Recognizing RGB Images by Learning from RGB-D Data

By Lin Chen, Wen Li, Dong Xu. 2014

72 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Few-Shot Adversarial Domain Adaptation (2017, methodology): “In addition to these methods, [6, 36, 50] have addressed UDA when an auxiliary data view [31, 37], is available during training, but that is beyond the scope of this work.”
Unified Deep Supervised Domain Adaptation and Generalization (2017, background): “Recently, [7, 42] have addressed UDA when an auxiliary data view [36, 43], is available during training, which is beyond the scope of this work.”
Bilinear heterogeneous information machine for RGB-D action recognition (2015, background): “Due to the advent of low-cost Kinect sensors [16], lots of attempts have been devoted to object recognition [3, 2] and action recognition [10, 13, 25, 5] from depth images.”
Learning with Side Information through Modality Hallucination (2016, methodology): “Along these lines a transformation learning approach was recently introduced to use depth information at training time to inform RGB test time detection by learning transformations into a common feature representation across modalities [4].”
Exploiting Low-Rank Structure from Latent Domains for Domain Generalization (2014, methodology): “Domain adaptation techniques, which aim to reduce the domain distribution mismatch when the training and testing samples come from different domains, have been successfully used for a broad range of vision applications such as object recognition and video event recognition [23,17,16,10,11,12,6,7,24]”
Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition (2016, methodology): “In addition, for DA-M2S we set two parameters as indicated in [7], while for C and the others we look for those that maximize performance.”
Contextual Learning (2020, unknown): “…rand index, mutual information Feyereisl & Aickelin (2012) k-means UL on images: MNIST Poetic descriptions Kernel CCA [+MMD for domain adaption] Chen et al. (2014) Kernel SVM on kernel descriptor features SL on RGB: gender (EURECOM, LFW-a), object (RGB-D O.D., Catech-256) RGB-D SL on images…”
Domain Adaptation by Mixture of Alignments of Second-or Higher-Order Scatter Tensors (2016, methodology): “In contrast to [2, 30] which use both the RGB data and depth maps as a source, we adapt our source stream based on AlexNet to use only the depth data from the RGB-D dataset – this helps us isolate performance of our algorithm in case of distinct heterogeneous domains.”
Information Bottleneck Learning Using Privileged Information for Visual Recognition (2016, methodology): “The LUPI paradigm has recently been used for boosting [4], for object localization in a structured prediction framework [12], for facial feature detection [33], for metric learning [13, 46], in a logistic classification framework [43], in a max-margin latent variable model [41], and in support of do”
Collaborative and Adversarial Network for Unsupervised Domain Adaptation (2018, background): “Existing domain adaptation methods can be roughly categorized as feature (transform) based approaches [1, 11, 17], which aims to seek new domain-invariant features or learn new feature transforms for domain adaptation, and classifier based approaches [8, 9, 4, 7, 5, 29, 10], which directly learn the”
Hand-Crafted Features or Machine Learnt Features? Together They Improve RGB-D Object Recognition (2014, methodology): “[8] adopt the unsupervised domain adaptation (UDA) to solve the RGB image recognition task, in which the auxiliary depth images from source domain are employed for learning target classifier used for RGB images recognition.”
Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach (2018, unknown): “Similar idea has been exploited for image recognition [32, 2], and by a concurrent work [30] for semantic segmentation.”