@inproceedings{vukotic:hal-01374727, TITLE = {{Multimodal and Crossmodal Representation Learning from Textual and Visual Features with Bidirectional Deep Neural Networks for Video Hyperlinking}}, AUTHOR = {Vukoti{\'c}, Vedran and Raymond, Christian and Gravier, Guillaume}, URL = {https://inria.hal.science/hal-01374727}, BOOKTITLE = {{ACM Multimedia 2016 Workshop: Vision and Language Integration Meets Multimedia Fusion (iV\&L-MM'16)}}, ADDRESS = {Amsterdam, Netherlands}, ORGANIZATION = {{ACM Multimedia}}, YEAR = {2016}, MONTH = Oct, KEYWORDS = {neural networks ; deep learning ; convolutional neural networks ; CNN ; deep neural networks ; DNN ; representation ; embedding ; multimodal ; crossmodal ; autoencoder ; video and text ; video hyperlinking ; bidirectional learning ; retrieval ; video retrieval ; tied weights ; shared weights ; multimodal fusion}, PDF = {https://inria.hal.science/hal-01374727/file/vukotic_iV%26L-MM_2016.pdf}, HAL_ID = {hal-01374727}, HAL_VERSION = {v1}, }