Yan Wang

Yan Wang, Xin Luo, Zhen-Duo Chen et al.

Despite the great success achieved, existing video moment retrieval (VMR) methods are developed under the assumption that data are centralizedly stored. However, in real-world applications, due to the inherent nature of data generation and privacy concerns, data are often distributed on different silos, bringing huge challenges to effective large-scale training. In this work, we try to overcome above limitation by leveraging the recent success of federated learning. As the first that is explored in VMR field, the new task is defined as video moment retrieval with distributed data. Then, a novel federated learning method named FedVMR is proposed to facilitate large-scale and secure training of VMR models in decentralized environment. Experiments on benchmark datasets demonstrate its effectiveness. This work is the very first attempt to enable safe and efficient VMR training in decentralized scene, which is hoped to pave the way for further study in the related research field.

Kyle Xiao, Houdong Hu, Yan Wang

Query reformulation is the process by which a input search query is refined by the user to match documents outside the original top-n results. On average, roughly 50% of text search queries involve some form of reformulation, and term suggestion tools are used 35% of the time when offered to users. As prevalent as text search queries are, however, such a feature has yet to be explored at scale for visual search. This is because reformulation for images presents a novel challenge to seamlessly transform visual features to match user intent within the context of a typical user session. In this paper, we present methods of semantically transforming visual queries, such as utilizing operations in the latent space of a generative adversarial model for the scenarios of fashion and product search.

Houdong Hu, Yan Wang, Linjun Yang et al.

In this paper, we introduce a web-scale general visual search system deployed in Microsoft Bing. The system accommodates tens of billions of images in the index, with thousands of features for each image, and can respond in less than 200 ms. In order to overcome the challenges in relevance, latency, and scalability in such large scale of data, we employ a cascaded learning-to-rank framework based on various latest deep learning visual features, and deploy in a distributed heterogeneous computing platform. Quantitative and qualitative experiments show that our system is able to support various applications on Bing website and apps.