First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors derive a new procedure to estimate a recursive-partition prediction rule in the streaming framework. Theoretical analyses demonstrate that the procedure is computationally efficient and attains the minimax prediction error rate, up to a log factor. A small empirical analysis is in agreement with the theory. The paper is excellent: the authors have produced an intuitive streaming algorithm with nearly sharp theoretical guarantees in terms of intrinsic dimension.

Neural Information Processing Systems http://nips.cc/

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1807" "Title:","Zero-shot recognition with unreliable attributes" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper strives to bridge the gap between the theory and practice of attribute-based zero-shot learning. The theory is that novel classes can be recognized automatically using pre-trained attribute predictors; in practice, however, learning these attribute classifiers can be as difficult or even more so than learning the object classes themselves. Random forests are trained to predict unseen classes from attribute vectors, and the training procedure takes into account the reliability of the attribute detectors by propagating a validation set through each decision tree at training time. The authors show how the method can be extended to handle training with a few training examples of test categories.

We thank the reviewers for their thoughtful and valuable feedback. There are no factual inaccuracies in the reviews that we would like to correct. We agree with the reviewers that the contributions of this paper are mostly theoretical in nature. Finally, we thank the reviewers for their specific suggestions for improving the presentation of our paper.

For an overview of random forests, we refer readers to the works of [10, 17, 26]. Empirical successes have attracted much attention on theoretical explorations of random forests.

For an overview of random forests, we refer readers to the works of [10, 17, 26]. Empirical successes have attracted much attention on theoretical explorations of random forests.

Neural Information Processing Systems http://nips.cc/

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper introduces an efficient feature transform of local decorrelation, which when combined with boosted (orthogonal) decision trees, considerably improves over the state-of-the-art on pedestrian detection. Overall, it is a clearly (and nicely) written paper with good analysis, enough details and solid experiments. Pros: - Very well written and executed paper - Attention to detail - Solid results - Straight forward and intuitive method Cons: - Incremental from Hariharan et al. (not major, see later) - If it claims ``Improved Detection'', as opposed to ``Improved Pedestrian Detection'', then I would have liked to see some more results on object detection or likewise. Going from global to local decorrelation, and doing the right analysis for design decisions set it apart.

The key element of the method is a vector-valued decision stump, factorized into an input-independent vector of length $K$ and label-independent scalar classifier.},