Vicente Ordonez

High level describable attributes for predicting aesthetics and interestingness

With the rise in popularity of digital cameras, the amount of visual data available on the web is growing exponentially. Some of these pictures are extremely beautiful and aesthetically pleasing, but the vast majority are uninteresting or of low quality. This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections. Our aesthetic quality estimation method explicitly predicts some of the possible image cues that a human might use to evaluate an image and then uses them in a discriminative approach. These cues or high level describable image attributes fall into three broad types: 1) compositional attributes related to image layout or configuration, 2) content attributes related to the objects or scene types depicted, and 3) sky-illumination attributes related to the natural lighting conditions. We demonstrate that an aesthetics classifier trained on these describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments. We also demonstrate our method for predicting the “interestingness” of Flickr photos, and introduce a novel problem of estimating query specific “interestingness”.

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32\(\times \) memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58\(\times \) faster convolutional operations (in terms of number of the high precision operations) and 32\(\times \) memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a Binary-Weight-Network version of AlexNet is the same as the full-precision AlexNet. We compare our method with recent network binarization methods, BinaryConnect and BinaryNets, and outperform these methods by large margins on ImageNet, more than \(16\,\%\) in top-1 accuracy. Our code is available at: http://allenai.org/plato/xnornet.

BabyTalk: Understanding and Generating Simple Image Descriptions

We present a system to automatically generate natural language descriptions from images. This system consists of two parts. The first part, content planning, smooths the output of computer vision-based detection and recognition algorithms with statistics mined from large pools of visually descriptive text to determine the best content words to use to describe an image. The second step, surface realization, chooses words to construct natural language sentences based on the predicted content and general statistics from natural language. We present multiple approaches for the surface realization step and evaluate each using automatic measures of similarity to human generated reference descriptions. We also collect forced choice human evaluations between descriptions from the proposed generation system and descriptions from competing approaches. The proposed system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work.

ReferItGame: Referring to Objects in Photographs of Natural Scenes

In this paper we introduce a new game to crowd-source natural language referring expressions. By designing a two player game, we can both collect and verify referring expressions directly within the game. To date, the game has produced a dataset containing 130,525 expressions, referring to 96,654 distinct objects, in 19,894 photographs of natural scenes. This dataset is larger and more varied than previous REG datasets and allows us to study referring expressions in real-world scenes. We provide an in depth analysis of the resulting dataset. Based on our findings, we design a new optimization based model for generating referring expressions and perform experimental evaluations on 3 test sets.

Learning High-Level Judgments of Urban Perception

Human observers make a variety of perceptual inferences about pictures of places based on prior knowledge and experience. In this paper we apply computational vision techniques to the task of predicting the perceptual characteristics of places by leveraging recent work on visual features along with a geo-tagged dataset of images associated with crowd-sourced urban perception judgments for wealth, uniqueness, and safety. We perform extensive evaluations of our models, training and testing on images of the same city as well as training and testing on images of different cities to demonstrate generalizability. In addition, we collect a new densely sampled dataset of streetview images for 4 cities and explore joint models to collectively predict perceptual judgments at city scale. Finally, we show that our predictions correlate well with ground truth statistics of wealth and crime.

Predicting Entry-Level Categories

Entry-level categories—the labels people use to name an object—were originally defined and studied by psychologists in the 1970s and 1980s. In this paper we extend these ideas to study entry-level categories at a larger scale and to learn models that can automatically predict entry-level categories for images. Our models combine visual recognition predictions with linguistic resources like WordNet and proxies for word “naturalness” mined from the enormous amount of text on the web. We demonstrate the usefulness of our models for predicting nouns (entry-level words) associated with images by people, and for learning mappings between concepts predicted by existing visual recognition systems and entry-level concepts. In this work we make use of recent successful efforts on convolutional network models for visual recognition by training classifiers for 7404 object categories on ConvNet activation features. Results for category mapping and entry-level category prediction for images show promise for producing more natural human-like labels. We also demonstrate the potential applicability of our results to the task of image description generation.

Large Scale Retrieval and Generation of Image Descriptions

What is the story of an image? What is the relationship between pictures, language, and information we can extract using state of the art computational recognition systems? In an attempt to address both of these questions, we explore methods for retrieving and generating natural language descriptions for images. Ideally, we would like our generated textual descriptions (captions) to both sound like a person wrote them, and also remain true to the image content. To do this we develop data-driven approaches for image description generation, using retrieval-based techniques to gather either: (a) whole captions associated with a visually similar image, or (b) relevant bits of text (phrases) from a large collection of image + description pairs. In the case of (b), we develop optimization algorithms to merge the retrieved phrases into valid natural language sentences. The end result is two simple, but effective, methods for harnessing the power of big data to produce image captions that are altogether more general, relevant, and human-like than previous attempts.

Stating the Obvious: Extracting Visual Common Sense Knowledge

Obtaining common sense knowledge using current information extraction techniques is extremely challenging. In this work, we instead propose to derive simple common sense statements from fully annotated object detection corpora such as the Microsoft Common Objects in Context dataset. We show that many thousands of common sense facts can be extracted from such corpora at high quality. Furthermore, using WordNet and a novel submodular k-coverage formulation, we are able to generalize our initial set of common sense assertions to unseen objects and uncover over 400k potentially useful facts.

Furniture-geek: Understanding fine-grained furniture attributes from freely associated text and tags

As the amount of user generated content on the internet grows, it becomes ever more important to come up with vision systems that learn directly from weakly annotated and noisy data. We leverage a large scale collection of user generated content comprising of images, tags and title/captions of furniture inventory from an e-commerce website to discover and categorize learnable visual attributes. Furniture categories have long been the quintessential example of why computer vision is hard, and we make one of the first attempts to understand them through a large scale weakly annotated dataset. We focus on a handful of furniture categories that are associated with a large number of fine-grained attributes. We propose a set of localized feature representations built on top of state-of-the-art computer vision representations originally designed for fine-grained object categorization. We report a thorough empirical characterization on the visual identifiability of various fine-grained attributes using these representations and show encouraging results on finding iconic images and on multi-attribute prediction.

Commonly Uncommon: Semantic Sparsity in Situation Recognition

Semantic sparsity is a common challenge in structured visual classification problems, when the output space is complex, the vast majority of the possible predictions are rarely, if ever, seen in the training set. This paper studies semantic sparsity in situation recognition, the task of producing structured summaries of what is happening in images, including activities, objects and the roles objects play within the activity. For this problem, we find empirically that most substructures required for prediction are rare, and current state-of-the-art model performance dramatically decreases if even one such rare substructure exists in the target output. We avoid many such errors by (1) introducing a novel tensor composition function that learns to share examples across substructures more effectively and (2) semantically augmenting our training data with automatically gathered examples of rarely observed outputs using web data. When integrated within a complete CRF-based structured prediction model, the tensor-based approach outperforms existing state of the art by a relative improvement of 2.11% and 4.40% on top-5 verb and noun-role accuracy, respectively. Adding 5 million images with our semantic augmentation techniques gives further relative improvements of 6.23% and 9.57% on top-5 verb and noun-role accuracy.