Abstract

Visual place recognition on low memory devices such as mobile phones and robotics systems is a challenging problem. The state of the art models for this task uses deep learning architectures having close to 100 million parameters which takes over 400MB of memory. This makes these models infeasible to be deployed in low memory devices and gives rise to the need of compressing them. Hence we study the effectiveness of model compression techniques like trained quantization and pruning for reducing the number of parameters on one of the best performing image retrieval models called NetVLAD. We show that a compressed network can be created by starting with a model pre-trained for the task of visual place recognition and then fine-tuning it via trained pruning and quantization. The compressed model is able to produce the same mAP as the original uncompressed network. We achieve almost 50% parameter pruning with no loss in mAP and 70% pruning with close to 2% mAP reduction, while also performing 8-bit quantization. Furthermore, together with 5-bit quantization, we perform about 50% parameter reduction by pruning and get only about 3% reduction in mAP. The resulting compressed networks have sizes of around 30MB and 65MB which makes them easily usable in memory constrained devices.

Abstract

Building robust text recognition systems for languages with cursive scripts like Urdu has always been challenging. Intricacies of the script and the absence of ample annotated data further act as adversaries to this task. We demonstrate the effectiveness of an end-to-end trainable hybrid CNN-RNN architecture in recognizing Urdu text from printed documents, typically known as Urdu OCR. The solution proposed is not bounded by any language specific lexicon with the model following a segmentation-free, sequence-tosequence transcription approach. The network transcribes a sequence of convolutional features from an input image to a sequence of target labels. This discards the need to segment the input image into its constituent characters/glyphs, which is often arduous for scripts like Urdu. Furthermore, past and future contexts modelled by bidirectional recurrent layers aids the transcription. We outperform …

Abstract

This paper proposes a method for detecting plagiarism in source-codes using deep features. The embeddings for programs are obtained using a character-level Recurrent Neural Network (char-RNN), which is pre-trained on Linux Kernel source-code. Many popular plagiarism detection tools are based on n-gram techniques at syntactic level. However, these approaches to plagiarism detection fail to capture long term dependencies (non-contiguous interaction) present in the source-code. Contrarily, the proposed deep features capture non-contiguous interaction within n-grams. These are generic in nature and there is no need to fine-tune the char-RNN model again to program submissions from each individual problem-set. Our experiments show the effectiveness of deep features in the task of classifying assignment program submissions as copy, partial-copy and non-copy. Comparing our proposed features with …

Abstract

While the problem of detecting generic objects in natural scene images has been the subject of research for a long time, the problem of detection of small objects has been largely ignored. While generic object detectors perform well on medium and large sized objects, they perform poorly for the overall task of recognition of small objects. This is because of the low resolution and simple shape of most small objects. In this work, we suggest a simple yet effective upsampling-based technique that performs better than the current state-of-the-art for end-to-end small object detection. Like most recent methods, we generate proposals and then classify them. We suggest improvements to both these steps for the case of small objects.

Abstract

e datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20–200 ms, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training.

Abstract

In this paper, we demonstrate a score based indexing approach for tennis videos. Given a broadcast tennis video (btv), we index all the video segments with their scores to create a navigable and searchable match. Our approach temporally segments the rallies in the video and then recognizes the scores from each of the segments, before refining the scores using the knowledge of the tennis scoring system. We finally build an interface to effortlessly retrieve and view the relevant video segments by also automatically tagging the segmented rallies with human accessible tags such as ‘fault’ and ‘deuce’. The efficiency of our approach is demonstrated on btv’s from two major tennis tournaments.

Abstract

Facial fiducial detection is a challenging problem for several reasons like varying pose, appearance, expression, partial occlusion and others. In the past, several approaches like mixture of trees [32], regression based methods [8], exemplar based methods [7] have been proposed to tackle this challenge. In this paper, we propose an exemplar based approach to select the best solution from among outputs of regression and mixture of trees based algorithms (which we call candidate algorithms). We show that by using a very simple SIFT and HOG based descriptor, it is possible to identify the most accurate fiducial outputs from a set of results produced by candidate algorithms on any given test image. Our approach manifests as two algorithms, one based on optimizing an objective function with quadratic terms and the other based on simple kNN. Both algorithms take as input fiducial locations produced by running state-of-the-art candidate algorithms on an input image, and output accurate fiducials using a set of automatically selected exemplar images with annotations. Our surprising result is that in this case, a simple algorithm like kNN is able to take advantage of the seemingly huge complementarity of these candidate algorithms, better than optimization based algorithms. We do extensive experiments on several datasets, and show that our approach outperforms state-of-the-art consistently. In some cases, we report as much as a 10% improvement in accuracy. We also extensively analyze each component of our approach, to illustrate its efficacy. An implementation and extended technical report of our approach is available www.sites.google.com/site/wacv2016facefiducialexemplars.

Abstract

A good post processing module is an indispensable part of an OCR pipeline. In this paper, we propose a novel method for error detection in Indian language OCR output. Our solution uses a recurrent neural network ( RNN ) for classification of a word as an error or not. We propose a generic error detection method and demonstrate its effectiveness on four popular Indian languages. We divide the words into their constituent aksharas and use their bigram and trigram level information to build a feature representation. In order to train the classifier on incorrect words, we use the mis-recognized words in the output of the OCR . In addition to RNN , we also explore the effectiveness of a generative model such as GMM for our task and demonstrate an improved performance by combining both the approaches. We tested our method on four popular Indian languages and report an average error detection performance above 80%.

Abstract

Egocentric videos are characterized by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. With the substantial increase in the number of egocentric videos, the value and utility of recognizing actions of the wearer in such videos has also thus increased. Unstructured movement of the camera due to natural head motion of the wearer causes sharp changes in the visual field of the egocentric camera causing many standard third person action recognition techniques to perform poorly on such videos. Objects present in the scene and hand gestures of the wearer are the most important cues for first person action recognition but are difficult to segment and recognize in an egocentric video. We propose a novel representation of the first person actions derived from feature trajectories. The features are simple to compute using standard point tracking and do not assume segmentation of hand/objects or recognizing object or hand pose unlike in many previous approaches. We train a bag of words classifier with the proposed features and report a performance improvement of more than 11% on publicly available datasets. Although not designed for the particular case, we show that our technique can also recognize wearer's actions when hands or objects are not visible.

Abstract

Classical visual servoing approaches use visual features based on geometry of the object such as points, lines, region, etc. to attain the desired camera pose. However, geometrical features are not suited for visual servoing across different object instances due to large variations in appearance and shape. In this paper, we present a new framework for visual servoing across object instances. Our approach is based on a discriminative learning framework where the desired pose is estimated using previously seen examples. Specifically, we learn a binary classifier that separates the desired pose from all other poses for that object category. The classification error is then used to control the end-effector so that the desired pose is attained. We present controllers for linear, kernel and exemplar Support Vector Machine (SVM) and empirically discuss their performance in the visual servoing context. To address large intra-category variation in appearance, we propose a modified version of Histogram of Oriented Gradients (HOG) features for visual servoing. We show effective servoing across diverse instances over 3 object categories with zero terminal velocity and acceptable camera pose error at termination.