25:31

Tony Cohn - Simultaneously Learning and Grounding Object Features and Spatial Relations

MITCBMM

19:22

Tomaso Poggio - Science and Engineering of Intelligence

MITCBMM

24:38

Stefanie Tellex - Human-Robot Collaboration

MITCBMM

37:17

Song Chun Zhu - Joint Video-Text Parsing and Query Answering

MITCBMM

17:33

Patrick Winston - The Vision Story: Why vision research really matters to me

MITCBMM

29:46

Linda Smith - The Visual Side of Early Object Name Learning (1 to 2 year old toddlers)

MITCBMM

30:57

Kristen Grauman - Learning the right thing with visual attributes

MITCBMM

31:13

Joyce Chai - Human-Human Communication

MITCBMM

36:57

Jeffrey Mark Siskind - Computer Vision Language

MITCBMM

26:41

Jason J Corso - When to Connection Vision and Language, The Low-, Mid- or High-Level

MITCBMM

19:21

Krystian Mikolajczyk - Image Annotation Challenge Summary

MITCBMM

29:39

Andrej Karpathy - Automated Image Captioning with ConvNets and Recurrent Nets

MITCBMM