Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJanuary 2020
A group-theoretic framework for data augmentation
The Journal of Machine Learning Research (JMLR), Volume 21, Issue 1Article No.: 245, Pages 9885–9955Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical framework to explain ...
- short-paperJuly 2021
FedNLP: An Interpretable NLP System to Decode Federal Reserve Communications
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalPages 2560–2564https://doi.org/10.1145/3404835.3462785The Federal Reserve System (the Fed) plays a significant role in affecting monetary policy and financial conditions worldwide. Although it is important to analyse the Fed's communications to extract useful information, it is generally long-form and ...
- research-articleJune 2017
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
NOSSDAV'17: Proceedings of the 27th Workshop on Network and Operating Systems Support for Digital Audio and VideoPages 67–72https://doi.org/10.1145/3083165.3083180We study the problem of predicting the Field-of-Views (FoVs) of viewers watching 360° videos using commodity Head-Mounted Displays (HMDs). Existing solutions either use the viewer's current orientation to approximate the FoVs in the future, or ...
360° Video Viewing Dataset in Head-Mounted Virtual Reality
MMSys'17: Proceedings of the 8th ACM on Multimedia Systems ConferencePages 211–216https://doi.org/10.1145/3083187.3083219360° videos and Head-Mounted Displays (HMDs) are getting increasingly popular. However, streaming 360° videos to HMDs is challenging. This is because only video content in viewers' Field-of-Views (FoVs) is rendered, and thus sending complete 360° videos ...
- research-articleDecember 2014
Implementing a signature perfume recommendation system based on perfume similarity evaluation
HCIK '15: Proceedings of HCI KoreaPages 461–465In this paper, we propose a perfume recommendation system which computes note similarity scores based on user feedbacks and suggests rather uncommon perfumes that the user potentially like, while being unaffected by the general popularity of certain ...
-
- research-articleOctober 2022
EuglPollock: Rethinking Interspecies Collaboration through Art Making
MM '22: Proceedings of the 30th ACM International Conference on MultimediaPages 1077–1084https://doi.org/10.1145/3503161.3548151Humans are no longer the exclusive creators of art; art can now be produced by non-human actors such as artificial intelligence, machines, or animals. This paper presents EuglPollock, a platform for creating artwork through interactions between humans ...
- research-articleAugust 2021
ReMember: Using Biosignals to Recall Memories of Companion Animals
Proceedings of the ACM on Computer Graphics and Interactive Techniques (PACMCGIT), Volume 4, Issue 2Article No.: 29, Pages 1–7https://doi.org/10.1145/3465614ReMember is an interactive installation that provides bereaved pet owners with a sense of presence and connection to their deceased companion animals. Many pet owners suffer from bereavement and grief upon the loss of companion animals, and rituals and ...
- research-articleMay 2015
All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement
WWW '15: Proceedings of the 24th International Conference on World Wide WebPages 1056–1066https://doi.org/10.1145/2736277.2741661Although analyzing user behavior within individual communities is an active and rich research domain, people usually interact with multiple communities both on- and off-line. How do users act in such multi-community environments? Although there are a ...
- research-articleApril 2017
Cats and Captions vs. Creators and the Clock: Comparing Multimodal Content to Context in Predicting Relative Popularity
WWW '17: Proceedings of the 26th International Conference on World Wide WebPages 927–936https://doi.org/10.1145/3038912.3052684The content of today's social media is becoming more and more rich, increasingly mixing text, images, videos, and audio. It is an intriguing research question to model the interplay between these different modes in attracting user attention and ...
- research-articleApril 2017
When Confidence and Competence Collide: Effects on Online Decision-Making Discussions
WWW '17: Proceedings of the 26th International Conference on World Wide WebPages 1381–1390https://doi.org/10.1145/3038912.3052681Group discussions are a way for individuals to exchange ideas and arguments in order to reach better decisions than they could on their own. One of the premises of productive discussions is that better solutions will prevail, and that the idea selection ...
- research-articleNovember 2019
Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Community
Proceedings of the ACM on Human-Computer Interaction (PACMHCI), Volume 3, Issue CSCWArticle No.: 163, Pages 1–21https://doi.org/10.1145/3359265Moderators of online communities often employ comment deletion as a tool. We ask here whether, beyond the positive effects of shielding a community from undesirable content, does comment removal actually cause the behavior of the comment's author to ...
- research-articleJune 2007
Testing cladistics on dialect networks and phyla (gallo-romance and southern italo-romance)
This present work deliberately abandons the purpose of capturing the global resemblance between languages and the ambition of giving a rational foundation to probability of changes in linguistics, to focus instead on cladistic approach, which was ...
- research-articleApril 2016
Internet Collaboration on Extremely Difficult Problems: Research versus Olympiad Questions on the Polymath Site
WWW '16: Proceedings of the 25th International Conference on World Wide WebPages 1283–1292https://doi.org/10.1145/2872427.2883023Despite the existence of highly successful Internet collaborations on complex projects, including open-source software, little is known about how Internet collaborations work for solving "extremely" difficult problems, such as open-ended research ...
- research-articleJuly 2010
Clueless: explorations in unsupervised, knowledge-lean extraction of lexical-semantic information
CoNLL '10: Proceedings of the Fourteenth Conference on Computational Natural Language LearningPage 55I will discuss two current projects on automatically extracting certain types of lexical-semantic information in settings wherein we can rely neither on annotations nor existing knowledge resources to provide us with clues. The name of the game in such ...
- research-articleNovember 2010
PageRank without hyperlinks: Structural reranking using links induced by language models
ACM Transactions on Information Systems (TOIS), Volume 28, Issue 4Article No.: 18, Pages 1–38https://doi.org/10.1145/1852102.1852104The ad hoc retrieval task is to find documents in a corpus that are relevant to a query. Inspired by the PageRank and HITS (hubs and authorities) algorithms for Web search, we propose a structural reranking approach to ad-hoc retrieval that applies to ...
- otherDecember 2020
Plantext
SA '20: SIGGRAPH Asia 2020 Art GalleryArticle No.: 45, Page 1https://doi.org/10.1145/3414686.3427139Many people enjoy keeping houseplants and get comfort from the presence of plants. Not only for aesthetics and medical purposes, plants also have many other uses in human history. As a result, plant ecology and its biological evolutions are closely ...
- research-articleMay 2009
Clusters, language models, and ad hoc information retrieval
ACM Transactions on Information Systems (TOIS), Volume 27, Issue 3Article No.: 13, Pages 1–39https://doi.org/10.1145/1508850.1508851The language-modeling approach to information retrieval provides an effective statistical framework for tackling various problems and often achieves impressive empirical performance. However, most previous work on language models for information ...
- research-articleApril 2016
Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
WWW '16: Proceedings of the 25th International Conference on World Wide WebPages 613–624https://doi.org/10.1145/2872427.2883081Changing someone's opinion is arguably one of the most important challenges of social interaction. The underlying process proves difficult to study: it is hard to know how someone's opinions are formed and whether and how someone's views shift. ...
- abstractOctober 2015
An Ant's Life: Storytelling in Virtual Reality
CHI PLAY '15: Proceedings of the 2015 Annual Symposium on Computer-Human Interaction in PlayPages 779–782https://doi.org/10.1145/2793107.2810264An Ant's Life is a game that explores the use of virtual reality in connection with physical props to tell a captivating story and create a unique immersive experience through innovation in graphics, gameplay and design. It takes a new approach to the ...
- research-articleJuly 2010
Don't 'have a clue'?: unsupervised co-learning of downward-entailing operators
Researchers in textual entailment have begun to consider inferences involving downward-entailing operators, an interesting and important class of lexical items that change the way inferences are made. Recent work proposed a method for learning English ...