Y
Yuexian Zou
Researcher at Peking University
Publications - 44
Citations - 663
Yuexian Zou is an academic researcher from Peking University. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 7, co-authored 44 publications receiving 182 citations.
Papers
More filters
Proceedings ArticleDOI
Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation
TL;DR: Wang et al. as mentioned in this paper proposed a posterior-and-priori knowledge exploration and distillation approach (PPKED) to automatically generate radiology reports, which is able to outperform previous state-of-the-art models on these two datasets.
Proceedings ArticleDOI
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
TL;DR: Wang et al. as mentioned in this paper proposed to refine the hard snippet representation in feature space, which guides the network to perceive precise temporal boundaries and avoid the temporal interval interruption, and they introduced a Hard Snippet Mining algorithm to locate the potential hard snippets.
Journal ArticleDOI
Federated Learning for Vision-and-Language Grounding Problems
TL;DR: This work proposes a federated learning framework to obtain various types of image representations from different tasks, which are then fused together to form fine-grained image representations that are much more powerful than the original representations alone in individual tasks.
Proceedings ArticleDOI
Enhancing End-to-End Multi-Channel Speech Separation Via Spatial Feature Learning
TL;DR: This work proposes an integrated architecture for learning spatial features directly from the multi-channel speech waveforms within an end-to-end speech separation framework using a 2d convolution layer and designs a conv2d kernel to compute the inter-channel convolution differences (ICDs), which are expected to provide the spatial cues that help to distinguish the directional sources.
Journal Article
Towards Data Distillation for End-to-end Spoken Conversational Question Answering
TL;DR: A new Spoken Conversational Question Answering task (SCQA), aiming at enabling QA systems to model complex dialogues flow given the speech utterances and text corpora and to explore the plausibility of providing more cues in spoken documents with systems in information gathering.