arXiv subjects

Basura Fernando

Publications and source records attributed to Basura Fernando.

At least 73 records · Page 4Linked to original sources

arXiv2017

Encouraging LSTMs to Anticipate Actions Very Early

In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos. As such, it is therefore key to the success of computer vision applications requiring to react as early as possible, such as autonomous navigation. In this paper, we propose a new action anticipation method that achieves high prediction accuracy even in the presence of a very small percentage of a video sequence. To this end, we develop a multi-stage LSTM architecture that leverages context-aware and action-aware features, and introduce a novel loss function that encourages the model to predict the correct class as early as possible. Our experiments on standard benchmark datasets evidence the benefits of our approach; We outperform the state-of-the-art action anticipation methods for early prediction by a relative increase in accuracy of 22.0% on JHMDB-21, 14.0% on UT-Interaction and 49.9% on UCF-101.

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

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↗

arXiv2017

Self-Supervised Video Representation Learning With Odd-One-Out Networks

We propose a new self-supervised CNN pre-training technique based on a novel auxiliary task called "odd-one-out learning". In this task, the machine is asked to identify the unrelated or odd element from a set of otherwise related elements. We apply this technique to self-supervised video representation learning where we sample subsequences from videos and ask the network to learn to predict the odd video subsequence. The odd video subsequence is sampled such that it has wrong temporal order of frames while the even ones have the correct temporal order. Therefore, to generate a odd-one-out question no manual annotation is required. Our learning machine is implemented as multi-stream convolutional neural network, which is learned end-to-end. Using odd-one-out networks, we learn temporal representations for videos that generalizes to other related tasks such as action recognition. On action classification, our method obtains 60.3\% on the UCF101 dataset using only UCF101 data for training which is approximately 10% better than current state-of-the-art self-supervised learning methods. Similarly, on HMDB51 dataset we outperform self-supervised state-of-the art methods by 12.7% on action classification task.

cs.CV↗

arXiv2017

Deep Learning for Automated Quality Assessment of Color Fundus Images in Diabetic Retinopathy Screening

Purpose To develop a computer based method for the automated assessment of image quality in the context of diabetic retinopathy (DR) to guide the photographer. Methods A deep learning framework was trained to grade the images automatically. A large representative set of 7000 color fundus images were used for the experiment which were obtained from the EyePACS that were made available by the California Healthcare Foundation. Three retinal image analysis experts were employed to categorize these images into Accept and Reject classes based on the precise definition of image quality in the context of DR. A deep learning framework was trained using 3428 images. Results A total of 3572 images were used for the evaluation of the proposed method. The method shows an accuracy of 100% to successfully categorise Accept and Reject images. Conclusion Image quality is an essential prerequisite for the grading of DR. In this paper we have proposed a deep learning based automated image quality assessment method in the context of DR. The method can be easily incorporated with the fundus image capturing system and thus can guide the photographer whether a recapture is necessary or not.

cs.CV↗

arXiv2016

Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation

Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and those that aim at focusing on the regions where the action occurs. While the former may suffer from the fact that context is not always reliable, the latter completely ignore this source of information, which can nonetheless be helpful in many situations. In this paper, we aim at making the best of both worlds by developing an approach that leverages both context-aware and action-aware features. At the core of our method lies a novel multi-stage recurrent architecture that allows us to effectively combine these two sources of information throughout a video. This architecture first exploits the global, context-aware features, and merges the resulting representation with the localized, action-aware ones. Our experiments on standard datasets evidence the benefits of our approach over methods that use each information type separately. We outperform the state-of-the-art methods that, as us, rely only on RGB frames as input for both action recognition and anticipation.

cs.CV↗

arXiv2016

Generalized BackPropagation, Étude De Cas: Orthogonality

This paper introduces an extension of the backpropagation algorithm that enables us to have layers with constrained weights in a deep network. In particular, we make use of the Riemannian geometry and optimization techniques on matrix manifolds to step outside of normal practice in training deep networks, equipping the network with structures such as orthogonality or positive definiteness. Based on our development, we make another contribution by introducing the Stiefel layer, a layer with orthogonal weights. Among various applications, Stiefel layers can be used to design orthogonal filter banks, perform dimensionality reduction and feature extraction. We demonstrate the benefits of having orthogonality in deep networks through a broad set of experiments, ranging from unsupervised feature learning to fine-grained image classification.

cs.CV↗

arXiv2016

SPICE: Semantic Propositional Image Caption Evaluation

There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor sufficient for the task of simulating human judgment. We hypothesize that semantic propositional content is an important component of human caption evaluation, and propose a new automated caption evaluation metric defined over scene graphs coined SPICE. Extensive evaluations across a range of models and datasets indicate that SPICE captures human judgments over model-generated captions better than other automatic metrics (e.g., system-level correlation of 0.88 with human judgments on the MS COCO dataset, versus 0.43 for CIDEr and 0.53 for METEOR). Furthermore, SPICE can answer questions such as `which caption-generator best understands colors?' and `can caption-generators count?'

cs.CV↗

arXiv2016

On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization

Some recent works in machine learning and computer vision involve the solution of a bi-level optimization problem. Here the solution of a parameterized lower-level problem binds variables that appear in the objective of an upper-level problem. The lower-level problem typically appears as an argmin or argmax optimization problem. Many techniques have been proposed to solve bi-level optimization problems, including gradient descent, which is popular with current end-to-end learning approaches. In this technical report we collect some results on differentiating argmin and argmax optimization problems with and without constraints and provide some insightful motivating examples.

cs.CV↗

arXiv2016

Rank Pooling for Action Recognition

We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to the video data can serve as a robust new video representation. As a specific example, we learn a pooling function via ranking machines. By learning to rank the frame-level features of a video in chronological order, we obtain a new representation that captures the video-wide temporal dynamics of a video, suitable for action recognition. Other than ranking functions, we explore different parametric models that could also explain the temporal changes in videos. The proposed functional pooling methods, and rank pooling in particular, is easy to interpret and implement, fast to compute and effective in recognizing a wide variety of actions. We evaluate our method on various benchmarks for generic action, fine-grained action and gesture recognition. Results show that rank pooling brings an absolute improvement of 7-10 average pooling baseline. At the same time, rank pooling is compatible with and complementary to several appearance and local motion based methods and features, such as improved trajectories and deep learning features.

cs.CV↗

arXiv2015

MidRank: Learning to rank based on subsequences

We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences. Most often in the supervised learning to rank literature, ranking is approached either by analyzing pairs of images or by optimizing a list-wise surrogate loss function on full sequences. In this work we propose MidRank, which learns from moderately sized sub-sequences instead. These sub-sequences contain useful structural ranking information that leads to better learnability during training and better generalization during testing. By exploiting sub-sequences, the proposed MidRank improves ranking accuracy considerably on an extensive array of image ranking applications and datasets.

cs.CV↗

arXiv2015

Guiding Long-Short Term Memory for Image Caption Generation

In this work we focus on the problem of image caption generation. We propose an extension of the long short term memory (LSTM) model, which we coin gLSTM for short. In particular, we add semantic information extracted from the image as extra input to each unit of the LSTM block, with the aim of guiding the model towards solutions that are more tightly coupled to the image content. Additionally, we explore different length normalization strategies for beam search in order to prevent from favoring short sentences. On various benchmark datasets such as Flickr8K, Flickr30K and MS COCO, we obtain results that are on par with or even outperform the current state-of-the-art.

cs.CV↗

arXiv2015

Location Recognition Over Large Time Lags

Would it be possible to automatically associate ancient pictures to modern ones and create fancy cultural heritage city maps? We introduce here the task of recognizing the location depicted in an old photo given modern annotated images collected from the Internet. We present an extensive analysis on different features, looking for the most discriminative and most robust to the image variability induced by large time lags. Moreover, we show that the described task benefits from domain adaptation.

cs.CV↗

arXiv2015

Object Class Detection and Classification using Multi Scale Gradient and Corner Point based Shape Descriptors

This paper presents a novel multi scale gradient and a corner point based shape descriptors. The novel multi scale gradient based shape descriptor is combined with generic Fourier descriptors to extract contour and region based shape information. Shape information based object class detection and classification technique with a random forest classifier has been optimized. Proposed integrated descriptor in this paper is robust to rotation, scale, translation, affine deformations, noisy contours and noisy shapes. The new corner point based interpolated shape descriptor has been exploited for fast object detection and classification with higher accuracy.

cs.CV↗

arXiv2015

Joint cross-domain classification and subspace learning for unsupervised adaptation

Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain. Several approaches have beenproposed for classification tasks in the unsupervised scenario, where no labeled target data are available. Most of the attention has been dedicated to searching a new domain-invariant representation, leaving the definition of the prediction function to a second stage. Here we propose to learn both jointly. Specifically we learn the source subspace that best matches the target subspace while at the same time minimizing a regularized misclassification loss. We provide an alternating optimization technique based on stochastic sub-gradient descent to solve the learning problem and we demonstrate its performance on several domain adaptation tasks.

cs.CV↗