@InProceedings{PrimusTrecVID2017, author = {Primus, Manfred Jürgen and Münzer, Bernd and Schoeffmann, Klaus}, booktitle = {Proceedings of TRECVID 2017}, title = {ITEC-UNIKLU Ad-Hoc Video Search Submission 2017}, year = {2017}, address = {NIST, Gaithersburg, MD, USA}, editor = {Awad,George and Butt,Asad and Fiscus,Jonathan and Joy,David and Delgado,Andrew and Michel,Martial and Smeaton,Alan and Graham,Yvette and Kraaij,Wessel and Quénot,Georges and Eskevich,Maria and Ordelman,Roeland and Jones,Gareth and Huet,Benoit}, month = {nov}, pages = {10}, publisher = {NIST, USA}, abstract = {This paper describes our approach used for the fully automatic and manually assisted Ad-hoc Video Search (AVS) task for TRECVID 2017. We focus on the combination of different convolutional neural network models and query optimization. Each of this model focus on a specific query part, which could be, e.g., location, objects, or the wide-ranging ImageNet classes. All classification results are collected in different combinations in Lucene indixes. For the manually assisted run we use a junk filter and different query optimization methods.}, language = {EN}, location = {Gaithersburg, MD, USA}, talkdate = {2017.11.13}, talktype = {poster} }