EE 500 Seminar - Grounded Language Acquisition and Vision - Winter 2015
Mon, 4:30-5:30pm in EEB M406

Schedule

Week Date Presenter Slides Readings
1 Jan 12 Hao Fang Introduction, "Show and Tell: A Neural Image Caption Generator", Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan pdf
2 Jan 26 Ji "Deep Visual-Semantic Alignments for Generating Image Descriptions", Andrej Karpathy, Li Fei-Fei, pdf
"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping", Andrej Karpathy, Armand Joulin, and Li Fei-Fei pdf
3 Feb 2 Hao Cheng "Learning Everything about Anything: Webly-Supervised Visual Concept Learning", Santosh Divvala, Ali Farhadi, Carlos Guestrin, CVPR 2014 pdf
4 Feb 9 Vicky, Kevin
  • From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions pdf
  • "Learning Spatial Knowledge for Text to 3D Scene Generation", Angel X. Chang, Manolis Savva and Christopher D. Manning, EMNLP 2014 pdf
  • 5 Feb 23 Trang "Models of Semantic Representation with Visual Attributes", Carina Silberer, Vittorio Ferrari, Mirella Lapata, ACL 2013 pdf
    6 March 2 Rik, Yi
  • Learning to Win by Reading Manuals in a Monte-Carlo Framework pdf
  • Linking people in videos with their names using coreference resolution pdf
  • 7 March 9 Min, Lee
  • Learning Distributions over Logical Forms for Referring Expression Generation pdf
  • Every Picture Tells a Story: Generating Sentences from Images pdf
  • Readings