Share This Author
Automatic differentiation in machine learning: a survey
- A. G. Baydin, Barak A. Pearlmutter, Alexey Radul, J. Siskind
- Computer ScienceJournal of machine learning research
- 20 February 2015
By precisely defining the main differentiation techniques and their interrelationships, this work aims to bring clarity to the usage of the terms “autodiff’, “automatic differentiation”, and “symbolic differentiation" as these are encountered more and more in machine learning settings.
A computational study of cross-situational techniques for learning word-to-meaning mappings
- J. Siskind
- Computer ScienceCognition
- 1 October 1996
The role of exposure to isolated words in early vocabulary development
Recognize Human Activities from Partially Observed Videos
- Yu Cao, D. P. Barrett, Song Wang
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 23 June 2013
A new method that can recognize human activities from partially observed videos in the general case by dividing each activity into multiple ordered temporal segments and applying sparse coding to derive the activity likelihood of the test video sample at each segment is proposed.
Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic
- J. Siskind
- Computer ScienceJournal of Artificial Intelligence Research
- 1 July 2001
An implemented system for recognizing the occurrence of events described by simple spatial-motion verbs in short image sequences using force dynamics and event logic to specify the lexical semantics of events to be more robust than prior systems based on motion profile.
Image Segmentation with Ratio Cut
A new cost function, cut ratio, for segmenting images using graph-based methods that allows the image perimeter to be segmented, guarantees that the segments produced by bipartitioning are connected, and does not introduce a size, shape, smoothness, or boundary-length bias.
Salient closed boundary extraction with ratio contour
- Song Wang, Toshiro Kubota, J. Siskind, Jun Wang
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 April 2005
The Gestalt laws of proximity and continuity are encoded in a novel boundary-saliency measure based on the relative gap length and average curvature when connecting fragments to form a closed boundary.
Video In Sentences Out
- Andrei Barbu, Alexander Bridge, Zhiqi Zhang
- LinguisticsConference on Uncertainty in Artificial…
- 12 April 2012
A system that produces sentential descriptions of video: who did what to whom, and where and how they did it, with an approach to event recognition that recovers object tracks, the track-to-role assignments, and changing body posture.
Image segmentation with minimum mean cut
A polynomial-time algorithm for finding a global minimum of the mean-cut cost function is presented and the results of applying that algorithm to several synthetic and real images are illustrated.
A Maximum-Likelihood Approach to Visual Event Classification
This paper presents a novel framework, based on maximum likelihood, for training models to recognise simple spatial-motion events, such as those described by the verbs pick up, put down, push, pull,…