{"671352":{"#nid":"671352","#data":{"uid":"36172","author":"dwatson71","created_gmt":"2023-08-09 14:40:31","changed_gmt":"2023-08-09 14:40:31","title":"ConvNets Framwork.jpg","body":[{"value":"\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EOverview of the proposed framework. Spatial and temporal features were extracted from a two-stream ConvNet using ResNet-101 pre-trained on ImageNet, and fine-tuned for single-frame activity prediction. Spatial and temporal features are concatenated and temporally-constructed into feature matrices. The constructed feature matrices are then used as input to both of our proposed methods: Temporal Segment LSTM (TS-LSTM) and Temporal-Inception. \u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"image":{"alt":"A graphic of the proposed framework with Temporal Segment LSTM (TS-LSTM) and Temporal-Inception.","view":{"#theme":"field","#title":"Image","#label_display":"hidden","#view_mode":"image_740","#language":"en","#field_name":"field_image","#field_type":"image","#field_translatable":false,"#entity_type":"media","#bundle":"image","#object":{},"#items":{},"#formatter":"image","#is_multiple":false,"#third_party_settings":[],"0":{"#theme":"image_formatter","#item":{},"#item_attributes":[],"#image_style":"large","#url":null,"#cache":{"tags":["config:image.style.large","file:254385"],"contexts":[],"max-age":-1}},"#cache":{"contexts":[],"tags":[],"max-age":-1},"#weight":0},"file":{"fid":"254385","name":"ConvNets Framwork.jpg","path":"\/sites\/default\/files\/2023\/08\/09\/ConvNets%20Framwork.jpg","fullpath":"\/var\/www\/html\/files\/public\/2023\/08\/09\/ConvNets Framwork.jpg","mime":"image\/jpeg","size":422146}},"groups":[{"id":"1255","name":"School of Electrical and Computer Engineering"}],"keywords":[]}}}