Multi-granularity Dynamic Conditional Transformer for Vision-Language Tracking
Open Access
- 26 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 13-21
Abstract
No abstract availableFunding Information
- The National Natural Science Foundation of China (U22B2054,62076192,62276199,62431020,62276201)
- the 111 Project, the Program for Cheung Kong Scholars and Innovative Research Team in University (IRT 15R53)
- the Science and Technology Innovation Project from the Chinese Ministry of Education. the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi'an Jiaotong University (HMHAI-202404,HMHAI-202405)
This publication has 22 references indexed in Scilit:
- Multi-modal visual tracking: Review and experimental comparisonComputational Visual Media, 2024
- Transformer vision-language tracking via proxy token guided cross-modal fusionPattern Recognition Letters, 2023
- LaSOT: A High-quality Large-scale Single Object Tracking BenchmarkInternational Journal of Computer Vision, 2020
- Siam R-CNN: Visual Tracking by Re-Detection2020
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild2018
- Squeeze-and-Excitation Networks2018
- ECO: Efficient Convolution Operators for Tracking2017
- Fully-Convolutional Siamese Networks for Object Tracking2016
- Learning Multi-domain Convolutional Neural Networks for Visual Tracking2016
- Microsoft COCO: Common Objects in Context2014