Multimodal learning with transformers: A survey
Transformer is a promising neural network learner, and has achieved great success in
various machine learning tasks. Thanks to the recent prevalence of multimodal applications …
various machine learning tasks. Thanks to the recent prevalence of multimodal applications …
Learning multiple adverse weather removal via two-stage knowledge learning and multi-contrastive regularization: Toward a unified model
In this paper, an ill-posed problem of multiple adverse weather removal is investigated. Our
goal is to train a model with a'unified'architecture and only one set of pretrained weights that …
goal is to train a model with a'unified'architecture and only one set of pretrained weights that …
A survey on semi-, self-and unsupervised learning for image classification
While deep learning strategies achieve outstanding results in computer vision tasks, one
issue remains: The current strategies rely heavily on a huge amount of labeled data. In many …
issue remains: The current strategies rely heavily on a huge amount of labeled data. In many …
Deep learning for free-hand sketch: A survey
Free-hand sketches are highly illustrative, and have been widely used by humans to depict
objects or stories from ancient times to the present. The recent prevalence of touchscreen …
objects or stories from ancient times to the present. The recent prevalence of touchscreen …
Multigraph transformer for free-hand sketch recognition
Learning meaningful representations of free-hand sketches remains a challenging task
given the signal sparsity and the high-level abstraction of sketches. Existing techniques …
given the signal sparsity and the high-level abstraction of sketches. Existing techniques …
An improved inter-intra contrastive learning framework on self-supervised video representation
In this paper, we propose a self-supervised contrastive learning method to learn video
feature representations. In traditional self-supervised contrastive learning methods …
feature representations. In traditional self-supervised contrastive learning methods …
Embedding global contrastive and local location in self-supervised learning
Self-supervised representation learning (SSL) typically suffers from inadequate data
utilization and feature-specificity due to the suboptimal sampling strategy and the …
utilization and feature-specificity due to the suboptimal sampling strategy and the …
Multistage spatio-temporal networks for robust sketch recognition
Sketch recognition relies on two types of information, namely, spatial contexts like the local
structures in images and temporal contexts like the orders of strokes. Existing methods …
structures in images and temporal contexts like the orders of strokes. Existing methods …
Self-supervised representation learning for videos by segmenting via sampling rate order prediction
J Huang, Y Huang, Q Wang, W Yang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Self-supervised representation learning for videos has been very attractive recently because
these methods exploit the information inherently obtained from the video itself instead of …
these methods exploit the information inherently obtained from the video itself instead of …
Fine-grained instance-level sketch-based video retrieval
Existing sketch-analysis work studies sketches depicting static objects or scenes. In this
work, we propose a novel cross-modal retrieval problem of fine-grained instance-level …
work, we propose a novel cross-modal retrieval problem of fine-grained instance-level …