CLVL Program*

Dec 17, 2015 

 8:30am   Opening 
 8:40am-9:15am Invited talk: Sanja Fidler, U. of. Toronto

Towards understanding stories in movies

 9:25am-10:00am Invited talk: Tamara Berg, UNC Chapel Hill

Image Description Generation and Beyond...
 10:00am-10:40am Coffee Break - Posters 
 10:40am-11:15am Invited talk: Devi Parikh, Virginia Tech

Visual Question Answering (VQA)

 11:20am-11:55am Invited talk: Svetlana Lazebnik, UIUC

Image Description: From Image-Sentence Embeddings to Region-Phrase Correspondence
 12:00pm-1:00pm Lunch break 
 1:00pm - 2:20pmOral Session

Semantic Enrichment of Bag-of-Visual-Words  
Anirudh Goyal, Shailesh Kumar, C.V Jawahar
extended abstract

A Multi-scale Multiple Instance Video Description Network,
Huijuan Xu,, Kate Saenko
extended abstract

Grounding of Textual Phrases in Images by Reconstruction
Anna Rohrbach, Marcus Rohrbach, Ronghang Hu, Trevor Darrell, Bernt Schiele
extended abstract

Relating Natural Language and Visual Recognition
 Marcus Rohrbach, Jacob Andreas, Trevor Darrell, Lisa Anne Hendricks, Dan Klein, Ronghang Hu, Raymond Mooney. Anna Rohrbach, Kate Saenko, Bernt Schiele, Subhashini Venugopalan
extended abstract

Sherlock: Modeling Structured Knowledge in Images
Mohamed Elhoseiny, Scott Cohen, Walter Chang, Brian Price, Ahmed Elgammal
extended abstract

Joint Learning from Video and Caption
Tingran Wang, Nishant Shukla, Caiming Xiong
extended abstract (poster only)
 2:25pm-3:00pm Invited talk: Kate Saenko, UMass Lowell

Implicit and Explicit Attention in Neural Models of Language and Vision.
 3:00pm-4:00pm Posters Session - Coffee Break 
 4:00pm-4:50pm Closing Keynote: Richard Socher, MetaMind 

Deep Learning for Multimodal Text-Image Modeling 
 4:50pm-6:00pm Panel Discussion

Panelist:  Scott Cohen (Adobe), Svetlana Lazebnik(UIUC), Kate Saenko (UMass), Richard Socher (MetaMind)