Abstract

t Automatic image annotation is one of the fundamental problems in computer vision and machine learning. Given an image, here the goal is to predict a set of textual labels that describe the semantics of that image. During the last decade, a large number of image annotation techniques have been proposed that have been shown to achieve encouragingresults on various annotation datasets. However, their scope has mostly remained restricted to quantitative results on the test data, thus ignoring various key aspects related to dataset properties and evaluation metrics that inherently affect the performance to a considerable extent. In this paper, first we evaluate ten state-of-the-art (both deep-learning based as well as non-deep-learning based) approaches for image annotation using the same baseline CNN features. Then we propose new quantitative measures to examine various issues/aspects in the image annotation domain, such as dataset specific biases, per-label versus per-image evaluation criteria, and the impact of changing the number and type of predicted labels. We believe the conclusions derived in this paper through thorough empirical analyzes would be helpful in making systematic advancements in this domain.

Abstract

In a world of proliferating data, the ability to rapidly summarize text is growing in importance. Automatic summarization of text can be thought of as a sequence to sequence problem. Another area of natural language processing that solves a sequence to sequence problem is machine translation, which is rapidly evolving due to the development of attentionbased encoder-decoder networks. This work applies these modern techniques to abstractive summarization. We perform analysis on various attention mechanisms for summarization with the goal of developing an approach and architecture aimed at improving the state of the art. In particular, we modify and optimize a translation model with self-attention for generating abstractive sentence summaries. The effectiveness of this base model along with attention variants is compared and analyzed in the context of standardized evaluation sets and test metrics. However, we show that these metrics are limited in their ability to effectively score abstractive summaries, and propose a new approach based on the intuition that an abstractive model requires an abstractive evaluation.

Abstract

View-graph selection is a crucial step for accurate and efficient large-scale structure from motion (sfm). Most sfm methods remove undesirable images and pairs using several fixed heuristic criteria, and propose tailor-made solutions to achieve specific reconstruction objectives such as efficiency, accuracy, or disambiguation. In contrast to these disparate solutions, we propose an optimization based formulation that can be used to achieve these different reconstruction objectives with taskspecific cost modeling and construct a very efficient network-flow based formulation for its approximate solution. The abstraction brought on by this selection mechanism separates the challenges specific to datasets and reconstruction objectives from the standard sfm pipeline and improves its generalization. This paper mainly focuses on application of this framework with standard sfm pipeline for accurate and ghost-free reconstructions of highly ambiguous datasets. To model selection costs for this task, we introduce new disambiguation priors based on local geometry. We further demonstrate versatility of the method by using it for the general objective of accurate and efficient reconstruction of largescale Internet datasets using costs based on well-known sfm priors.

Abstract

Post-capture control of the focus position of an image is a useful photographic tool. Changing the focus of a single image involves the complex task of simultaneously estimating the radiance and the defocus radius of all scene points. We introduce RefocusGAN, a deblurthen-reblur approach to single image refocusing. We train conditional adversarial networks for deblurring and refocusing using wide-aperture images created from light-fields. By appropriately conditioning our networks with a focus measure, an in-focus image and a refocus control parameter δ, we are able to achieve generic free-form refocusing over a single image.

Abstract

Replacing overexposed or dull skies in outdoor photographs is a desirable photo manipulation. It is often necessary to color correct the foreground after replacement to make it consistent with the new sky. Methods have been proposed to automate the process of sky replacement and color correction. However, many times a color correction is unwanted by the artist or may produce unrealistic results. We propose a data-driven approach to sky-replacement that avoids color correction by finding a diverse set of skies that are consistent in color and natural illumination with the query image foreground. Our database consists of ∼ 1200 natural images spanning many outdoor categories. Given a query image, we retrieve the most consistent images from the database according to L2 similarity in feature space and produce candidate composites. The candidates are re-ranked based on realism and diversity. We used pre-trained CNN features and a rich set of hand-crafted features that encode color statistics, structural layout, and natural illumination statistics, but observed color statistics to be the most effective for this task. We share our findings on feature selection and show qualitative results and a user-study based evaluation to show the effectiveness of the proposed method.

Abstract

Human body tracking typically requires specialized capture set-ups. Although pose tracking is available in consumer devices like Microsoft Kinect, it is restricted to stick figures visualizing body part detection. In this paper, we propose a method for full 3D human body shape and motion capture of arbitrary movements from the depth channel of a single Kinect, when the subject wears casual clothes. We do not use the RGB channel or an initialization procedure that requires the subject to move around in front of the camera. This makes our method applicable for arbitrary clothing textures and lighting environments, with minimal subject intervention. Our method consists of 3D surface feature detection and articulated motion tracking, which is regularized by a statistical human body model [26]. We also propose the idea of a Consensus Mesh (CMesh) which is the 3D template of a person created from a single view point. We demonstrate tracking results on challenging poses and argue that using CMesh along with statistical body models can improve tracking accuracies. Quantitative evaluation of our dense body tracking shows that our method has very little drift which is improved by the usage of CMesh.

Abstract

Human actions comprise of joint motion of articulated body parts or “gestures”. Human skeleton is intuitively represented as a sparse graph with joints as nodes and natural connections between them as edges. Graph convolutional networks have been used to recognize actions from skeletal videos. We introduce a part-based graph convolutional network (PB-GCN) for this task, inspired by Deformable Part-based Models (DPMs). We divide the skeleton graph into four subgraphs with joints shared across them and learn a recognition model using a part-based graph convolutional network. We show that such a model improves performance of recognition, compared to a model using entire skeleton graph. Instead of using 3D joint coordinates as node features, we show that using relative coordinates and temporal displacements boosts performance. Our model achieves state-of-the-art performance on two challenging benchmark datasets NTURGB+D and HDM05, for skeletal action recognition.

Abstract

A light field is a 4D function which captures all the radiance information of a scene. Image-based creation of light fields reconstructs the 4D space using pre-captured imagery from various views and employs refocusing to generate output images. Handheld cameras can also capture light fields using a microlens array between the sensor and the main lens, but physical constraints limit their spatial and angular resolutions. In this paper, we present a GPU based synthetic light field rendering framework that is robust and physically accurate. We demonstrate the equivalence of the standard light field camera representation with light slab representation for synthetic light fields and exhibit the capability of our framework to trace light fields of resolutions much higher than available in commercial plenoptic cameras. The light slab is rich in quality but bulky to store. Our system provides parameters to balance the quality and storage requirements. We also present a compact representation of the 4D light slabs using a video compression codec and demonstrate different quality-size combinations using these representations.

Abstract

The ability of machine-based agents to play games in human-like fashion is considered a benchmark of progress in AI. In this paper, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, an elementary version of Visual Question Answering task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketch stroke sequences as visual data. Notably, Sketch-QA involves asking a fixed question (" What object is being drawn?") and gathering open-ended guess-words from human guessers. To mimic Pictionary-style guessing, we propose a deep neural model which generates guess-words in response to temporally evolving human-drawn sketches. Our model even makes human-like mistakes while guessing, thus amplifying the human mimicry factor. We evaluate our model on the large-scale guess-word dataset generated via Sketch-QA task and compare with various baselines. We also conduct a Visual Turing Test to obtain human impressions of the guess-words generated by humans and our model. Experimental results demonstrate the promise of our approach for Pictionary and similarly themed games.

Abstract

Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based selection. However, classical re-id approaches generate per-camera lists independently. Therefore, target identifications by operator in a subset of cameras cannot be utilized to improve ranking of the target in remaining set of network cameras. To address this shortcoming, we propose a novel sequential multi-camera re-id approach. The proposed approach can accommodate human operator inputs and provides early gains via a monotonic improvement in target ranking. At the heart of our approach is a fusion function which operates on deep feature representations of query and candidate matches. We formulate an optimization procedure custom-designed to incrementally improve query representation. Since existing evaluation methods cannot be directly adopted to our setting, we also propose two novel evaluation protocols. The results on two large-scale re-id datasets (Market-1501, DukeMTMC-reID) demonstrate that our multi-camera method significantly outperforms baselines and other popular feature fusion schemes. Additionally, we conduct a comparative subject-based study of human operator performance. The superior operator performance enabled by our approach makes a compelling case for its integration into deployable video-surveillance systems.