arXiv subjects

Stephen Gould

Publications and source records attributed to Stephen Gould.

At least 109 records · Page 6Linked to original sources

arXiv2019

Representation Learning on Unit Ball with 3D Roto-Translational Equivariance

Convolution is an integral operation that defines how the shape of one function is modified by another function. This powerful concept forms the basis of hierarchical feature learning in deep neural networks. Although performing convolution in Euclidean geometries is fairly straightforward, its extension to other topological spaces---such as a sphere ($\mathbb{S}^2$) or a unit ball ($\mathbb{B}^3$)---entails unique challenges. In this work, we propose a novel `\emph{volumetric convolution}' operation that can effectively model and convolve arbitrary functions in $\mathbb{B}^3$. We develop a theoretical framework for \emph{volumetric convolution} based on Zernike polynomials and efficiently implement it as a differentiable and an easily pluggable layer in deep networks. By construction, our formulation leads to the derivation of a novel formula to measure the symmetry of a function in $\mathbb{B}^3$ around an arbitrary axis, that is useful in function analysis tasks. We demonstrate the efficacy of proposed volumetric convolution operation on one viable use case i.e., 3D object recognition.

cs.CV↗

arXiv2019

Learning to Find Common Objects Across Few Image Collections

Given a collection of bags where each bag is a set of images, our goal is to select one image from each bag such that the selected images are from the same object class. We model the selection as an energy minimization problem with unary and pairwise potential functions. Inspired by recent few-shot learning algorithms, we propose an approach to learn the potential functions directly from the data. Furthermore, we propose a fast greedy inference algorithm for energy minimization. We evaluate our approach on few-shot common object recognition as well as object co-localization tasks. Our experiments show that learning the pairwise and unary terms greatly improves the performance of the model over several well-known methods for these tasks. The proposed greedy optimization algorithm achieves performance comparable to state-of-the-art structured inference algorithms while being ~10 times faster. The code is publicly available on https://github.com/haamoon/finding_common_object.

cs.CV↗

arXiv2019

The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation

Determining the position and orientation of a calibrated camera from a single image with respect to a 3D model is an essential task for many applications. When 2D-3D correspondences can be obtained reliably, perspective-n-point solvers can be used to recover the camera pose. However, without the pose it is non-trivial to find cross-modality correspondences between 2D images and 3D models, particularly when the latter only contains geometric information. Consequently, the problem becomes one of estimating pose and correspondences jointly. Since outliers and local optima are so prevalent, robust objective functions and global search strategies are desirable. Hence, we cast the problem as a 2D-3D mixture model alignment task and propose the first globally-optimal solution to this formulation under the robust $L_2$ distance between mixture distributions. We search the 6D camera pose space using branch-and-bound, which requires novel bounds, to obviate the need for a pose estimate and guarantee global optimality. To accelerate convergence, we integrate local optimization, implement GPU bound computations, and provide an intuitive way to incorporate side information such as semantic labels. The algorithm is evaluated on challenging synthetic and real datasets, outperforming existing approaches and reliably converging to the global optimum.

cs.CV↗

arXiv2018

Partially-Supervised Image Captioning

Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild - for example, as assistants for people with impaired vision - a much larger number and variety of visual concepts must be understood. To address this problem, we teach image captioning models new visual concepts from labeled images and object detection datasets. Since image labels and object classes can be interpreted as partial captions, we formulate this problem as learning from partially-specified sequence data. We then propose a novel algorithm for training sequence models, such as recurrent neural networks, on partially-specified sequences which we represent using finite state automata. In the context of image captioning, our method lifts the restriction that previously required image captioning models to be trained on paired image-sentence corpora only, or otherwise required specialized model architectures to take advantage of alternative data modalities. Applying our approach to an existing neural captioning model, we achieve state of the art results on the novel object captioning task using the COCO dataset. We further show that we can train a captioning model to describe new visual concepts from the Open Images dataset while maintaining competitive COCO evaluation scores.

cs.CV↗

arXiv2018

Second-order Temporal Pooling for Action Recognition

Deep learning models for video-based action recognition usually generate features for short clips (consisting of a few frames); such clip-level features are aggregated to video-level representations by computing statistics on these features. Typically zero-th (max) or the first-order (average) statistics are used. In this paper, we explore the benefits of using second-order statistics. Specifically, we propose a novel end-to-end learnable feature aggregation scheme, dubbed temporal correlation pooling that generates an action descriptor for a video sequence by capturing the similarities between the temporal evolution of clip-level CNN features computed across the video. Such a descriptor, while being computationally cheap, also naturally encodes the co-activations of multiple CNN features, thereby providing a richer characterization of actions than their first-order counterparts. We also propose higher-order extensions of this scheme by computing correlations after embedding the CNN features in a reproducing kernel Hilbert space. We provide experiments on benchmark datasets such as HMDB-51 and UCF-101, fine-grained datasets such as MPII Cooking activities and JHMDB, as well as the recent Kinetics-600. Our results demonstrate the advantages of higher-order pooling schemes that when combined with hand-crafted features (as is standard practice) achieves state-of-the-art accuracy.

cs.CV↗

arXiv2018

Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments

A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have made incredible progress in closely related areas. This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering. Both tasks can be interpreted as visually grounded sequence-to-sequence translation problems, and many of the same methods are applicable. To enable and encourage the application of vision and language methods to the problem of interpreting visually-grounded navigation instructions, we present the Matterport3D Simulator -- a large-scale reinforcement learning environment based on real imagery. Using this simulator, which can in future support a range of embodied vision and language tasks, we provide the first benchmark dataset for visually-grounded natural language navigation in real buildings -- the Room-to-Room (R2R) dataset.

cs.CV↗

arXiv2018

Video Representation Learning Using Discriminative Pooling

Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the underlying action---indeed, many are common across multiple actions---pooling schemes that impose equal importance on all frames might be unfavorable. In an attempt to tackle this problem, we propose discriminative pooling, based on the notion that among the deep features generated on all short clips, there is at least one that characterizes the action. To this end, we learn a (nonlinear) hyperplane that separates this unknown, yet discriminative, feature from the rest. Applying multiple instance learning in a large-margin setup, we use the parameters of this separating hyperplane as a descriptor for the full video segment. Since these parameters are directly related to the support vectors in a max-margin framework, they serve as robust representations for pooling of the features. We formulate a joint objective and an efficient solver that learns these hyperplanes per video and the corresponding action classifiers over the hyperplanes. Our pooling scheme is end-to-end trainable within a deep framework. We report results from experiments on three benchmark datasets spanning a variety of challenges and demonstrate state-of-the-art performance across these tasks.

cs.CV↗

arXiv2018

Non-Linear Temporal Subspace Representations for Activity Recognition

Representations that can compactly and effectively capture the temporal evolution of semantic content are important to computer vision and machine learning algorithms that operate on multi-variate time-series data. We investigate such representations motivated by the task of human action recognition. Here each data instance is encoded by a multivariate feature (such as via a deep CNN) where action dynamics are characterized by their variations in time. As these features are often non-linear, we propose a novel pooling method, kernelized rank pooling, that represents a given sequence compactly as the pre-image of the parameters of a hyperplane in a reproducing kernel Hilbert space, projections of data onto which captures their temporal order. We develop this idea further and show that such a pooling scheme can be cast as an order-constrained kernelized PCA objective. We then propose to use the parameters of a kernelized low-rank feature subspace as the representation of the sequences. We cast our formulation as an optimization problem on generalized Grassmann manifolds and then solve it efficiently using Riemannian optimization techniques. We present experiments on several action recognition datasets using diverse feature modalities and demonstrate state-of-the-art results.

cs.CV↗

arXiv2018

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.

cs.CV↗

arXiv2018

Neural Algebra of Classifiers

The world is fundamentally compositional, so it is natural to think of visual recognition as the recognition of basic visually primitives that are composed according to well-defined rules. This strategy allows us to recognize unseen complex concepts from simple visual primitives. However, the current trend in visual recognition follows a data greedy approach where huge amounts of data are required to learn models for any desired visual concept. In this paper, we build on the compositionality principle and develop an "algebra" to compose classifiers for complex visual concepts. To this end, we learn neural network modules to perform boolean algebra operations on simple visual classifiers. Since these modules form a complete functional set, a classifier for any complex visual concept defined as a boolean expression of primitives can be obtained by recursively applying the learned modules, even if we do not have a single training sample. As our experiments show, using such a framework, we can compose classifiers for complex visual concepts outperforming standard baselines on two well-known visual recognition benchmarks. Finally, we present a qualitative analysis of our method and its properties.

cs.CV↗

arXiv2017

Human Action Forecasting by Learning Task Grammars

For effective human-robot interaction, it is important that a robotic assistant can forecast the next action a human will consider in a given task. Unfortunately, real-world tasks are often very long, complex, and repetitive; as a result forecasting is not trivial. In this paper, we propose a novel deep recurrent architecture that takes as input features from a two-stream Residual action recognition framework, and learns to estimate the progress of human activities from video sequences -- this surrogate progress estimation task implicitly learns a temporal task grammar with respect to which activities can be localized and forecasted. To learn the task grammar, we propose a stacked LSTM based multi-granularity progress estimation framework that uses a novel cumulative Euclidean loss as objective. To demonstrate the effectiveness of our proposed architecture, we showcase experiments on two challenging robotic assistive tasks, namely (i) assembling an Ikea table from its constituents, and (ii) changing the tires of a car. Our results demonstrate that learning task grammars offers highly discriminative cues improving the forecasting accuracy by more than 9% over the baseline two-stream forecasting model, while also outperforming other competitive schemes.

cs.CV↗

arXiv2017

Human Pose Forecasting via Deep Markov Models

Human pose forecasting is an important problem in computer vision with applications to human-robot interaction, visual surveillance, and autonomous driving. Usually, forecasting algorithms use 3D skeleton sequences and are trained to forecast for a few milliseconds into the future. Long-range forecasting is challenging due to the difficulty of estimating how long a person continues an activity. To this end, our contributions are threefold: (i) we propose a generative framework for poses using variational autoencoders based on Deep Markov Models (DMMs); (ii) we evaluate our pose forecasts using a pose-based action classifier, which we argue better reflects the subjective quality of pose forecasts than distance in coordinate space; (iii) last, for evaluation of the new model, we introduce a 480,000-frame video dataset called Ikea Furniture Assembly (Ikea FA), which depicts humans repeatedly assembling and disassembling furniture. We demonstrate promising results for our approach on both Ikea FA and the existing NTU RGB+D dataset.

cs.CV↗

arXiv2017

Generalized Rank Pooling for Activity Recognition

Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity. Usually, this pooling step discards the temporal order of the frames, which could otherwise be used for better recognition. Towards this end, we propose a novel pooling method, generalized rank pooling (GRP), that takes as input, features from the intermediate layers of a CNN that is trained on tiny sub-sequences, and produces as output the parameters of a subspace which (i) provides a low-rank approximation to the features and (ii) preserves their temporal order. We propose to use these parameters as a compact representation for the video sequence, which is then used in a classification setup. We formulate an objective for computing this subspace as a Riemannian optimization problem on the Grassmann manifold, and propose an efficient conjugate gradient scheme for solving it. Experiments on several activity recognition datasets show that our scheme leads to state-of-the-art performance.

cs.CV↗

arXiv2017

Guided Open Vocabulary Image Captioning with Constrained Beam Search

Existing image captioning models do not generalize well to out-of-domain images containing novel scenes or objects. This limitation severely hinders the use of these models in real world applications dealing with images in the wild. We address this problem using a flexible approach that enables existing deep captioning architectures to take advantage of image taggers at test time, without re-training. Our method uses constrained beam search to force the inclusion of selected tag words in the output, and fixed, pretrained word embeddings to facilitate vocabulary expansion to previously unseen tag words. Using this approach we achieve state of the art results for out-of-domain captioning on MSCOCO (and improved results for in-domain captioning). Perhaps surprisingly, our results significantly outperform approaches that incorporate the same tag predictions into the learning algorithm. We also show that we can significantly improve the quality of generated ImageNet captions by leveraging ground-truth labels.

cs.CV↗

arXiv2017

Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a novel method to extract accurate masks from networks pre-trained for the task of object recognition, thus forgoing external objectness modules. We first show how foreground/background masks can be obtained from the activations of higher-level convolutional layers of a network. We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network. Our experiments evidence that exploiting these masks in conjunction with a weakly-supervised training loss yields state-of-the-art tag-based weakly-supervised semantic segmentation results.

cs.CV↗

arXiv2017

Discriminatively Learned Hierarchical Rank Pooling Networks

In this work, we present novel temporal encoding methods for action and activity classification by extending the unsupervised rank pooling temporal encoding method in two ways. First, we present "discriminative rank pooling" in which the shared weights of our video representation and the parameters of the action classifiers are estimated jointly for a given training dataset of labelled vector sequences using a bilevel optimization formulation of the learning problem. When the frame level features vectors are obtained from a convolutional neural network (CNN), we rank pool the network activations and jointly estimate all parameters of the model, including CNN filters and fully-connected weights, in an end-to-end manner which we coined as "end-to-end trainable rank pooled CNN". Importantly, this model can make use of any existing convolutional neural network architecture (e.g., AlexNet or VGG) without modification or introduction of additional parameters. Then, we extend rank pooling to a high capacity video representation, called "hierarchical rank pooling". Hierarchical rank pooling consists of a network of rank pooling functions, which encode temporal semantics over arbitrary long video clips based on rich frame level features. By stacking non-linear feature functions and temporal sub-sequence encoders one on top of the other, we build a high capacity encoding network of the dynamic behaviour of the video. The resulting video representation is a fixed-length feature vector describing the entire video clip that can be used as input to standard machine learning classifiers. We demonstrate our approach on the task of action and activity recognition. Obtained results are comparable to state-of-the-art methods on three important activity recognition benchmarks with classification performance of 76.7% mAP on Hollywood2, 69.4% on HMDB51, and 93.6% on UCF101.

cs.CV↗

arXiv2017

Unsupervised Human Action Detection by Action Matching

We propose a new task of unsupervised action detection by action matching. Given two long videos, the objective is to temporally detect all pairs of matching video segments. A pair of video segments are matched if they share the same human action. The task is category independent---it does not matter what action is being performed---and no supervision is used to discover such video segments. Unsupervised action detection by action matching allows us to align videos in a meaningful manner. As such, it can be used to discover new action categories or as an action proposal technique within, say, an action detection pipeline. Moreover, it is a useful pre-processing step for generating video highlights, e.g., from sports videos. We present an effective and efficient method for unsupervised action detection. We use an unsupervised temporal encoding method and exploit the temporal consistency in human actions to obtain candidate action segments. We evaluate our method on this challenging task using three activity recognition benchmarks, namely, the MPII Cooking activities dataset, the THUMOS15 action detection benchmark and a new dataset called the IKEA dataset. On the MPII Cooking dataset we detect action segments with a precision of 21.6% and recall of 11.7% over 946 long video pairs and over 5000 ground truth action segments. Similarly, on THUMOS dataset we obtain 18.4% precision and 25.1% recall over 5094 ground truth action segment pairs.

cs.CV↗

arXiv2017

DeepPermNet: Visual Permutation Learning

We present a principled approach to uncover the structure of visual data by solving a novel deep learning task coined visual permutation learning. The goal of this task is to find the permutation that recovers the structure of data from shuffled versions of it. In the case of natural images, this task boils down to recovering the original image from patches shuffled by an unknown permutation matrix. Unfortunately, permutation matrices are discrete, thereby posing difficulties for gradient-based methods. To this end, we resort to a continuous approximation of these matrices using doubly-stochastic matrices which we generate from standard CNN predictions using Sinkhorn iterations. Unrolling these iterations in a Sinkhorn network layer, we propose DeepPermNet, an end-to-end CNN model for this task. The utility of DeepPermNet is demonstrated on two challenging computer vision problems, namely, (i) relative attributes learning and (ii) self-supervised representation learning. Our results show state-of-the-art performance on the Public Figures and OSR benchmarks for (i) and on the classification and segmentation tasks on the PASCAL VOC dataset for (ii).

cs.CV↗