The Lowlands team at TRECVID 2007
نویسندگان
چکیده
Type Run Description MAP Official A UTen English ASR 0.0031 A UTt hs-t2-nm Top-2 concepts from t hs graph method with neighbor multiply 0.0137 A UTwiki-t2-nm Top-2 Wikipedia concepts with neighbor multiply 0.0131 A UTwiki-t2-en-nm Top-2 Wikipedia concepts and English ASR with neighbor multiply 0.0107 A UTwiki-t2-nl-nm Top-2 Wikipedia concepts and Dutch ASR with neighbor multiply 0.0096 A UTwordnet-t2-mult Top-2 Wordnet concepts with neighbor multiply 0.0083 Additional A UTnl Dutch ASR 0.0031 A UTwikiS-t2-nT Top-2 Wikipedia concepts on stemmed queries with neighbor using the concept detector scores from the B tsinghua-icrc 5 run 0.0410 A UTt hs-t2-n Top-2 concepts from t hs graph method of stemmed queries with neighbor the concept detector scores from the B tsinghua-icrc 5 run 0.0346 I UTinter-wiki-nm Interactive Search Task using Wikipedia concepts with neighbor multiply 0.0405 I UTinter-en Interactive Search Task using ASR based search 0.0338 Summary: Concept to Query does not differ very much; Best combination method neighbor; Preprocessing of Queries helps; Choice of detector source helps. For all components further investigations needed. Interactive system: rather poor but good insights why.
منابع مشابه
TRECVid 2012 Experiments at Dublin City University
Following previous participations in TRECVid, this year, the DCU-IAD team participated in four tasks of TRECVid 2012: Instance Search (INS), Interactive Known-Item Search (KIS), Multimedia Event Detection (MED) and Multimedia Event Recounting (MER).
متن کاملEURECOM at TRECVID 2016: The Adhoc Video Search and Video Hyperlinking Tasks
This paper describes the submissions of the EURECOM team to the TRECVID 2016 AVS and LNK tasks.
متن کاملTRECVID 2010 Experiments at Dublin City University
This year the DCU-CLARITY-iAD team participated in the both the instance search and interactive known-item search tasks of TRECVid 2010. For our instance search submission, we used classifiers to search for candidate objects in each keyframe. This was achieved by a coarse-to-fine search based on a hierarchical representation of the regions in the keyframes. Our results proved inconclusive, but ...
متن کاملREGIMVID at TRECVID 2009: Semantic Access to Multimedia Data
In this paper we describe our TRECVID 2009 video retrieval experiments. The REGIMVID team participated in two tasks: High Level Feature Extraction and Automatic Search. Our TRECVID 2009 experiments focus on increasing the robustness of a small set of sensors and the relevance of the results using a probabilistic weighting of learning examples.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007