HashingforContentIdentification:From SynchronizationtoRetrieval

In the past few years, nearest neighbour search methods based on hashing have gained considerable attention for effective and efficient large-scale similarity search, facilitating a variety of applications. In this talk, we will elaborate several recent works, ranging from audio hashing for multi-screen synchronization, robust iterative quantization for image search, balanced hashing for video search to MFbased deep cross-modal hashing for large-scale data retrieval. The intention is to showcase the differences of carrying out research activities in industry and academia.