VL'15 Program

Place: Culturgest - Room 3 Room 6 and Culturgest - Lower Level Foyer (posters); Lisbon, Portugal
Time: September 18, 2015, 08:45-18:00

Session 1, 08:45-10:30, Room 6
Chair: Marie-Francine Moens
--
08:45-09:00 
Opening remarks
Marie-Francine Moens

09:00-10:00
Invited Talk 1: Grounding Distributional Semantics in the Visual World
Marco Baroni

10:00-10:30 
Poster spotlights 1:
10:00-10:05
Visually-Verifiable Textual Entailment: A Challenge Task for Combining Language and Vision
Jayant Krishnamurthy

10:05-10:10
Computational Integration of Human Vision and Natural Language through Bitext Alignment
Preethi Vaidyanathan, Emily Prud'hommeaux, Cecilia O. Alm, Jeff B. Pelz and Anne R. Haake

10:10-10:15
Towards Reliable Automatic Multimodal Content Analysis
Olli Philippe Lautenbacher, Liisa Tiittula, Maija Hirvonen, Jorma Laaksonen and Mikko Kurimo

10:15-10:20
Lingusitic Analysis of Multi-Modal Recurrent Neural Networks
Ákos Kádár, Grzegorz Chrupała and Afra Alishahi

10:20-10:25
Defining Visually Descriptive Language
Robert Gaizauskas, Josiah Wang and Arnau Ramisa

10:25-10:30
Semantic Tuples for Evaluation of Image to Sentence Generation
Lily D. Ellebracht, Arnau Ramisa, Pranava Swaroop Madhyastha, Jose Cordero-Rama, Francesc Moreno-Noguer and Ariadna Quattoni 



Coffee break, 10:30-11:00


Session 2, 11:00-12:15, Room 6
Chair: Desmond Elliott
--
11:00-11:25
Image Representations and New Domains in Neural Image Captioning
Jack Hessel, Nicolas Savva and Michael Wilber

11:25-11:50
Image with a Message: Towards Detecting Non-Literal Image Usages by Visual Linking
Lydia Weiland, Laura Dietz and Simone Paolo Ponzetto

11:50-12:15
Poster Spotlights 2:

11:50-11:55
Visual Classifier Prediction by Distributional Semantic Embedding of Text Descriptions
Mohamed Elhoseiny and Ahmed Elgammal

11:55-12:00
Understanding Urban Land Use through the Visualization of Points of Interest
Evgheni Polisciuc, Ana Alves and Penousal Machado

12:00-12:05
Comparing Attribute Classifiers for Interactive Language Grounding
Yanchao Yu, Arash Eshghi and Oliver Lemon

12:05-12:10
Combining Geometric, Textual and Visual Features for Generating Prepositions in Image Descriptions (to appear in EMNLP 2015)
Arnau Ramisa, Josiah Wang, Ying Lu, Emmanuel Dellandrea, Francesc Moreno-Noguer and Robert Gaizauskas 

12:10-12:15
From the Virtual to the Real World: Referring to Visible Objects Under Uncertainty in Real-World Spatial Scenes (to appear in EMNLP 2015)
Dimitra Gkatzia and Verena Rieser



Lunch (not provided by VL'15) and Poster Session, 12:15-14:00, Lower Level Foyer


Session 3, 14:00-15:30, Room 6
Chair: Ivan Vulic
--
14:00-15:00
Invited Talk 2: The ImageCLEF 2015 Task on Scalable Image Annotation, Localization and Sentence Generation
Krystian Mikolajczyk

15:00-15:30
Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval
Sebastian Schuster, Ranjay Krishna, Angel Chang, Li Fei-Fei and Christopher D. Manning 


Coffee break, 15:30-16:00


Session 4, 16:00-18:00, Room 6
Chair: Luisa Coheur
--
16:00-16:25
Do Distributed Semantic Models Dream of Electric Sheep? Visualizing Word Representations through Image Synthesis
Angeliki Lazaridou, Dat Tien Nguyen and Marco Baroni

16:25-16:50
A Weighted Combination of Text and Image Classifiers for User Gender Inference
Tomoki Taniguchi, Shigeyuki Sakaki, Ryosuke Shigenaka, Yukihiro Tsuboshita and Tomoko Ohkuma

16:50-17:15
Coupling Natural Language Processing and Animation Synthesis in Portuguese Sign Language Translation
Inês Almeida, Luísa Coheur and Sara Candeias 

17:15-17:40
Describing Spatial Relationships between Objects in Images in English and French
Anja Belz, Adrian Muscat, Maxime Aberton and Sami Benjelloun

17:40-18:00
Closing Remarks and Discussion
VL'15 Organizers