Abstract

Multi-target tracking of pedestrians is a challenging task due to uncertainty about targets, caused mainly by similarity between pedestrians, occlusion over a relatively long time and a cluttered background. A usual scheme for tackling multi-target tracking is to divide it into two sub-problems: data association and trajectory estimation. A reasonable approach is based on joint optimization of a discrete model for data association and a continuous model for trajectory estimation in a Markov Random Field framework. Nonetheless, usual solutions of the data association problem are based only on location information, while the visual information in the images is ignored. Visual features can be useful for associating detections with true targets more reliably, because the targets usually have discriminative features. In this work, we propose a combination of position and visual feature information in a discrete data association …

Abstract

We aim to solve the highly challenging task of generating continuous sign language videos solely from speech segments for the first time. Recent efforts in this space have focused on generating such videos from human-annotated text transcripts without considering other modalities. However, replacing speech with sign language proves to be a practical solution while communicating with people suffering from hearing loss. Therefore, we eliminate the need of using text as input and design techniques that work for more natural, continuous, freely uttered speech covering an extensive vocabulary. Since the current datasets are inadequate for generating sign language directly from speech, we collect and release the first Indian sign language dataset comprising speech-level annotations, text transcripts, and the corresponding sign-language videos. Next, we propose a multi-tasking transformer network trained to generate signer's poses from speech segments. With speech-to-text as an auxiliary task and an additional cross-modal discriminator, our model learns to generate continuous sign pose sequences in an end-to-end manner. Extensive experiments and comparisons with other baselines demonstrate the effectiveness of our approach. We also conduct additional ablation studies to analyze the effect of different modules of our network. A demo video containing several results is attached to the supplementary material.

Abstract

The advent of digital pathology presents opportunities for computer vision for fast, accurate, and objective solutions for histopathological images and aid in knowledge discovery. This work uses deep learning to predict genomic biomarkers - TP53 mutation, PIK3CA mutation, ER status, PR status, HER2 status, and intrinsic subtypes, from breast cancer histopathology images. Furthermore, we attempt to understand the underlying morphology as to how these genomic biomarkers manifest in images. Since gene sequencing is expensive, not always available, or even feasible, predicting these biomarkers from images would help in diagnosis, prognosis, and effective treatment planning. We outperform the existing works with a minimum improvement of 0.02 and a maximum of 0.13 AUROC scores across all tasks. We also gain insights that can serve as hypotheses for further experimentations, including the presence of lymphocytes and karyorrhexis. Moreover, our fully automated workflow can be extended to other tasks across other cancer subtypes.

Abstract

This paper addresses the task of group activity recognition in multi-person videos. Existing approaches decompose this task into feature learning and relational reasoning. Despite showing progress, these methods only rely on appearance features for people and overlook the available contextual information, which can play an important role in group activity understanding. In this work, we focus on the feature learning aspect and propose a two-stream architecture that not only considers person-level appearance features, but also makes use of contextual information present in videos for group activity recognition. In particular, we propose to use two types of contextual information beneficial for two different scenarios: pose context and scene context that provide crucial cues for group activity understanding. We combine appearance and contextual features to encode each person with an enriched representation. Finally, these combined features are used in relational reasoning for predicting group activities. We evaluate our method on two benchmarks, Volleyball and Collective Activity and show that joint modeling of contextual information with appearance features benefits in group activity understanding.

Abstract

India is a country with thousands of languages and dialects spoken across a billion-strong population. For multi-lingual content creation and accessibility, text-to-speech systems will play a crucial role. However, the current neural TTS systems are data-hungry and need about 20 hours of clean single-speaker speech data for each language and speaker. This is not scalable for the large number of Indian languages and dialects. In this work, we demonstrate three simple, yet effective pre-training strategies that allow us to train neural TTS systems with just about one-tenth of the data needs while also achieving better accuracy and naturalness. We show that such pre-trained neural TTS systems can be quickly adapted to different speakers across languages and genders with less than 2 hours of data, thus significantly reducing the effort for future expansions to the thousands of rare Indian languages. We specifically …

Abstract

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.

Abstract

We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa. org

Abstract

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.

Abstract

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network,(CDeC-Net) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on all the publicly available benchmark datasets-ICDAR-2013, ICDAR-2017, ICDAR-2019, UNLV, Marmot, PubLayNet, and TableBank-with extensive experiments. Our solution has three important properties:(i) a single trained model CDeC-Net‡ performs well across all the popular benchmark datasets;(ii) we report excellent performances across multiple, including higher, thresholds of IoU;(iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models will be publicly released for enabling the reproducibility of the results.

Abstract

his paper presents results of Document Visual Question Answering Challenge organized as part of" Text and Documents in the Deep Learning Era" workshop, in CVPR 2020. The challenge introduces a new problem-Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer (s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.