Sciweavers

MM
2015
ACM
16views Multimedia» more  MM 2015»
8 years 6 months ago
Accelerating Large-scale Image Retrieval on Heterogeneous Architectures with Spark
Apache Spark is a general-purpose cluster computing system for big data processing and has drawn much attention recently from several fields, such as pattern recognition, machine...
Hanli Wang, Bo Xiao, Lei Wang, Jun Wu
MM
2015
ACM
15views Multimedia» more  MM 2015»
8 years 6 months ago
Modeling Perspective Effects in Photographic Composition
Automatic understanding of photo composition is a valuable technology in multiple areas including digital photography, multimedia advertising, entertainment, and image retrieval. ...
Zihan Zhou, Siqiong He, Jia Li, James Ze Wang
MM
2015
ACM
19views Multimedia» more  MM 2015»
8 years 6 months ago
SHOE: Sibling Hashing with Output Embeddings
We present a supervised binary encoding scheme for image retrieval that learns projections by taking into account similarity between classes obtained from output embeddings. Our m...
Sravanthi Bondugula, Varun Manjunatha, Larry S. Da...
MM
2015
ACM
24views Multimedia» more  MM 2015»
8 years 6 months ago
Image Retrieval by Cross-Media Relevance Fusion
How to estimate cross-media relevance between a given query and an unlabeled image is a key question in the MSR-Bing Image Retrieval Challenge. We answer the question by proposing...
Jianfeng Dong, Xirong Li, Shuai Liao, Jieping Xu, ...
MM
2015
ACM
16views Multimedia» more  MM 2015»
8 years 6 months ago
Query-by-Emoji Video Search
This technical demo presents Emoji2Video, a query-by-emoji interface for exploring video collections. Ideogram-based video search and representation presents an opportunity for an...
Spencer Cappallo, Thomas Mensink, Cees G. M. Snoek
MM
2015
ACM
48views Multimedia» more  MM 2015»
8 years 6 months ago
Unsupervised Cosegmentation based on Global Graph Matching
Cosegmentation is defined as the task of segmenting a common object from multiple images. Hitherto, graph matching has been known as a promising approach because of its flexibil...
Takanori Tamanaha, Hideki Nakamaya
MM
2015
ACM
4views Multimedia» more  MM 2015»
8 years 6 months ago
Image2Emoji: Zero-shot Emoji Prediction for Visual Media
We present Image2Emoji, a multi-modal approach for generating emoji labels for an image in a zero-shot manner. Different from existing zero-shot image-to-text approaches, we expl...
Spencer Cappallo, Thomas Mensink, Cees G. M. Snoek
MM
2015
ACM
20views Multimedia» more  MM 2015»
8 years 6 months ago
Bandwidth-aware Prefetching for Proactive Multi-video Preloading and Improved HAS Performance
This paper considers the problem of providing users playing one streaming video the option of instantaneous and seamless playback of alternative videos. Recommendation systems can...
Vengatanathan Krishnamoorthi, Niklas Carlsson, Der...
MM
2015
ACM
14views Multimedia» more  MM 2015»
8 years 6 months ago
Vision-Inertial Hybrid Tracking for Robust and Efficient Augmented Reality on Smartphones
This paper aims at robust and efficient pose tracking for augmented reality on modern smartphones. Existing methods, relying on either vision analysis or motion sensing, are eithe...
Xin Yang, Xun Si, Tangli Xue, Liheng Zhang, Kwang-...