Abstract

Our goal is to spot words in silent speech videos withoutexplicitly recognizing the spoken words, where the lip mo-tion of the speaker is clearly visible and audio is absent. Ex-isting work in this domain has mainly focused on recogniz-ing a fixed set of words in word-segmented lip videos, whichlimits the applicability of the learned model due to limitedvocabulary and high dependency on the model’s recogni-tion performance.Our contribution is two-fold: 1) we develop a pipelinefor recognition-free retrieval, and show its performanceagainst recognition-based retrieval on a large-scale datasetand another set of out-of-vocabulary words. 2) We intro-duce a query expansion technique using pseudo-relevantfeedback and propose a novel re-ranking method based onmaximizing the correlation between spatio-temporal land-marks of the query and the top retrieval candidates. Ourword spotting method achieves 35% higher mean aver-age precision over recognition-based method on large-scaleLRW dataset. Finally, we demonstrate the application of themethod by word spotting in a popular speech video (“Thegreat dictator” by Charlie Chaplin) where we show that theword retrieval can be used to understand what was spokenperhaps in the silent movies

Abstract

The accuracy of information retrieval systems is often measured using complex loss functions such as the average precision (AP) or the normalized discounted cumulative gain (NDCG). Given a set of positive and negative samples, the parameters of a retrieval system can be estimated by minimizing these loss functions. However, the non-differentiability and non-decomposability of these loss functions does not allow for simple gradient based optimization algorithms. This issue is generally circumvented by either optimizing a structured hinge-loss upper bound to the loss function or by using asymptotic methods like the direct-loss minimization framework. Yet, the high computational complexity of loss-augmented inference, which is necessary for both the frameworks, prohibits its use in large training data sets. To alleviate this deficiency, we present a novel quicksort flavored algorithm for a large class of non-decomposable loss functions. We provide a complete characterization of the loss functions that are amenable to our algorithm, and show that it includes both AP and NDCG based loss functions. Furthermore, we prove that no comparison based algorithm can improve upon the computational complexity of our approach asymptotically. We demonstrate the effectiveness of our approach in the context of optimizing the structured hinge loss upper bound of AP and NDCG loss for learning models for a variety of vision tasks. We show that our approach provides significantly better results than simpler decomposable loss functions, while requiring a comparable training time.

Abstract

With the increase in the number of students enrolled in the university system, regular assessment of student performance has become challenging. This is specially true in case of summative assessments, where one expects the student to write down an answer on paper, rather than selecting a correct answer from multiple choices. In this paper, we present a document image workflow system that helps in scaling the handwritten student assessments in a typical university setting. We argue that this improves the efficiency since the book keeping time as well as physical paper movement is minimized. An electronic workflow can make the anonymization easy, alleviating the fear of biases in many cases. Also, parallel and distributed assessment by multiple instructors is straightforward in an electronic workflow system. At the heart of our solution, we have (i) a distributed image capture module with a mobile phone (ii) image processing algorithms that improve the quality and readability (iii) image annotation module that process the evaluations/feedbacks as a separate layer. Our system also acts as a platform for modern image analysis which can be adapted to the domain of student assessments. This include (i) Handwriting recognition and word spotting [5] (ii) Measure of document similarity [6] (iii) Aesthetic analysis of handwriting [7] (iv) Identity of the writer [4] etc. With the handwriting assessment workflow system, all these recent advances in computer vision can become practical and applicable in evaluating student assessments

Abstract

Deep CNNs for semantic segmentation have high memory and run time requirements. Various approaches have been proposed to make CNNs efficient like grouped, shuffled, depth-wise separable convolutions. We study the effectiveness of these techniques on a real-time semantic segmentation architecture like ERFNet for improving runtime by over 5X. We apply these techniques to CNN layers partially or fully and evaluate the testing accuracies on Cityscapes dataset. We obtain accuracy vs parameters/FLOPs trade offs, giving accuracy scores for models that can run under specified runtime budgets. We further propose a novel training procedure which starts out with a dense convolution but gradually evolves towards a grouped convolution. We show that our proposed training method and efficient architecture design can improve accuracies by over 8% with depthwise separable convolutions applied on the encoder of ERFNet and attaching a light weight decoder. This results in a model which has a 5X improvement in FLOPs while only suffering a 4% degradation in accuracy with respect to ERFNet.

Abstract

Semantic segmentation is a popular task in computer vision today, and deep neural network models have emerged as the popular solution to this problem in recent times. The typical loss function used to train neural networks for this task is the cross-entropy loss. However, the success of the learned models is measured using Intersection-OverUnion (IoU), which is inherently non-differentiable. This gap between performance measure and loss function results in a fall in performance, which has also been studied by few recent efforts. In this work, we propose a novel method to automatically learn a surrogate loss function that approximates the IoU loss and is better suited for good IoU performance. To the best of our knowledge, this is the first such work that attempts to learn a loss function for this purpose. The proposed loss can be directly applied over any network. We validated our method over different networks (FCN, SegNet, UNet) on the PASCAL VOC and Cityscapes datasets. Our results on this work show consistent improvement over baseline methods.

Abstract

In this paper, we improve the performance of the recently proposed Direct Query Classifier (DQC). The (DQC) is a classifier based retrieval method and in general, such methods have been shown to be superior to the OCR-based solutions for performing retrieval in many practical document image datasets. In (DQC), the classifiers are trained for a set of frequent queries and seamlessly extended for the rare and arbitrary queries. This extends the classifier based retrieval paradigm to an unlimited number of classes (words) present in a language. The (DQC) requires indexing cut-portions (n-grams) of the word image and DTW distance has been used for indexing. However, DTW is computationally slow and therefore limits the performance of the (DQC). We introduce query specific DTW distance, which enables effective computation of global principal alignments for novel queries. Since the proposed query specific DTW distance is a linear approximation of the DTW distance, it enhances the performance of the (DQC). Unlike previous approaches, the proposed query specific DTW distance uses both the class mean vectors and the query information for computing the global principal alignments for the query. Since the proposed method computes the global principal alignments using n-grams, it works well for both frequent and rare queries. We also use query expansion (QE) to further improve the performance of our query specific DTW. This also allows us to seamlessly adapt our solution to new fonts, styles and collections. We have demonstrated the utility of the proposed technique over 3 different datasets. The proposed query specific DTW performs well compared to the previous DTW approximations.

Abstract

We present an approach for unsupervised training of CNNs in order to learn discriminative face representations. We mine supervised training data by noting that multiple faces in the same video frame must belong to different persons and the same face tracked across multiple frames must belong to the same person. We obtain millions of face pairs from hundreds of videos without using any manual supervision. Although faces extracted from videos have a lower spatial resolution than those which are available as part of standard supervised face datasets such as LFW and CASIA-WebFace, the former represent a much more realistic setting, e.g. in surveillance scenarios where most of the faces detected are very small. We train our CNNs with the relatively low resolution faces extracted from video frames collected, and achieve a higher verification accuracy on the benchmark LFW dataset cf. hand-crafted features such as LBPs, and even surpasses the performance of state-of-the-art deep networks such as VGG-Face, when they are made to work with low resolution input images.

Abstract

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community. In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN.

Abstract

We consider the task of learning to estimate human pose in still images. In order to avoid the high cost of full supervision, we propose to use a diverse data set, which consists of two types of annotations: (i) a small number of images are labeled using the expensive ground-truth pose; and (ii) other images are labeled using the inexpensive action label. As action information helps narrow down the pose of a human, we argue that this approach can help reduce the cost of training without significantly affecting the accuracy. To demonstrate this we design a probabilistic framework that employs two distributions: (i) a conditional distribution to model the uncertainty over the human pose given the image and the action; and (ii) a prediction distribution, which provides the pose of an image without using any action information. We jointly estimate the parameters of the two aforementioned distributions by minimizing their dissimilarity coefficient, as measured by a task-specific loss function. During both training and testing, we only require an efficient sampling strategy for both the aforementioned distributions. This allows us to use deep probabilistic networks that are capable of providing accurate pose estimates for previously unseen images. Using the MPII data set, we show that our approach outperforms baseline methods that either do not use the diverse annotations or rely on pointwise estimates of the pose.

Abstract

We are motivated by the fact that multiple representations of the environment are required to stand for the changes in appearance with time and for changes that appear in a cyclic manner. These changes are, for example, from day to night time, and from day to day across seasons. In such situations, the robot visits the same routes multiple times and collects different appearances of it. Multiple visual experiences usually find robotic vision applications like visual localization, mapping, place recognition, and autonomous navigation. The novelty in this paper is an algorithm that connects multiple visual experiences via aligning multiple image sequences. This problem is solved by finding the maximum flow in a directed graph flow-network, whose vertices represent the matches between frames in the test and reference sequences. Edges of the graph represent the cost of these matches. The problem of finding the best match is reduced to finding the minimum-cut surface, which is solved as a maximum flow network problem. Application to visual localization is considered in this paper to show the effectiveness of the proposed multiple image sequence alignment method, without loosing its generality. Experimental evaluations show that the precision of sequence matching is improved by considering multiple visual sequences for the same route, and that the method performs favorably against state-of-the-art single representation methods like SeqSLAM and ABLE-M.