17 citations · 42 across the 13 of their papers we have counts for
13 papers
Self-supervised learning of audio representations using angular contrastive loss
Shanshan Wang, Soumya Tripathy, Annamaria Mesaros
In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this…
Self-supervised Graph Learning for Long-tailed Cognitive Diagnosis
Shanshan Wang, Zhen Zeng, Xun Yang +1
Cognitive diagnosis is a fundamental yet critical research task in the field of intelligent education, which aims to discover the proficiency level of different students on specifi…
Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding
Shanshan Wang, Zhumin Chen, Zhaochun Ren +3
Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, m…
BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective
Shanshan Wang, Lei Zhang, Pichao Wang
Triplet loss, one of the deep metric learning (DML) methods, is to learn the embeddings where examples from the same class are closer than examples from different classes. Motivate…
Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair
Shanshan Wang, Gaurav Naithani, Archontis Politis +1
Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper…
Audio-visual scene classification: analysis of DCASE 2021 Challenge submissions
Shanshan Wang, Toni Heittola, Annamaria Mesaros +1
This paper presents the details of the Audio-Visual Scene Classification task in the DCASE 2021 Challenge (Task 1 Subtask B). The task is concerned with classification using audio…
A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysis
Shanshan Wang, Annamaria Mesaros, Toni Heittola +1
This paper introduces a curated dataset of urban scenes for audio-visual scene analysis which consists of carefully selected and recorded material. The data was recorded in multipl…
Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision
Hoel Kervadec, Jose Dolz, Shanshan Wang +2
We propose a novel weakly supervised learning segmentation based on several global constraints derived from box annotations. Particularly, we leverage a classical tightness prior t…
Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation
Lei Zhang, Shanshan Wang, Guang-Bin Huang +3
In many practical transfer learning scenarios, the feature distribution is different across the source and target domains (i.e. non-i.i.d.). Maximum mean discrepancy (MMD), as a do…
Low-Latency Deep Clustering For Speech Separation
Shanshan Wang, Gaurav Naithani, Tuomas Virtanen
This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of long-…
Fine-grained visual recognition with salient feature detection
Hui Feng, Shanshan Wang, Shuzhi Sam Ge
Computer vision based fine-grained recognition has received great attention in recent years. Existing works focus on discriminative part localization and feature learning. In this…
Adversarial Transfer Learning for Cross-domain Visual Recognition
Shanshan Wang, Lei Zhang, JingRu Fu
In many practical visual recognition scenarios, feature distribution in the source domain is generally different from that of the target domain, which results in the emergence of g…
Cross Domain Adaptation by Learning Partially Shared Classifiers and Weighting Source Data Points in the Shared Subspaces
Hongqi Wang, Anfeng Xu, Shanshan Wang +1
Transfer learning is a problem defined over two domains. These two domains share the same feature space and class label space, but have significantly different distributions. One d…