Learning to Recognize Objects from Unseen Modalities

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Cross Modal Distillation for Supervision Transfer (2015, background): “While [4, 43] hallucinate modalities during training time, [8, 33, 40] focus on the problem of jointly embedding or learning representations from multiple modalities into a shared feature space to improve learning [33] or enabling zero-shot learning[8, 40].”
Learning with Side Information through Modality Hallucination (2016, background): “[5] learned a mapping to hallucinate a missing modality at training time, but was only shown with weak recognition models.”
Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities (2018, unknown): “Models based on autoencoders [57], adversarial learning [7], or multiple 89 kernel learning [32] have also been proposed for these tasks.”
Shifting Weights: Adapting Object Detectors from Image to Video (2012, methodology): “In [30, 32], features or modalities unseen in the training data are used to help in testing.”
Automatic Understanding of Image and Video Advertisements (2017, background): “There is work in learning domaininvariant representations [22, 75, 7, 8, 18, 20, 31, 43, 11], but a challenge in the case of ads is that data from each “domain” (the particular way e.”
Cross-modal adaptation for RGB-D detection (2016, background): “Other approaches have been proposed to transfer generic information across modalities [8], but have only been shown with weak detection models.”