klauscc

VindLU. Python

TALLFormer. Python

lipnet-replication. A replication of Google DeepMind's paper:LipNet: End-to-End Sentence-level Lipreading

jpeg_toolbox_python. extract the dct coefficient of jpeg images. Provide c and python interface.

DAM. Official code for DAM: Dynamic Adapter Merging for Continual Video QA Learning

digitalImageForensics. 图像篡改检测

visual-speaker-authentication. Visual speaker authentication with random prompt texts by a Multi-task CNN Framework

airnet. airtnet source code

str-model-analysis. Scene Text Recognition: A model Analysis

video-cover-picker. pick the most appropriate frame in the video as the cover

spring-learn. Java

kyee-common-framework. this framework, whose purpose is to simplify configurations, was developed when I was an intern in kyee

webcamera-stream-demo. stream webcamera to browser using websocket

variational-transformer. variational transformer