Fix missing video inputs for PerceptionLM. (#39971)
* Fix missing video inputs for PerceptionLM.
* Minor fix for vanilla input image (only C,H,W, no tiles dim).
* Revert "Minor fix for vanilla input image (only C,H,W, no tiles dim)."
This reverts commit 181d87b964e59c4118035a9fd4f530c6e551ba9f.