RGB-D semantic segmentation has made notable progress by fusing RGB and Depth, yet mainstream models still learn features almost exclusively from pixel-level supervision, lacking direct high-level semantic constraints. This raises a central question-can external knowledge such as language priors inject stronger semanti...
Zi-Chuan Wei, Yin-Long Liu, Yan Xia et al.· 0 citations
Visual Question Answering (VQA) in embodied settings draws on computer vision, natural language processing, and robotics. Unlike traditional VQA, Embodied Question Answering (EQA) may require an agent to acquire and retain evidence from a 3D environment before answering a natural language query. This semi-systematic su...
A novel transformation strategy that exploits geometric relations derived from the gravity prior is proposed that achieves stronger performance compared to existing state-of-the-art (SOTA) approaches and is integrated into ORB-SLAM2.
Hu Cao, Qian-Yi Yang, Xin-Yi Li et al.· IEEE Transactions on Image P...· 0 citations
A structured scoping review of reinforcement learning for generative robot policies and a bounded state-based locomotion reproduction is presented and a full-chain backpropagation adaptation exhibited clear seed-dependent variation.
Shihan Sun, Yinlong Liu· Robotics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
