With　the　fast　development　of　information　and　communication　technologies,　video　streaming　services　and　applications　are　increasing　rapidly.　However,　the　network　condition　is　volatile.　In　order　to　provide　users　with　better　quality　of　service,　it　is　necessary　to　develop　an　accurate　and　low-complexity　model　for　Quality　of　Experience　(QoE)　prediction　of　time-varying　video.　Memory　effects　refer　to　the　psychological　influence　factor　of　historical　experience,　which　can　be　taken　into　account　to　improve　the　accuracy　of　QoE　evaluation.　In　this　paper,　we　design　subjective　experiments　to　explore　the　impact　of　Short-Term　Memory　(STM)　on　QoE.　The　experimental　results　show　that　the　user＇s　real-time　QoE　is　influenced　by　the　duration　of　previous　viewing　experience　and　the　expectations　generated　by　STM.　Furthermore,　we　propose　analytical　models　to　determine　the　relationship　between　intrinsic　video　quality,　expectation　and　real-time　QoE.　The　proposed　models　have　better　performance　for　real-time　QoE　prediction　when　the　video　is　transmitted　in　a　fluctuate　network.　The　models　are　capable　of　providing　more　accurate　guidance　for　improving　the　quality　of　video　streaming　services.