MGMingqi Gao

Mingqi Gao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mingqi Gao has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes

    by Yixuan Yang, Luyang Xie, Zhen Luo, Zixiang Zhao, Tongsheng Ding, Xudong Xu, Mingqi Gao, Feng Zheng


  • Weakly-Supervised RGBD Video Object Segmentation

    by Jinyu Yang, Mingqi Gao, Feng Zheng, Xiantong Zhen, Rongrong Ji, Ling Shao, Aleš Leonardis

    Depth information opens up opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, RGBD VOS is still unexplored due to the high-cost collection and time-consuming annotation of RGBD segmentation data. In this work, we first introduce a new benchmark for RGBD VOS, named DepthVOS, which contains 350 videos (over 55k frames) and is annotated with masks and bounding boxes. Then, we propose a novel and strong baseline model - Fused Color-Depth Network (FusedCDNet) which can be learned merely under bounding box supervision and then be used to generate masks with a bounding box guideline only in the first frame. In summary, our model includes three major advantages: a weakly-supervised training strategy to overcome the high-cost labeling, a cross-modal fusion module to handle complex scenes, and weakly-supervised prediction to promote ease of use. Extensive experiments demonstrate that our proposed method performs on par with top fully-supervised algorithms. We will open-source our project http://github.com/yjybuaa/depthvos/, which will facilitate the development of RGBD VOS.


  • Unveiling the Power of Visible-Thermal Video Object Segmentation

    by Jinyu Yang, Mingqi Gao, Runmin Cong, Chengjie Wang, Feng Zheng, Aleš Leonardis

    Despite recent progress, Video Object Segmentation (VOS) remains challenging in complex situations such as low light and dark scenes. In this paper, we tackle the visibility limitations by introducing thermal information as auxillary for VOS. Specifically, we generate a hybrid benchmark dataset for Visible-Thermal VOS, named VisT300, which contains 300 challenging videos with visible light and thermal frames and corresponding object mask annotations. Besides, a Visible-Thermal integration Network, named as VTiNet, is proposed to use both cross-modal and cross-frame propagation for accurate video object segmentation. It is advantageous in two aspects: 1) effective cross-modal feature fusion and propagation for strong expressions on visible, thermal, and fused modalities; 2) effective modality-sensitive memory bank enables preserving the most valuable historical contexts in each modality. Extensive experiments demonstrate our VTiNet outperforms the state-of-the-art VOS works by a large margin (over 5% than RGB SotAs in Mean J&F). Our preliminary research clearly recovers that importing complementary modalities can effectively increase the strength of models to achieve robust segmentation in challenging scenarios. Data and code are released at https://github.com/yjybuaa/vtinet, and we hope this work will promote the progress of visible-thermal VOS.


  • Decoupling Multimodal Transformers for Referring Video Object Segmentation

    by Mingqi Gao, Jinyu Yang, Jungong Han, Ke Lu, Feng Zheng, Giovanni Montana

    Referring Video Object Segmentation (RVOS) aims to segment the text-depicted object from video sequences. With excellent capabilities in long-range modelling and information interaction, transformers have been increasingly applied in existing RVOS architectures. To better leverage multimodal data, most efforts focus on the interaction between visual and textual features. However, they ignore the syntactic structures of the text during the interaction, where all textual components are intertwined, resulting in ambiguous vision-language alignment. In this paper, we improve the multimodal interaction by DECOUPLING the interweave. Specifically, we train a lightweight subject perceptron, which extracts the subject part from the input text. Then, the subject and text features are fed into two parallel branches to interact with visual features. This enables us to perform subject-aware and context-aware interactions, respectively, thus encouraging more explicit and discriminative feature embedding and alignment. Moreover, we find the decoupled architecture also facilitates incorporating the vision-language pre-trained alignment into RVOS, further improving the segmentation performance. Experimental results on all RVOS benchmark datasets demonstrate the superiority of our proposed method over the state-of-the-arts. The code of our method is available at: https://github.com/gaomingqi/dmformer.