Curriculum multi-negative augmentation for debiased video grounding

X Lan, Y Yuan, H Chen, X Wang, Z Jie, L Ma… - Proceedings of the …, 2023 - ojs.aaai.org
Video Grounding (VG) aims to locate the desired segment from a video given a sentence
query. Recent studies have found that current VG models are prone to over-rely the …

Curriculum graph machine learning: A survey

H Li, X Wang, W Zhu - arxiv preprint arxiv:2302.02926, 2023 - arxiv.org
Graph machine learning has been extensively studied in both academia and industry.
However, in the literature, most existing graph machine learning models are designed to …

Data-augmented curriculum graph neural architecture search under distribution shifts

Y Yao, X Wang, Y Qin, Z Zhang, W Zhu… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Graph neural architecture search (NAS) has achieved great success in designing
architectures for graph data processing. However, distribution shifts pose great challenges …

Large Language Model with Curriculum Reasoning for Visual Concept Recognition

Y Zhang, X Wang, H Chen, J Fan, W Wen… - Proceedings of the 30th …, 2024 - dl.acm.org
Visual concept recognition aims to capture the basic attributes of an image and reason
about the relationships among them to determine whether the image satisfies a certain …

Curriculum Learning for Multimedia in the Era of Large Language Models

X Wang, Y Zhou, H Chen, W Zhu - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
This tutorial focuses on curriculum learning (CL), an important topic in machine learning,
which gains an increasing amount of attention in the research community. CL is a learning …

Neighbor Does Matter: Curriculum Global Positive-Negative Sampling for Vision-Language Pre-training

B Huang, F He, Q Wang, H Chen, G Li, Z Feng… - Proceedings of the …, 2024 - dl.acm.org
Sampling strategies have been widely adopted in Vision-Language Pre-training (VLP) and
have achieved great success recently. However, the sampling strategies adopted by current …

Curriculum Learning: Theories, Approaches, Applications, Tools, and Future Directions in the Era of Large Language Models

X Wang, Y Zhou, H Chen, W Zhu - … Proceedings of the ACM on Web …, 2024 - dl.acm.org
This tutorial focuses on curriculum learning (CL), an important topic in machine learning,
which gains an increasing amount of attention in the research community. CL is a learning …

CurBench: Curriculum Learning Benchmark

Y Zhou, Z Pan, X Wang, H Chen, H Li, Y Huang… - Forty-first International … - openreview.net
Curriculum learning is a training paradigm where machine learning models are trained in a
meaningful order, inspired by the way humans learn curricula. Due to its capability to …

[PDF][PDF] Application of Self-Paced learning for noisy meta-learning

A Aszalós - 2024 - repository.tudelft.nl
Meta-learning is an important emerging paradigm in machine learning, aimed at improving
dataefficiency and generalization performance across learning tasks. Challenges caused by …

[PDF][PDF] DATA-EFFICIENT LOW-COMPLEXITY ACOUSTIC SCENE CLASSIFICATION WITH CURRICULUM LEARNING AND SE-LAYER

X Chen, W **e - dcase.community
This technical report presents a data-efficient and low-complexity acoustic scene
classification (ASC) system developed for Task 1 of the DCASE2024 Challenge. The …