In this paper we demonstrate an effective method for parsing clothing in fashion photographs, an extremely challenging problem due to the large number of possible garment items, variations in configuration, garment appearance, layering, and occlusion. In addition, we provide a large novel dataset and tools for labeling garment items, to enable future research on clothing estimation. Finally, we present intriguing initial results on using clothing estimates to improve pose identification, and demonstrate a prototype application for pose-independent visual garment retrieval.

We propose an agent-based behavioral model of pedestrians to improve tracking performance in realistic scenarios. In this model, we view pedestrians as decision-making agents who consider a plethora of personal, social, and environmental factors to decide where to go next. We formulate prediction of pedestrian behavior as an energy minimization on this model. Two of our main contributions are simple, yet effective estimates of pedestrian destination and social relationships (groups). Our final contribution is to incorporate these hidden properties into an energy formulation that results in accurate behavioral prediction. We evaluate both our estimates of destination and grouping, as well as our accuracy at prediction and tracking against state of the art behavioral model and show improvements, especially in the challenging observational situation of infrequent appearance observations -something that might occur in thousands of webcams available on the Internet.

Abstract-Clothing recognition is a societally and commercially important yet extremely challenging problem due to large variations in clothing appearance, layering, style, and body shape and pose. In this paper, we tackle the clothing parsing problem using a retrieval-based approach. For a query image, we find similar styles from a large database of tagged fashion images and use these examples to recognize clothing items in the query. Our approach combines parsing from: pre-trained global clothing models, local clothing models learned on the fly from retrieved examples, and transferred parse-masks (Paper Doll item transfer) from retrieved examples. We evaluate our approach extensively and show significant improvements over previous state-of-the-art for both localization (clothing parsing given weak supervision in the form of tags) and detection (general clothing parsing). Our experimental results also indicate that the general pose estimation problem can benefit from clothing parsing.

We examine correlated equilibria in the recently introduced formalism of graphical games, a succinct representation for multiplayer games. We establish a natural and powerful relationship between the graphical structure of a multiplayer game and a certain Markov network representing distributions over joint actions. Our first main result establishes that this Markov network succinctly represents all correlated equilibria of the graphical game up to expected payoff equivalence. Our second main result provides a general algorithm for computing correlated equilibria in a graphical game based on its associated Markov network. For a special class of graphical games that includes trees, this algorithm runs in time polynomial in the graphical game representation (which is polynomial in the number of players and exponential in the graph degree).

No abstract

The ZED camera is binocular vision system that can be used to provide a 3D perception of the world. It can be applied in autonomous robot navigation, virtual reality, tracking, motion analysis and so on. This paper proposes a mathematical error model for depth data estimated by the ZED camera with its several resolutions of operation. For doing that, the ZED is attached to a Nvidia Jetson TK1 board providing an embedded system that is used for processing raw data acquired by ZED from a 3D checkerboard. Corners are extracted from the checkerboard using RGB data, and a 3D reconstruction is done for these points using disparity data calculated from the ZED camera, coming up with a partially ordered, and regularly distributed (in 3D space) point cloud of corners with given coordinates, which are computed by the device software. These corners also have their ideal world (3D) positions known with respect to the coordinate frame origin that is empirically set in the pattern. Both given (computed)  coordinates from the camera’s data and known (ideal) coordinates of a corner can, thus, be compared for estimating the error between the given and ideal point locations of the detected corner cloud. Subsequently, using a curve fitting technique, we obtain the equations that model the RMS (Root Mean Square) error. This procedure is repeated for several resolutions of the ZED sensor, and at several distances. Results showed its best effectiveness with a maximum distance of approximately sixteen meters, in real time, which allows its use in robotic or other online applications.

No abstract

We introduce a new approach to the study of influence in strategic settings where the action of an individual depends on that of others in a network-structured way. We propose influence games (IGs) as a game-theoretic (GT) model of the behavior of a large but finite networked population. IGs allow both positive and negative influence factors, permitting reversals in behavioral choices. We embrace pure-strategy Nash equilibrium (PSNE), an important solution concept in non-cooperative game theory, to formally define the stable outcomes of an IG and to predict potential outcomes without explicitly considering intricate dynamics. We address an important problem in network influence, the identification of the most influential individuals, and approach it algorithmically using PSNE computation. Computationally, we provide (a) complexity characterizations of various problems on IGs; (b) efficient algorithms for several special cases and heuristics for hard cases; and (c) approximation algorithms, with provable guarantees, for the problem of identifying the most influential individuals. Experimentally, we evaluate our approach using both synthetic IGs and real-world settings of general interest, each corresponding to a separate branch of the U.S. Government. Mathematically, we connect IGs to important GT models: potential and polymatrix games.