Share This Author
Overcoming Language Priors in VQA via Decomposed Linguistic Representations
A novel method of language attention-based VQA that learns decomposed linguistic representations of questions and utilizes the representations to infer answers for overcoming language priors is presented.
Visual-Semantic Graph Matching for Visual Grounding
- Chenchen Jing, Yuwei Wu, Mingtao Pei, Yao Hu, Yunde Jia, Qi Wu
- Computer ScienceACM Multimedia
- 12 October 2020
This paper forms visual grounding as a graph matching problem to find node correspondences between a visual scene graph and a language scene graph, and learns unified contextual node representations of the two graphs by using a cross-modal graph convolutional network to reduce their discrepancy.
Analysis of Pathogenicity and Virulence Factors of Ageratum leaf curl Sichuan virus
Ageratum leaf curl Sichuan virus (ALCScV) is a novel monopartite begomovirus, which was identified from Ageratum conyzoides plants in Sichuan Province, China. In this study, we showed that ALCScV can…
Deep CNN based binary hash video representations for face retrieval
Heterogeneous Hashing Network for Face Retrieval Across Image and Video Domains
- Chenchen Jing, Zhen Dong, Mingtao Pei, Yunde Jia
- Computer ScienceIEEE Transactions on Multimedia
- 1 March 2019
A heterogeneous hashing network to generate effective and compact hash representations of both face images and face videos for face retrieval across image and video domains is presented.
Overexpression of the glucosyltransferase gene BoaUGT74B1 enhances the accumulation of indole glucosinolates in Chinese kale
Unsupervised deep quantization for object instance search
Fusing Appearance Features and Correlation Features for Face Video Retrieval
This paper fuse appearance features and correlation features to exploit rich information of face videos for face video retrieval via a deep convolutional neural network, and integrates feature extractions, feature fusion, and hash learning into a unified optimization framework to guarantee optimal Compatibility.
Maintaining Reasoning Consistency in Compositional Visual Question Answering
This paper presents a dialog-like reasoning method for maintaining reasoning consistency in answering a compositional question and its sub-questions like a dialog task, and uses a consistency constraint to penalize inconsistent answer predictions.
Learning the Dynamics of Visual Relational Reasoning via Reinforced Path Routing
A reinforced path routing method that represents an input image via a structured visual graph and introduces a reinforcement learning based model to explore paths (sequences of nodes) over the graph based on an input sentence to infer reasoning results.