Asia
Supplemental Material for Learning with Noisy Correspondence for Cross-modal Matching
Some parts of the work was done while Zhenyu Huang was an internship at Baidu Inc.
LearningwithNoisyCorrespondence forCross-modalMatching
In practice, however, such an assumption is extremely expensive even impossible to satisfy. Based on this observation, we reveal and study alatent and challenging direction in cross-modal matching, named noisy correspondence, which could be regarded as a new paradigm of noisylabels.
CXPlain: Causal Explanations for Model Interpretation under Uncertainty
Neural Information Processing Systems http://nips.cc/
Towards Editing Time Series
Synthesizing time series data is pivotal in modern society, aiding effective decision-making and ensuring privacy preservation in various scenarios.
cba76ef96c4cd625631ab4d33285b045-Paper-Conference.pdf
Learning disentangled and distributed representation ofgenerativefactors oftheworld isbelieved tobenefit compositional generalization, because those invariant features canbereused assymbols to build exponentially larger amounts of objects with higher complexity [1, 2, 3, 4].
