Abstract Galaxy morphology reflects structural properties that contribute to the understanding of formation and evolution galaxies. Deep convolutional networks have proven be very successful in learning hidden features allow for unprecedented performance morphological classification Such mostly follow supervised paradigm, which requires sufficient labeled data training. However, labeling a mill...

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer performance compared to fully-supervised methods, seeming deliver message that human labels hardly contribute transferrable features. In this paper, we defend usefulness semantic but point out and metho...

Electrophysiological mapping using multiple-unit criteria was employed to study the representation of the visual field in the superior colliculus of the rabbit. It was found that the contralateral superior colliculus of the rabbit has an extended representation beyond the representation of the zero vertical meridian or the line of decussation in the geniculostriate system. The amount of extende...

This paper discusses open problems and future research regarding the recognition and representation of structures in sequences of either 2D images or 3D data. All presented concepts aim at improving the recognition of structure in data (especially by decreasing the influence of noise) and at extending the representational power of known descriptors (within the scope of this paper graphs and ske...

This paper proposes object-based moving visual representations for quick browsing of video content. These representations are hierarchical, such that at the coarse level a sequence of alpha planes provides a moving representation of object shape and motion information for object contours. Alternatively, a 2D mesh representation provides a complete visual representation of object mot ion and sha...

This paper presents a novel semantic regularized matrix factorization method for learning descriptive visual bag-of-words (BOW) representation. Although very influential in image classification, the traditional visual BOW representation has one distinct drawback. That is, for efficiency purposes, this visual representation is often generated by directly clustering the low-level visual feature v...

text from WO2001072212A1) A method and apparatus for electronically performing a visual field test for a patient. A visual field test pattern is displayed to the patient on an electronic display device and the patient's responses to the visual field test pattern are recorded. A visual field representation is generated from the patient's responses. The visual field representation is then used as...

In this paper, we investigate audio-visual interaction in sparse representation to obtain robust features for audio-visual speech recognition. Firstly, we introduce our system which uses sparse representation method for noise robust audio-visual speech recognition. Then, we introduce the dictionary matrix used in this paper, and consider the construction of audio-visual dictionary. Finally, we ...