Cmu - Ucr - Bosch @ Trecvid 2017 : Video to Text Retrieval
نویسندگان
چکیده
We participated in the matching and ranking subtask in TRECVid challenge 2017. The task here was to return a ranked list of the most likely text descriptions that correspond to each video. We adopted a joint visual semantic embedding approach for image-text retrieval and applied to the video-text retrieval task utilizing key-frames extracted by dissimilaritybased sparse subset selection approach. We trained our system on the MS-COCO dataset and tested on the TRECVid dataset. Our approach got an average mean inverted ranking score of 0.255 across 4 sets of testing data, and we ranked the 3rd overall in the challenge on this task.
منابع مشابه
Video Searching and Browsing Using ViewFinder: Interactive Search Experiments for TRECVID-2003
This research project explores the topic of video information retrieval in conjunction with the task definitions and data provided by the Text REtrieval Conference’s (TREC) 2003 Video Workshop (TRECVID-2003). Included in this paper, we discuss our processes and various phases in participating with TRECVID-2003. Specific sections discussed include database development, data indexing and retrieva...
متن کاملVideo Searching and Browsing Using ViewFinder: Participation and Assessment in TRECVID-2003
This research project explores the topic of video information retrieval in conjunction with the task definitions and data provided by the Text REtrieval Conference’s (TREC) 2003 Video Workshop (TRECVID-2003). Included in this paper, we discuss our processes and various phases in participating with TRECVID-2003. Specific sections discussed include database development, data indexing and retrieva...
متن کاملTRECVID 2010 - An Overview of the Goals, Tasks, Data, Evaluation Mechanisms and Metrics
The Text Retrieval Conference’s (TREC’s) Video Retrieval Evaluation (TRECVID) 2010 was a TRECstyle video analysis and retrieval evaluation, the goal of which remains to promote progress in contentbased exploitation of digital video via open, metricsbased evaluation. Over the last 10 years this effort has yielded a better understanding of how systems can effectively accomplish such processing an...
متن کاملYork_University at TRECVID 2010
In this paper, we describe our work done by members at York University in Canada for the KIS (Known-item search) task of TRECVID 2010. This is the first time that we participate in the TRECVID. With rich experience in text retrieval, we mainly focus on the meta information of videos, and try to figure out the importance of these description corpus. In order to obtain this goal, we do not use an...
متن کاملLarge Scale Evaluations of Multimedia Information Retrieval: The TRECVid Experience
Information Retrieval is a supporting technique which underpins a broad range of content-based applications including retrieval, filtering, summarisation, browsing, classification, clustering, automatic linking, and others. Multimedia information retrieval (MMIR) represents those applications when applied to multimedia information such as image, video, music, etc. In this presentation and exten...
متن کامل