• Home
  • Search
  • Transductive Learning With Prior Knowledge for Generalized Zero-Shot Action Recognition
  • Cite Icon32
  • https://doi.org/10.1109/tcsvt.2023.3284977Copy DOI Icon

Transductive Learning With Prior Knowledge for Generalized Zero-Shot Action Recognition

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

It is challenging to achieve generalized zero-shot action recognition. Different from the conventional zero-shot tasks which assume that the instances of the source classes are absent in the test set, the generalized zero-shot task studies the case that the test set contains both the source and the target classes. Due to the gap between visual feature and semantic embedding as well as the inherent bias of the learned classifier towards the source classes, the existing generalized zero-shot action recognition approaches are still far less effective than traditional zero-shot action recognition approaches. Facing these challenges, a novel transductive learning with prior knowledge (TLPK) model is proposed for generalized zero-shot action recognition. First, TLPK learns the prior knowledge which assists in bridging the gap between visual features and semantic embeddings, and preliminarily reduces the bias caused by the visual-semantic gap. Then, a transductive learning method that employs unlabeled target data is designed to overcome the bias problem in an effective manner. To achieve this, a target semantic-available approach and a target semantic-free approach are devised to utilize the target semantics in two different ways, where the target semantic-free approach exploits prior knowledge to produce well-performed semantic embeddings. By exploring the usage of the aforementioned prior-knowledge learning and transductive learning strategies, TLPK significantly bridges the visual-semantic gap and alleviates the bias between the source and the target classes. The experiments on the benchmark datasets of HMDB51 and UCF101 demonstrate the effectiveness of the proposed model compared to the state-of-the-art methods. The source code of this work can be found in <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://mic.tongji.edu.cn</uri>

Similar Papers
  • Research Article
  • Citations115

Inductive Multi-Hypergraph Learning and Its Application on View-Based 3D Object Classification.

  • Aug 02, 2018
  • IEEE Transactions on Image Processing
  • Zizhao Zhang +4
  • Research Article
  • Citations1

Transductive polyhedral conic classifiers for machine learning applications

  • Sep 01, 2022
  • Pattern Recognition Letters
  • Hakan Cevikalp +1
  • Conference Article

An Improved Progressive Transductive Algorithm Based on One Class SVM

  • Oct 01, 2011
  • Shuxiong Qiu +4
  • Research Article
  • Citations2

Transductive zero-shot learning via knowledge graph and graph convolutional networks.

  • Aug 06, 2025
  • Scientific reports
  • Qiong Li +2
  • Research Article
  • Citations17

A new transductive learning method with universum data

  • Jan 10, 2021
  • Applied Intelligence
  • Yanshan Xiao +2
  • Research Article
  • Citations28

Ventral & Dorsal Stream Theory based Zero-Shot Action Recognition

  • Mar 28, 2021
  • Pattern Recognition
  • Meng Xing +4
  • Research Article

Two-way Markov random walk transductive learning algorithm

  • Mar 01, 2014
  • Journal of Central South University
  • Hong Li +3
  • Conference Article
  • Citations1

A Transductive Transfer Learning Method for Ship Target Recognition

  • Jul 01, 2013
  • Zhiping Dan +4
  • Research Article
  • Citations19

A relational approach to probabilistic classification in a transductive setting

  • Jun 24, 2008
  • Engineering Applications of Artificial Intelligence
  • Donato Malerba +2
  • Dissertation

Discovering visual patterns for image data analysis

  • Jan 01, 2015
  • Hongxing Wang
  • Research Article
  • Citations28

Emotion recognition in the wild via sparse transductive transfer linear discriminant analysis

  • Jan 05, 2016
  • Journal on Multimodal User Interfaces
  • Yuan Zong +5
  • Book Chapter
  • Citations26

Towards a Fair Evaluation of Zero-Shot Action Recognition Using External Data

  • Jan 01, 2019
  • Alina Roitberg +3
  • Research Article
  • Citations20

A transductive transfer learning approach for image classification

  • Sep 20, 2020
  • International Journal of Machine Learning and Cybernetics
  • Samaneh Rezaei +2
  • Research Article
  • Citations14

Modality independent adversarial network for generalized zero shot image classification

  • Nov 21, 2020
  • Neural Networks
  • Haofeng Zhang +4
  • PDF
  • Research Article
  • Citations5

Transductive learning as an alternative to translation initiation site identification

  • Feb 02, 2017
  • BMC Bioinformatics
  • Cristiano Lacerda Nunes Pinto +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.