ICDAR 2021 Competition on Document VisualQuestion Answering

In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single Document VQA and Document Collection VQA with a newly introduced on Infographics VQA. Infographics VQA is based on a new dataset of more than 5,000 infographics images and 30,000 question-answer pairs. The winner methods have scored 0.6120 ANLS in Infographics VQA task, 0.7743 ANLSL in Document Collection VQA task and 0.8705 ANLS in Single Document VQA. We present a summary of the datasets used for each task, description of each of the submitted methods and the results and analysis of their performance. A summary of the progress made on Single Document VQA since the first edition of the DocVQA 2020 challenge is also presented.

Multi-Domain Incremental Learning for Semantic Segmentation

Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmentation frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmentation. Given a model trained on a particular geographical domain, the goal is to (i) incrementally learn a new geographical domain, (ii) while retaining performance on the old domain, (iii) given that the previous domain's dataset is not accessible. We propose a dynamic architecture that assigns universally shared, domain-invariant parameters to capture homogeneous semantic features present in all domains, while dedicated domain-specific parameters learn the statistics of each domain. Our novel optimization strategy helps achieve a good balance between retention of old knowledge (stability) and acquiring new knowledge (plasticity). We demonstrate the effectiveness of our proposed solution on domain incremental settings pertaining to real-world driving scenes from roads of Germany (Cityscapes), the United States (BDD100k), and India (IDD).

Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor

This paper proposes a video editor based on OpenShot with several state-of-the-art facial video editing algorithms as added functionalities. Our editor provides an easy-to-use interface to apply modern lip-syncing algorithms interactively. Apart from lip-syncing, the editor also uses audio and facial re-enactment to generate expressive talking faces. The manual control improves the overall experience of video editing without missing out on the benefits of modern synthetic video generation algorithms. This control enables us to lip-sync complex dubbed movie scenes, interviews, television shows, and other visual content. Furthermore, our editor provides features that automatically translate lectures from spoken content, lip-sync of the professor, and background content like slides. While doing so, we also tackle the critical aspect of synchronizing background content with the translated speech. We qualitatively evaluate the usefulness of the proposed editor by conducting human evaluations. Our evaluations show a clear improvement in the efficiency of using human editors and an improved video generation quality. We attach demo videos with the supplementary material clearly explaining the tool and also showcasing multiple results.

Ego4D: Around the World in 3,000 Hours of Egocentric Video

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,025 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 855 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

Evaluating Computer Vision Techniques for Urban Mobility on Large-Scale, Unconstrained Roads

Conventional approaches for addressing road safety rely on manual interventions or immobile CCTV infrastructure. Such methods are expensive in enforcing compliance to traffic rules and do not scale to large road networks. This paper proposes a simple mobile imaging setup to address several common problems in road safety at scale. We use recent computer vision techniques to identify possible irregularities on roads, the absence of street lights, and defective traffic signs using videos from a moving camera-mounted vehicle. Beyond the inspection of static road infrastructure, we also demonstrate the mobile imaging solution's applicability to spot traffic violations. Before deploying our system in the real-world, we investigate the strengths and shortcomings of computer vision techniques on thirteen condition-based hierarchical labels. These conditions include different timings, road type, traffic density, and state of road damage. Our demonstrations are then carried out on 2000 km of unconstrained road scenes, captured across an entire city. Through this, we quantitatively measure the overall safety of roads in the city through carefully constructed metrics. We also show an interactive dashboard for visually inspecting and initiating action in a time, labor and cost-efficient manner. Code, models, and datasets used in this work will be publicly released.

Efficient and Generic Interactive Segmentation Framework to Correct Mispredictions during Clinical Evaluation of Medical Images

Semantic segmentation of medical images is an essential first step in computer-aided diagnosis systems for many applications. However, given many disparate imaging modalities and inherent variations in the patient data, it is difficult to consistently achieve high accuracy using modern deep neural networks (DNNs). This has led researchers to propose interactive image segmentation techniques where a medical expert can interactively correct the output of a DNN to the desired accuracy. However, these techniques often need separate training data with the associated human interactions, and do not generalize to various diseases, and types of medical images. In this paper, we suggest a novel conditional inference technique for DNNs which takes the intervention by a medical expert as test time constraints and performs inference conditioned upon these constraints. Our technique is generic can be used for medical images from any modality. Unlike other methods, our approach can correct multiple structures simultaneously and add structures missed at initial segmentation. We report an improvement of 13.3, 12.5, 17.8, 10.2, and 12.4 times in user annotation time than full human annotation for the nucleus, multiple cells, liver and tumor, organ, and brain segmentation respectively. We report a time saving of 2.8, 3.0, 1.9, 4.4, and 8.6 fold compared to other interactive segmentation techniques. Our method can be useful to clinicians for diagnosis and post-surgical follow-up with minimal intervention from the medical expert. The source-code and the detailed results are available here [1].

ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction

Scanned receipts OCR and key information extraction (SROIE) represent the processeses of recognizing text from scanned receipts and extracting key texts from them and save the extracted tests to structured documents. SROIE plays critical roles for many document analysis applications and holds great commercial potentials, but very little research works and advances have been published in this area. In recognition of the technical challenges, importance and huge commercial potentials of SROIE, we organized the ICDAR 2019 competition on SROIE. In this competition, we set up three tasks, namely, Scanned Receipt Text Localisation (Task 1), Scanned Receipt OCR (Task 2) and Key Information Extraction from Scanned Receipts (Task 3). A new dataset with 1000 whole scanned receipt images and annotations is created for the competition. In this report we will presents the motivation, competition datasets, task definition, evaluation protocol, submission statistics, performance of submitted methods and results analysis.

Few Shot Learning With No Labels

Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes use of vast amounts of annotated data by simply shifting the label requirement from novel classes to base classes. Since data annotation is time-consuming and costly, reducing the label requirement even further is an important goal. To that end, our paper presents a more challenging few-shot setting where no label access is allowed during training or testing. By leveraging self-supervision for learning image representations and image similarity for classification at test time, we achieve competitive baselines while using \textbf{zero} labels, which is at least fewer labels than state-of-the-art. We hope that this work is a step towards developing few-shot learning methods which do not depend on annotated data at all. Our code will be publicly released.

Visual Speech Enhancement Without A Real Visual Stream

In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state-of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent works using lip movements as additional cues improve the quality of generated speech over "audio-only" methods. But, these methods cannot be used for several applications where the visual stream is unreliable or completely absent. We propose a new paradigm for speech enhancement by exploiting recent breakthroughs in speech-driven lip synthesis. Using one such model as a teacher network, we train a robust student network to produce accurate lip movements that mask away the noise, thus acting as a "visual noise filter". The intelligibility of the speech enhanced by our pseudo-lip approach is comparable (< 3% difference) to the case of using real lips. This implies that we can exploit the advantages of using lip movements even in the absence of a real video stream. We rigorously evaluate our model using quantitative metrics as well as human evaluations. Additional ablation studies and a demo video on our website containing qualitative comparisons and results clearly illustrate the effectiveness of our approach. We provide a demo video which clearly illustrates the effectiveness of our proposed approach on our website: \url{http://cvit.iiit.ac.in/research/projects/cvit-projects/visual-speech-enhancement-without-a-real-visual-stream}. The code and models are also released for future research: \url{https://github.com/Sindhu-Hegde/pseudo-visual-speech-denoising}.

Improving Word Recognition using Multiple Hypotheses and Deep Embeddings

We propose a novel scheme for improving the word recognition accuracy using word image embeddings. We use a trained text recognizer, which can predict multiple text hypothesis for a given word image. Our fusion scheme improves the recognition process by utilizing the word image and text embeddings obtained from a trained word image embedding network. We propose EmbedNet, which is trained using a triplet loss for learning a suitable embedding space where the embedding of the word image lies closer to the embedding of the corresponding text transcription. The updated embedding space thus helps in choosing the correct prediction with higher confidence. To further improve the accuracy, we propose a plug-and-play module called Confidence based Accuracy Booster (CAB). The CAB module takes in the confidence scores obtained from the text recognizer and Euclidean distances between the embeddings to generate an updated distance vector. The updated distance vector has lower distance values for the correct words and higher distance values for the incorrect words. We rigorously evaluate our proposed method systematically on a collection of books in the Hindi language. Our method achieves an absolute improvement of around 10 percent in terms of word recognition accuracy.