English
Related papers

Related papers: Differential Contrastive Training for Gaze Estimat…

200 papers

Graph contrastive learning (GCL) has emerged as a pivotal technique in the domain of graph representation learning. A crucial aspect of effective GCL is the caliber of generated positive and negative samples, which is intrinsically dictated…

Machine Learning · Computer Science 2024-02-19 Xinjian Zhao , Liang Zhang , Yang Liu , Ruocheng Guo , Xiangyu Zhao

The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks. While CLIP has revolutionized multimodal learning through joint training on images and text, its potential to unintentionally disclose…

Machine Learning · Computer Science 2024-03-04 Alyssa Huang , Peihan Liu , Ryumei Nakada , Linjun Zhang , Wanrong Zhang

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising…

Machine Learning · Computer Science 2024-01-30 Wei Ju , Yiyang Gu , Zhengyang Mao , Ziyue Qiao , Yifang Qin , Xiao Luo , Hui Xiong , Ming Zhang

Automatic radiology reporting has great clinical potential to relieve radiologists from heavy workloads and improve diagnosis interpretation. Recently, researchers have enhanced data-driven neural networks with medical knowledge graphs to…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Mingjie Li , Bingqian Lin , Zicong Chen , Haokun Lin , Xiaodan Liang , Xiaojun Chang

Contrastive Language-Image Pre-training (CLIP) excels in global alignment with language but exhibits limited sensitivity to spatial information, leading to strong performance in zero-shot classification tasks but underperformance in tasks…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Congpei Qiu , Yanhao Wu , Wei Ke , Xiuxiu Bai , Tong Zhang

Traditional gaze estimation methods typically require explicit user calibration to achieve high accuracy. This process is cumbersome and recalibration is often required when there are changes in factors such as illumination and pose. To…

Computer Vision and Pattern Recognition · Computer Science 2019-10-24 Zhuoqing Chang , Matias Di Martino , Qiang Qiu , Steven Espinosa , Guillermo Sapiro

Appearance-based gaze estimation from RGB images provides relatively unconstrained gaze tracking. We have previously proposed a gaze decomposition method that decomposes the gaze angle into the sum of a subject-independent gaze estimate…

Computer Vision and Pattern Recognition · Computer Science 2022-02-15 Zhaokang Chen , Bertram E. Shi

Aiming to generalize the well-trained gaze estimation model to new target domains, Cross-domain Gaze Estimation (CDGE) is developed for real-world application scenarios. Existing CDGE methods typically extract the domain-invariant features…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Hao-Ran Yang , Xiaohui Chen , Chuan-Xian Ren

The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge through different…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Pengwei Yin , Jingjing Wang , Guanzhong Zeng , Di Xie , Jiang Zhu

We introduce a novel semi-supervised Graph Counterfactual Explainer (GCE) methodology, Dynamic GRAph Counterfactual Explainer (DyGRACE). It leverages initial knowledge about the data distribution to search for valid counterfactuals while…

Machine Learning · Computer Science 2023-08-07 Bardh Prenkaj , Mario Villaizan-Vallelado , Tobias Leemann , Gjergji Kasneci

Graph contrastive learning (GCL) has recently emerged as an effective learning paradigm to alleviate the reliance on labelling information for graph representation learning. The core of GCL is to maximise the mutual information between the…

Machine Learning · Computer Science 2022-10-18 Yizhen Zheng , Yu Zheng , Xiaofei Zhou , Chen Gong , Vincent CS Lee , Shirui Pan

Gaze-annotated facial data is crucial for training deep neural networks (DNNs) for gaze estimation. However, obtaining these data is labor-intensive and requires specialized equipment due to the challenge of accurately annotating the gaze…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Nerea Aranjuelo , Siyu Huang , Ignacio Arganda-Carreras , Luis Unzueta , Oihana Otaegui , Hanspeter Pfister , Donglai Wei

Inspired by human visual attention, deep neural networks have widely adopted attention mechanisms to learn locally discriminative attributes for challenging visual classification tasks. However, existing approaches primarily emphasize the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Jiahang Li , Shibo Xue , Yong Su

Multiple datasets have been created for training and testing appearance-based gaze estimators. Intuitively, more data should lead to better performance. However, combining datasets to train a single esti-mator rarely improves gaze…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Liang Wu , Bertram E. Shi

Image Aesthetics Assessment (IAA) is a challenging task due to its subjective nature and expensive manual annotations. Recent large-scale vision-language models, such as Contrastive Language-Image Pre-training (CLIP), have shown their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Liwu Xu , Jinjin Xu , Yuzhe Yang , Xilu Wang , Yijie Huang , Yaqian Li

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Alex Andonian , Shixing Chen , Raffay Hamid

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower…

Computer Vision and Pattern Recognition · Computer Science 2020-02-05 Wenyang Hu , Xiaocong Cai , Jun Hou , Shuai Yi , Zhiping Lin

Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. In order to avoid potential misleading…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Hanzhe Hu , Deyi Ji , Weihao Gan , Shuai Bai , Wei Wu , Junjie Yan

Among different existing graph self-supervised learning strategies, graph contrastive learning (GCL) has been one of the most prevalent approaches to this problem. Despite the remarkable performance those GCL methods have achieved, existing…

Machine Learning · Computer Science 2022-10-27 Qianlong Wen , Zhongyu Ouyang , Chunhui Zhang , Yiyue Qian , Yanfang Ye , Chuxu Zhang

Recent studies show that graph neural networks (GNNs) are prevalent to model high-order relationships for collaborative filtering (CF). Towards this research line, graph contrastive learning (GCL) has exhibited powerful performance in…

Information Retrieval · Computer Science 2024-02-27 Xubin Ren , Lianghao Xia , Jiashu Zhao , Dawei Yin , Chao Huang