Epileptic　seizure　detection　has　gained　increasing　attention　in　clinical　therapy.　Scalp　electroencephalogram　(EEG)　analysis　is　a　common　way　to　capture　brain　abnormality　for　seizure　onset　detection.　This　paper　presents　a　novel　context-learning　based　approach　using　multi-feature　fusion　to　compensate　for　incomplete　description　of　single　feature　in　epileptic　EEG　signals.　First,　EEG　scalogram　sequence　is　generated　using　wavelet　transform　to　represent　the　time-frequency　information.　Second,　three　sets　of　EEG　context　features　are　unsupervisedly　learned　in　parallel　by　using　global　principal　component　analysis　(GPCA),　stacked　denoising　autoencoders　(SDAEs)　and　EEG　embeddings,　respectively.　Finally,　the　multi-features　are　concatenated　into　a　fixed-length　feature　vector　for　seizure　classification.　The　experimental　results　conducted　on　two　real　EEG　datasets　demonstrate　that　the　proposed　cross-patient　learning　model　is　able　to　extract　meaningful　context　features　from　different　perspectives,　and　hence　can　detect　the　onset　of　epileptic　seizure　effectively.