IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information

2022

Citations in the corpus

• Disentangling in Latent Space by Harnessing a Pretrained Generator (2020, background): “A properly disentangled representation can benefit semantic data mixing [30, 62], transfer learning for downstream tasks [6, 60], or even interpretability [43].”
• Optimizing Dense Retrieval Model Training with Hard Negatives (2021, methodology): “We further investigate using index compression techniques [13] to greatly save computational resources for ADORE.”
• Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption (2020, methodology): “On the image classification task, the base model is ResNet34 (He et al. 2016), the datasets are CIFAR-10 (Torralba, Fergus, and Freeman 2008) and ImageNet, and the evaluation metric is accuracy.”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “Moreover, VocGAN also applied the joint conditional and unconditional (JCU) loss [256].”
• Accelerating Large-Scale Inference with Anisotropic Vector Quantization (2019, methodology): “…methods of this form are available for binary quantization (He et al., 2013; Liong et al., 2015; Dai et al., 2017), product quantization (Jegou et al., 2011; Guo et al., 2016b; Zhang et al., 2014; Wu et al., 2017), additive quantization (Babenko & Lempitsky, 2014; Martinez et al.,…”
• Adaptive Graph Encoder for Attributed Graph Embedding (2020, methodology): “For node clustering, we perform Spectral Clustering [22] on the similarity matrices of saved embeddings, and select the best epoch by Davies–Bouldin index [8] (DBI), which measures the clustering quality without label information.”
• Towards causal benchmarking of bias in face analysis algorithms (2020, methodology): “In particular, empirical studies show that each image attribute often has a direction v ∈ R that predominantly captures its variability [36, 82].”