A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
WARD-CMU @ TRECVID 2015
2015
TREC Video Retrieval Evaluation
We think all the changes are beneficial to the final submission 'WARD-CMU p-fusion 1' which wins 4 events in all 7 events. ...
We make the event names bold which we get the first positions in SED 2015 [12] . In total, we win 4 events in no matter the retrospective or the interactive competitions. ...
dblp:conf/trecvid/DuL0H15
fatcat:bwf4kwcvprgrxl2ji6tyduwkuq
CMU Informedia@TRECVID 2015: MED/SIN/LNK/SED
2015
TREC Video Retrieval Evaluation
We report on our system used in the TRECVID 2015 Multimedia Event Detection (MED) task. On the MED task, the CMU team submitted runs in the Semantic Query (SQ) and 10Ex settings. ...
MED System Description On the MED task, the CMU team uses the MED 2014 [1] system which has enabled the system to achieve good performance in the 000Ex and 010Ex settings. ...
WARD-CMU@TRECVID 2015 Surveillance Event Detection Xingzhong Du 1 , Xuanchong Li 2 , Xiaofang Zhou 1 , Alexander Hauptmann 2 1 The University of Queensland, 2 Carnegie Mellon University
I. ...
dblp:conf/trecvid/Yu0XLXCLMGMDCMW15
fatcat:ebabmpmrk5hyva5axagzma33n4
A Comprehensive Review of the Video-to-Text Problem
[article]
2021
arXiv
pre-print
, VTT 2016 - 11 TRECVID, VTT 2017 - 16 TRECVID, VTT 2018 - 12 TRECVID, VTT 2019 - 10 TRECVID, VTT 2020 - 6
annotated each video clip. ...
Transformer (Zhou et al. 2018c ) and RUC+CMU 11 (Chen et al. 2019c ) the best methods of 2018 and 2019, respectively. ...
arXiv:2103.14785v3
fatcat:xwzziozwjbghfobtowu5bny6bu