activity
20182021
most citedFeature Re-Learning with Data Augmentation for Video Relevance Prediction

17 citations · 28 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV20211 cited

Unsupervised Domain Expansion for Visual Categorization

Jie Wang, Kaibin Tian, Dayong Ding +2

Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has b…

cs.CV2020

SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries

Xirong Li, Fangming Zhou, Chaoxi Xu +2

Retrieving unlabeled videos by textual queries, known as Ad-hoc Video Search (AVS), is a core theme in multimedia data management and retrieval. The success of AVS counts on cross-…

cs.CV2020

Dual Encoding for Video Retrieval by Text

Jianfeng Dong, Xirong Li, Chaoxi Xu +4

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusive…

cs.CV202017 cited

Feature Re-Learning with Data Augmentation for Video Relevance Prediction

Jianfeng Dong, Xun Wang, Leimin Zhang +3

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. Thanks to the increa…

cs.CV201910 cited

Hierarchical Attention Networks for Medical Image Segmentation

Fei Ding, Gang Yang, Jinlu Liu +5

The medical image is characterized by the inter-class indistinction, high variability, and noise, where the recognition of pixels is challenging. Unlike previous self-attention bas…

cs.CV2018

Imagination Based Sample Construction for Zero-Shot Learning

Gang Yang, Jinlu Liu, Xirong Li

Zero-shot learning (ZSL) which aims to recognize unseen classes with no labeled training sample, efficiently tackles the problem of missing labeled data in image retrieval. Nowaday…