Mouse Motion Behavior Recognition Based on DeepLabCut and Convolutional Long Short-Term Memory Network

“MouseBehaviourDataset” contains a 7 frame length and 1 frame interval mouse behaviour-recognition dataset. "MouseKeypointDataset " contains the mouse keypoint detection dataset. "BehaviourWeights" contain the weights of behavior recognition algorithms LSTM, BI-LSTM, ConvLSTM and 3DCNN. "KeypointWeights" contain the weights of keypoint detection algorithms CPM, Hourglass, DeepLabCut and imporved DeepLabCut. “Results” is the result of relevant experiments.

小鼠行为识别数据集（MouseBehaviourDataset）为包含7帧长度、1帧间隔的小鼠行为识别数据集。小鼠关键点检测数据集（MouseKeypointDataset）包含小鼠关键点检测数据集。行为识别算法权重集（BehaviourWeights）包含行为识别算法长短期记忆网络（LSTM）、双向长短期记忆网络（BI-LSTM）、卷积长短期记忆网络（ConvLSTM）以及三维卷积神经网络（3DCNN）的模型权重。关键点检测算法权重集（KeypointWeights）包含关键点检测算法卷积姿态机（CPM）、沙漏网络（Hourglass）、DeepLabCut以及改进版DeepLabCut的模型权重。实验结果集（Results）收录了相关实验的最终结果。