, Lu Chen, Liuyi Wang, Zongtao He, Chengju Liu, Qijun Chen
We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together.
no code implementations • ICCV 2023 • Ronghao Dang, Liuyi Wang, Zongtao He, Shuai Su, Chengju Liu, Qijun Chen
After seeing the target, we remember the target location and navigate to.
no code implementations • 9 Apr 2022 • Ronghao Dang, Zhuofan Shi, Liuyi Wang, Zongtao He, Chengju Liu, Qijun Chen
Thus, in this paper, we propose a directed object attention (DOA) graph to guide the agent in explicitly learning the attention relationships between objects, thereby reducing the object attention bias.
no code implementations • 26 Feb 2020 • Sukai Wang, Yuxiang Sun, Chengju Liu, Ming Liu
Recent machine learning-based multi-object tracking (MOT) frameworks are becoming popular for 3-D point clouds.
no code implementations • 4 Aug 2019 • Xiaochuan Yin, Chengju Liu
In contrast to the previous methods, our proposed method calculates the camera motion with a direct method rather than regressing the ego-motion from the pose network.
1 code implementation • 17 Sep 2018 • Peng Yun, Lei Tai, Yu-An Wang, Chengju Liu, Ming Liu
Inspired by the recent use of focal loss in image-based object detection, we extend this hard-mining improvement of binary cross entropy to point-cloud-based object detection and conduct experiments to show its performance based on two different 3D detectors: 3D-FCN and VoxelNet.