Zeng Shuang

Results 33 issues of Zeng Shuang

Hello, I'd like to recommend a VLN paper: **JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation**. Previous methods' explicit semantic memory (such as constructing text cognitive...

Can the output get the real 3D size of the object?

Everything works fine when I run the R2R configuration. But the following error occurs when running the RxR configuration, and the data is in the correct location: Traceback (most recent...