Luis E. Ortiz

Parsing clothing in fashion photographs

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.

Who are you with and where are you going

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.

Correlated equilibria in graphical games

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).

Retrieving Similar Styles to Parse Clothing

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.

Competitive algorithms for VWAP and limit order trading

We introduce new online models for two important aspectsof modern financial markets: Volume Weighted Average Pricetrading and limit order books. We provide an extensivestudy of competitive algorithms in these models and relatethem to earlier online algorithms for stock trading.

Chic or Social: Visual Popularity Analysis in Online Fashion Networks

From Flickr to Facebook to Pinterest, pictures are increasingly becoming a core content type in social networks. But, how important is this visual content and how does it influence behavior in the network? In this paper we study the effects of visual, textual, and social factors on popularity in a large real-world network focused on fashion. We make use of state of the art computer vision techniques for clothing representation, as well as network and text information to predict post popularity in both in-network and out-of-network scenarios. Our experiments find significant statistical evidence that social factors dominate the in-network scenario, but that combinations of content and social factors can be helpful for predicting popularity outside of the network. This in depth study of image popularity in social networks suggests that social factors should be carefully considered for research involving social network photos.

On influence, stable behavior, and the most influential individuals in networks: a game-theoretic approach

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 network influence games as a game-theoretic model of the behavior of a large but finite networked population. In particular, we study an instance we call linear-influence games that allows both positive and negative influence factors, permitting reversals in behavioral choices. We embrace pure-strategy Nash equilibrium, an important solution concept in non-cooperative game theory, to formally define the stable outcomes of a network influence game 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 pure-strategy Nash-equilibria computation. Computationally, we provide (a) complexity characterizations of various problems on linear-influence games; (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 network influence games and real-world settings of general interest, each corresponding to a separate branch of the U.S. Government. Mathematically, we connect linear-influence games to important models in game theory: potential and polymatrix games.

Learning probabilistic models of cellular network traffic with applications to resource management

Given the exponential increase in broadband cellular traffic it is imperative that scalable traffic measurement and monitoring techniques be developed to aid various resource management methods. In this paper, we use a machine learning technique to learn the underlying conditional dependence and independence structure in the base station traffic loads to show how such probabilistic models can be used to reduce the traffic monitoring efforts. The broad goal is to exploit the model to develop a spatial sampling technique that estimates the loads on all the base stations based on actual measurements only on a small subset of base stations. We take special care to develop a sparse model that focuses on capturing only key dependences. Using trace data collected in a network of 400 base stations we show the effectiveness of this approach in reducing the monitoring effort. To understand the tradeoff between the accuracy and monitoring complexity better, we also study the use of this modeling approach on real applications. Two applications are studied - energy saving and opportunistic scheduling. They show that load estimation via such modeling is quite effective in reducing the monitoring burden.

Interdependent Defense Games with Applications to Internet Security at the Level of Autonomous Systems

We propose interdependent defense (IDD) games, a computational game-theoretic framework to study aspects of the interdependence of risk and security in multi-agent systems under deliberate external attacks. Our model builds upon interdependent security (IDS) games, a model by Heal and Kunreuther that considers the source of the risk to be the result of a fixed randomized-strategy. We adapt IDS games to model the attacker’s deliberate behavior. We define the attacker’s pure-strategy space and utility function and derive appropriate cost functions for the defenders. We provide a complete characterization of mixed-strategy Nash equilibria (MSNE), and design a simple polynomial-time algorithm for computing all of them for an important subclass of IDD games. We also show that an efficient algorithm to determine whether some attacker’s strategy can be a part of an MSNE in an instance of IDD games is unlikely to exist. Yet, we provide a dynamic programming (DP) algorithm to compute an approximate MSNE when the graph/network structure of the game is a directed tree with a single source. We also show that the DP algorithm is a fully polynomial-time approximation scheme. In addition, we propose a generator of random instances of IDD games based on the real-world Internet-derived graph at the level of autonomous systems (≈27 K nodes and ≈100 K edges as measured in March 2010 by the DIMES project). We call such games Internet games. We introduce and empirically evaluate two heuristics from the literature on learning-in-games, best-response gradient dynamics (BRGD) and smooth best-response dynamics (SBRD), to compute an approximate MSNE in IDD games with arbitrary graph structures, such as randomly-generated instances of Internet games. In general, preliminary experiments applying our proposed heuristics are promising. Our experiments show that, while BRGD is a useful technique for the case of Internet games up to certain approximation level, SBRD is more efficient and provides better approximations than BRGD. Finally, we discuss several extensions, future work, and open problems.