activity
20172023
most citedA survey on trajectory clustering analysis

80 citations · 83 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV2023

Self-supervised Training Sample Difficulty Balancing for Local Descriptor Learning

Jiahan Zhang, Dayong Tian

In the case of an imbalance between positive and negative samples, hard negative mining strategies have been shown to help models learn more subtle differences between positive and…

cs.LG2023★ 1 cited

Interval Type-2 Fuzzy Neural Networks for Multi-Label Classification

Dayong Tian, Feifei Li, Yiwen Wei

Prediction of multi-dimensional labels plays an important role in machine learning problems. We found that the classical binary labels could not reflect the contents and their rela…

cs.CV2019

Global Hashing System for Fast Image Search

Dayong Tian, Dacheng Tao

Hashing methods have been widely investigated for fast approximate nearest neighbor searching in large data sets. Most existing methods use binary vectors in lower dimensional spac…

cs.CV2019

Coupled Learning for Facial Deblur

Dayong Tian, Dacheng Tao

Blur in facial images significantly impedes the efficiency of recognition approaches. However, most existing blind deconvolution methods cannot generate satisfactory results due to…

cs.IR2018

Learning Decorrelated Hashing Codes for Multimodal Retrieval

Dayong Tian

In social networks, heterogeneous multimedia data correlate to each other, such as videos and their corresponding tags in YouTube and image-text pairs in Facebook. Nearest neighbor…

cs.CV2018★ 80 cited

A survey on trajectory clustering analysis

Jiang Bian, Dayong Tian, Yuanyan Tang +1

This paper comprehensively surveys the development of trajectory clustering. Considering the critical role of trajectory data mining in modern intelligent systems for surveillance…

cs.IR2017★ 2 cited

Semi-supervised Multimodal Hashing

Dayong Tian, Maoguo Gong, Deyun Zhou +2

Retrieving nearest neighbors across correlated data in multiple modalities, such as image-text pairs on Facebook and video-tag pairs on YouTube, has become a challenging task due t…