We present a technique for estimating the similarity between objects such as
movies or foods whose proper representation depends on human perception. Our
technique combines a modest number of human similarity assessments to infer a
pairwise similarity function between the objects. This similarity function
captures some human notion of similarity which may be difficult or impossible
to automatically extract, such as which movie from a collection would be a
better substitute when the desired one is unavailable. In contrast to prior
techniques, our method does not assume that all similarity questions on the
collection can be answered or that all users perceive similarity in the same
way. When combined with a user model, we find how each assessor's tastes vary,
affecting their perception of similarity.

本文提出了一种技术，可以估计对象之间的相似度，如电影或食品，其适当的表达取决于人类的感知，这种相似度函数可以捕获一些难以自动提取的人类相似度的概念，当与用户模型相结合时，我们发现每个评估者的口味变化会影响他们对相似度的感知。

测量异构集合中人类感知的相似性

Measuring Human-perceived Similarity in Heterogeneous Collections

Since scenes are composed in part of objects, accurate recognition of scenes
requires knowledge about both scenes and objects. In this paper we address two
related problems: 1) scale induced dataset bias in multi-scale convolutional
neural network (CNN) architectures, and 2) how to combine effectively
scene-centric and object-centric knowledge (i.e. Places and ImageNet) in CNNs.
An earlier attempt, Hybrid-CNN, showed that incorporating ImageNet did not help
much. Here we propose an alternative method taking the scale into account,
resulting in significant recognition gains. By analyzing the response of
ImageNet-CNNs and Places-CNNs at different scales we find that both operate in
different scale ranges, so using the same network for all the scales induces
dataset bias resulting in limited performance. Thus, adapting the feature
extractor to each particular scale (i.e. scale-specific CNNs) is crucial to
improve recognition, since the objects in the scenes have their specific range
of scales. Experimental results show that the recognition accuracy highly
depends on the scale, and that simple yet carefully chosen multi-scale
combinations of ImageNet-CNNs and Places-CNNs, can push the state-of-the-art
recognition accuracy in SUN397 up to 66.26% (and even 70.17% with deeper
architectures, comparable to human performance).

通过分析 ImageNet-CNNs 和 Places-CNNs 在不同尺度上的响应，本文提出了一种基于尺度的深度学习算法，并发现 scale-specific CNN 对于提高物体场景识别的准确性至关重要。实验结果表明，简单而精心选择的 ImageNet-CNN 和 Places-CNN 的多尺度组合可以将 SUN397 的最新识别准确性推至 66.26％（甚至在更深的架构中达到 70.17％，与人类的表现相当）。

使用 CNN 进行场景识别：对象，尺度和数据集偏差

Scene recognition with CNNs: objects, scales and dataset bias

In this paper we introduce the problem of Visual Semantic Role Labeling:
given an image we want to detect people doing actions and localize the objects
of interaction. Classical approaches to action recognition either study the
task of action classification at the image or video clip level or at best
produce a bounding box around the person doing the action. We believe such an
output is inadequate and a complete understanding can only come when we are
able to associate objects in the scene to the different semantic roles of the
action. To enable progress towards this goal, we annotate a dataset of 16K
people instances in 10K images with actions they are doing and associate
objects in the scene with different semantic roles for each action. Finally, we
provide a set of baseline algorithms for this task and analyze error modes
providing directions for future work.

本文介绍了视觉语义角色标注的问题，即在给定图像的情况下，我们希望检测人们进行的动作并定位交互对象，为了实现这个目标，我们注释了一组数据集，并提供了一组基准算法来解决这个问题，并分析了错误模式，为未来的工作提供了方向。