UniMod1K: Towards a More Universal Large-Scale Dataset and Benchmark for Multi-modal Learning
- 22 February 2024
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (8) , 2845-2860
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62020106012; 62106089; 62332008; 62336004; U1836218)
- 111 Project of Ministry of Education of China (B12018)
- Engineering and Physical Sciences Research Council (EP/V002856/1; EP/T022205/1)
This publication has 62 references indexed in Scilit:
- Deeper Depth Prediction with Fully Convolutional Residual Networks2016
- An occlusion-aware particle filter tracker to handle complex and persistent occlusionsComputer Vision and Image Understanding, 2016
- Deep Residual Learning for Image Recognition2016
- Multi-modal RGB–Depth–Thermal Human Body SegmentationInternational Journal of Computer Vision, 2016
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Robust object tracking using color and depth images with a depth based occlusion handling and recovery2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines2013
- Make3D: Learning 3D Scene Structure from a Single Still ImageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008