Proceedings of the Third Workshop on Vision and Language

Proceedings of the Third Workshop on Vision and Language Anja Belz Darren Cosker Frank Keller William Smith Kalina Bontcheva Sien Moens Alan Smeaton August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics http://www.aclweb.org/anthology/W14-54 book VL:2014 The Effect of Sensor Errors in Situated Human-Computer Dialogue NielsSchütte JohnKelleher BrianMac Namee Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 1–8 http://www.aclweb.org/anthology/W14-5401 inproceedings schutte-kelleher-macnamee:2014:VL Joint Navigation in Commander/Robot Teams: Dialog & Task Performance When Vision is Bandwidth-Limited DouglasSummers-Stay TaylorCassidy ClareVoss Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 9–16 http://www.aclweb.org/anthology/W14-5402 inproceedings summersstay-cassidy-voss:2014:VL TUHOI: Trento Universal Human Object Interaction Dataset Dieu-ThuLe JasperUijlings RaffaellaBernardi Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 17–24 http://www.aclweb.org/anthology/W14-5403 inproceedings le-uijlings-bernardi:2014:VL Concept-oriented labelling of patent images based on Random Forests and proximity-driven generation of synthetic data DimitrisLiparas AnastasiaMoumtzidou StefanosVrochidis IoannisKompatsiaris Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 25–32 http://www.aclweb.org/anthology/W14-5404 inproceedings liparas-EtAl:2014:VL Exploration of functional semantics of prepositions from corpora of descriptions of visual scenes SimonDobnik JohnKelleher Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 33–37 http://www.aclweb.org/anthology/W14-5405 inproceedings dobnik-kelleher:2014:VL A Poodle or a Dog? Evaluating Automatic Image Annotation Using Human Descriptions at Different Levels of Granularity JosiahWang FeiYan AhmetAker RobertGaizauskas Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 38–45 http://www.aclweb.org/anthology/W14-5406 inproceedings wang-EtAl:2014:VL Key Event Detection in Video using ASR and Visual Data NirajShrestha Aparna N.Venkitasubramanian Marie-FrancineMoens Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 46–53 http://www.aclweb.org/anthology/W14-5407 inproceedings shrestha-venkitasubramanian-moens:2014:VL Twitter User Gender Inference Using Combined Analysis of Text and Image Processing ShigeyukiSakaki YasuhideMiura XiaojunMa KeigoHattori TomokoOhkuma Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 54–61 http://www.aclweb.org/anthology/W14-5408 inproceedings sakaki-EtAl:2014:VL Semantic and geometric enrichment of 3D geo-spatial models with captioned photos and labelled illustrations ChrisJones PaulRosin JonathanSlade Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 62–67 http://www.aclweb.org/anthology/W14-5409 inproceedings jones-rosin-slade:2014:VL Weakly supervised construction of a repository of iconic images LydiaWeiland WolfgangEffelsberg Simone PaoloPonzetto Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 68–73 http://www.aclweb.org/anthology/W14-5410 inproceedings weiland-effelsberg-ponzetto:2014:VL Cross-media Cross-genre Information Ranking based on Multi-media Information Networks TongtaoZhang HaiboLi HongzhaoHuang HengJi Min-HsuanTsai Shen-FuTsai ThomasHuang Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 74–81 http://www.aclweb.org/anthology/W14-5411 inproceedings zhang-EtAl:2014:VL Speech-accompanying gestures in Russian: functions and verbal context YuliaNikolaeva Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 82–86 http://www.aclweb.org/anthology/W14-5412 inproceedings nikolaeva:2014:VL DALES: Automated Tool for Detection, Annotation, Labelling, and Segmentation of Multiple Objects in Multi-Camera Video Streams MohammadBhat Joanna IsabelleOlszewska Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 87–94 http://www.aclweb.org/anthology/W14-5413 inproceedings bhat-olszewska:2014:VL A Hybrid Segmentation of Web Pages for Vibro-Tactile Access on Touch-Screen Devices WaseemSAFI FabriceMaurel Jean-MarcRoutoure PierreBeust GaëlDias Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 95–102 http://www.aclweb.org/anthology/W14-5414 inproceedings safi-EtAl:2014:VL Expression Recognition by Using Facial and Vocal Expressions GholamrezaAnbarjafari AlvoAabloo Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 103–105 http://www.aclweb.org/anthology/W14-5415 inproceedings anbarjafari-aabloo:2014:VL Formulating Queries for Collecting Training Examples in Visual Concept Classification KevinMcGuinness FeiyanHu RamiAlbatal AlanSmeaton Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 106–108 http://www.aclweb.org/anthology/W14-5416 inproceedings mcguinness-EtAl:2014:VL Towards Succinct and Relevant Image Descriptions DesmondElliott Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 109–111 http://www.aclweb.org/anthology/W14-5417 inproceedings elliott:2014:VL Coloring Objects: Adjective-Noun Visual Semantic Compositionality DatTien Nguyen AngelikiLazaridou RaffaellaBernardi Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 112–114 http://www.aclweb.org/anthology/W14-5418 inproceedings tiennguyen-lazaridou-bernardi:2014:VL Multi-layered Image Representation for Image Interpretation MarinaIvasic-Kos MiranPobar IvoIpsic Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 115–117 http://www.aclweb.org/anthology/W14-5419 inproceedings ivasickos-pobar-ipsic:2014:VL The Last 10 Metres: Using Visual Analysis and Verbal Communication in Guiding Visually Impaired Smartphone Users to Entrances AnjaBelz AnilBharath Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 118–120 http://www.aclweb.org/anthology/W14-5420 inproceedings belz-bharath:2014:VL Keyphrase Extraction using Textual and Visual Features YaakovHaCohen-Kerner StefanosVrochidis DimitrisLiparas AnastasiaMoumtzidou IoannisKompatsiaris Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 121–123 http://www.aclweb.org/anthology/W14-5421 inproceedings hacohenkerner-EtAl:2014:VL Towards automatic annotation of communicative gesturing KristiinaJokinen GrahamWilcock Proceedings of the Third Workshop on Vision and Language August 2014

Dublin, Ireland

Dublin City University and the Association for Computational Linguistics 124–125 http://www.aclweb.org/anthology/W14-5422 inproceedings jokinen-wilcock:2014:VL