25 citations · 76 across the 12 of their papers we have counts for
4 papers · 1 filter
Interactive-predictive neural multimodal systems
Álvaro Peris, Francisco Casacuberta
Despite the advances achieved by neural models in sequence to sequence learning, exploited in a variety of tasks, they still make errors. In many use cases, these are corrected by…
Egocentric Video Description based on Temporally-Linked Sequences
Marc Bolaños, Álvaro Peris, Francisco Casacuberta +2
Egocentric vision consists in acquiring images along the day from a first person point-of-view using wearable cameras. The automatic analysis of this information allows to discover…
VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering
Marc Bolaños, Álvaro Peris, Francisco Casacuberta +1
In this paper, we address the problem of visual question answering by proposing a novel model, called VIBIKNet. Our model is based on integrating Kernelized Convolutional Neural Ne…
Video Description using Bidirectional Recurrent Neural Networks
Álvaro Peris, Marc Bolaños, Petia Radeva +1
Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combin…