Abstract

Multi-view Detection (MVD) is highly effective for occlusion reasoning in a crowded environment. While recent works using deep learning have made significant advances in the field, they have overlooked the generalization aspect, which makes them impractical for real-world deployment. The key novelty of our work is to formalize three critical forms of generalization and propose experiments to evaluate them: generalization with i) a varying number of cameras, ii) varying camera positions, and finally, iii) to new scenes. We find that existing state-of-the-art models show poor generalization by overfitting to a single scene and camera configuration. To address the concerns: (a) we propose a novel Generalized MVD (GMVD) dataset, assimilating diverse scenes with changing day- time, camera configurations, varying number of cameras, and (b) we discuss the properties essential to bring generalization to MVD and propose a barebones model to incorporate them. We perform a comprehensive set of experiments on the WildTrack, MultiViewX and the GMVD datasets to motivate the necessity to evaluate generalization abilities of MVD methods and to demonstrate the efficacy of the proposed approach. The code and the proposed dataset can be found at https://github.com/jeetv/GMVD

Abstract

In this work, we deal with the relaxation of two central assumptions in standard locally realistic hidden variable (LRHV) inequalities: free will in choosing measurement settings, and the presence of perfect detectors at the measurement devices. Quantum correlations violating LRHV inequalities are called quantum nonlocal correlations. In principle, in an adversarial situation, there could be a hidden variable introducing bias in the selection of measurement settings, but observers with no access to that hidden variable could be unaware of the bias. In practice, however, detectors do not have perfect efficiency. A main focus of this paper is the introduction of the framework in which given a quantum state with nonlocal behavior under constrained free will, we can determine the threshold values of detector parameters (detector inefficiency and dark counts) such that the detectors are robust enough to certify nonlocality. We also introduce a class of LRHV inequalities with constrained free will, and we discuss their implications in the testing of quantum nonlocal correlation

Abstract

Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios. Preparation and training of deploy-able deep learning architectures require the models to be suited to different traffic scenarios and adapt to different situations. Currently, existing datasets, while large-scale, lack such diversities and are geographically biased towards mainly developed cities. An unstructured and complex driving layout found in several developing countries such as India poses a challenge to these models due to the sheer degree of variations in the object types, densities, and locations. To facilitate better research toward accommodating such scenarios, we build a new dataset, IDD-3D, which consists of multimodal data from multiple cameras and LiDAR sensors with 12k annotated driving LiDAR frames across various traffic scenarios. We discuss the need for this dataset through statistical comparisons with existing datasets and highlight benchmarks on standard 3D object detection and tracking tasks in complex layouts. Code and data available 1 .

Abstract

Over the last decade, online lecture videos have become increasingly popular and have experienced a meteoric rise during the pandemic. However, video-language research has primarily focused on instructional videos or movies, and tools to help students navigate the growing online lectures are lacking. Our first contribution is to facilitate research in the educational domain by introducing AVLectures, a large-scale dataset consisting of 86 courses with over 2,350 lectures covering various STEM subjects. Each course contains video lectures, transcripts, OCR outputs for lecture frames, and optionally lecture notes, slides, assignments, and related educational content that can inspire a variety of tasks. Our second contribution is introducing video lecture segmentation that splits lectures into bitesized topics. Lecture clip representations leverage visual, textual, and OCR cues and are trained on a pretext selfsupervised task of matching the narration with the temporally aligned visual content. We formulate lecture segmentation as an unsupervised task and use these representations to generate segments using a temporally consistent 1- nearest neighbor algorithm, TW-FINCH [44]. We evaluate our method on 15 courses and compare it against various visual and textual baselines, outperforming all of them. Our comprehensive ablation studies also identify the key factors driving the success of our approach.

Abstract

To perform network forensic analysis on an incident in software defined networking (SDN), logs are of the utmost importance. Without any logs, an investigator is not be able to complete and justify the forensic analysis. With the advancement of network and communication technologies, the volume of logs that needs to be collected and retained is growing exponentially big. The network administrators face the problems in maintaining such huge logs for longer period of time for forensic analysis. Network Providers rely on purging data based on a certain stipulated duration expected by the local rules for forensics evidence. SDN providers have limitations in managing such big data since the expense involved is commensurate with the duration of data retention. Here, in this work we propose a novel idea to reduce and summarize large forensic data sets for faster querying as well as reducing its space complexity by using bloom filters. Through this work we aim to propose a system which can deliver more optimized forensic data availability in SDN platform compared to existing systems.

Abstract

Deep Learning on face recognition problems has shown extremely high accuracy owing to their ability in finding strongly discriminating features. However, face images in the wild show variations in pose, lighting, expressions, and the presence of facial attributes (for example eyeglasses). We ask, why then are these vari- ations not detected and used during the matching process? We demonstrate that this is indeed possible while restricting ourselves to facial attribute variation, to prove the case in point. We show two ways of doing so. a) By using the face attribute labels as a form of prior, we bin the matching template pairs into three bins depend- ing on whether each template of the matching pair possesses a given facial attribute or not. By operating on each bin and averaging the result, we better the EER of SOTA by over 1 % over a large set of matching pairs. b) We use the attribute labels and correlate them with each neuron of an embedding generated by a SOTA architecture pre-trained DNN on a large Face dataset and fine-tuned on face-attribute labels. We then suppress a set of maximally correlating neurons and perform matching after doing so. We demonstrate this improves the EER by over 2 %.

Abstract

Computer tomography (CT) have been routinely used for the diagnosis of lung diseases and recently, during the pandemic, for detecting the infectivity and severity of COVID-19 disease. One of the major concerns in using ma-chine learning (ML) approaches for automatic processing of CT scan images in clinical setting is that these methods are trained on limited and biased sub-sets of publicly available COVID-19 data. This has raised concerns regarding the generalizability of these models on external datasets, not seen by the model during training. To address some of these issues, in this work CT scan images from confirmed COVID-19 data obtained from one of the largest public repositories, COVIDx CT 2A were used for training and internal vali-dation of machine learning models. For the external validation we generated Indian-COVID-19 CT dataset, an open-source repository containing 3D CT volumes and 12096 chest CT images from 288 COVID-19 patients from In-dia. Comparative performance evaluation of four state-of-the-art machine learning models, viz., a lightweight convolutional neural network (CNN), and three other CNN based deep learning (DL) models such as VGG-16, ResNet-50 and Inception-v3 in classifying CT images into three classes, viz., normal, non-covid pneumonia, and COVID-19 is carried out on these two datasets. Our analysis showed that the performance of all the models is comparable on the hold-out COVIDx CT 2A test set with 90% - 99% accuracies (96% for CNN), while on the external Indian-COVID-19 CT dataset a drop in the performance is observed for all the models (8% - 19%). The traditional ma-chine

Abstract

Learning an efficient label embedding framework for word images enables effective word spotting of handwritten documents. In this work, we propose different schemes of label embedding for word images using deep neural architectures and their representations. We refer to our first scheme as the two-stage label embedding technique which projects both word images and their corresponding textual strings into a common subspace. We further introduce an end-to-end label embedding scheme using deep neural architecture which simplifies the embedding process and reports state-of-the-art performance for the task of word spotting and recognition. We also validate the role of synthetic data as a complementary modality to further enhance the embedding process. On the challenging IAM handwritten dataset, we report an mAP of 0.9753 for query-by-string-based word spotting, while under lexicon-based word recognition, our proposed method reports 1.67 and 3.62 character and word error rates, respectively. We also present the detailed ablation study on various variants of our end-to-end embedding architecture and perform analysis under varying embedding sizes. We further validate the embedding scheme on degraded printed document datasets from both Latin and Indic scripts.

Abstract

In our work, we study the age of information (AoI) in a multi-source system where K sources transmit updates of their time-varying processes via a common-aggregator node to a destination node through a channel with packet delivery errors. We analyze AoI for an (α, β, 0, 1)-Gilbert-Elliot (GE) packet erasure channel with a round-robin scheduling policy. We employ maximum distance separable (MDS) scheme at aggregator for encoding the multi-source updates. We characterize the mean AoI for the MDS coded system for the case of large blocklengths. We further show that the optimal coding rate that achieves maximum coding gain over the uncoded system is n(1 − P) − O(n), where P , β α+β 0 + α α+β 1, and this maximum coding gain is (1 + P)/(1 + O(1)). In our work, we study the age of information (AoI) in a multi-source system where K sources transmit updates of their time-varying processes via a common-aggregator node to a destination node through a channel with packet delivery errors. We analyze AoI for an (α, β, 0, 1)-Gilbert-Elliot (GE) packet erasure channel with a round-robin scheduling policy. We employ maximum distance separable (MDS) scheme at aggregator for encoding the multi-source updates. We characterize the mean AoI for the MDS coded system for the case of large blocklengths. We further show that the optimal coding rate that achieves maximum coding gain over the uncoded system is n(1 − P) − O(n), where P , β α+β 0 + α α+β 1, and this maximum coding gain is (1 + P)/(1 + O(1)).

Abstract

This paper considers a communication system where a source sends time-sensitive information to its destination. We assume that both arrival and service processes of the messages are memoryless and the source has a single server with no buffer. Besides, we consider that the service is interrupted by an independent random process, which we model using the OnOff process. For this setup, we study the age of information for two queueing disciplines: 1) non-preemptive, where the messages arriving while the server is occupied are discarded, and 2) preemptive, where the in-service messages are replaced with newly arriving messages in the Off states. For these disciplines, we derive closed-form expressions for the mean peak age and mean age. Index Terms—Age of information, Peak age, On-Off process, preemptive discipline, non-preemptive discipline