With　the　advent　of　the　we-media　era,　live　video　is　being　sought　after　by　more　and　more　web　users.　How　to　effectively　identify　and　supervise　the　streamer　activities　in　the　live　video　is　of　great　significance　to　promote　the　high-quality　development　of　the　live　video　industry.　The　streamer　activity　can　be　characterized　by　the　temporal　composition　of　a　series　of　actions.　To　improve　the　accuracy　of　streamer　temporal　action　detection,　it　is　a　promising　path　to　utilize　the　temporal　action　location　and　co-attention　mechanism　to　overcome　the　problem　of　blurring　action　boundary.　Therefore,　a　streamer　temporal　action　detection　method　by　co-attention　boundary　matching　in　live　video　is　proposed.　(1)　The　global　spatiotemporal　features　and　action　template　features　of　live　video　are　extracted　by　using　two-stream　convolutional　network　and　action　spatiotemporal　attention　network　respectively.　(2)　The　probability　sequences　are　generated　from　the　global　spatiotemporal　features　through　temporal　action　evaluation,　and　the　boundary　matching　confidence　maps　are　produced　by　confidence　evaluation　of　global　spatiotemporal　features　and　action　template　features　under　the　co-attention　mechanism.　(3)　The　streamer　temporal　actions　are　detected　based　on　the　action　proposals　generated　by　probability　sequences　and　boundary　matching　maps.　We　establish　a　real-world　streamer　action　BJUT-SAD　dataset　and　conduct　extensive　experiments　to　verify　that　our　method　can　boost　the　accuracy　of　streamer　temporal　action　detection　in　live　video.　In　particular,　our　temporal　action　proposal　generation　and　streamer　action　detection　task　produce　competitive　results　to　prior　methods,　demonstrating　the　effectiveness　of　our　method.