Abstract

We propose thetextbf {AViNet} architecture for audiovisual saliency prediction. AViNet is a fully convolutional encoder-decoder architecture. The encoder combines visual features learned for action recognition, with audio embeddings learned via an aural network designed to classify objects and scenes. The decoder infers a saliency map via trilinear interpolation and 3D convolutions, combining hierarchical features. The overall architecture is conceptually simple, causal, and runs in real-time (60 fps). AViNet outperforms the state-of-the-art on ten (seven audiovisual and three visual-only) datasets while surpassing human performance on the CC, SIM, and AUC metrics for the AVE dataset. Visual features maximally account for saliency on existing datasets with audio-only contributing to minor gains, except in specific contexts like social events. Our work, therefore, motivates the need to curate saliency datasets reflective of real-life, where both the visual and aural modalities complimentarily drive saliency. Our code and pre-trained models are available at this https URL

Abstract

Semantics play an important role when it comes to automated systems using text or language and it is different for different domains. In this paper, we tackle the FinSim 2020 shared task at IJCAIPRICAI 2020. The task deals with designing a semantic model which can automatically classify short phrases/terms from financial domain into the most relevant hypernym (or top-level) concept in an external ontology. We perform several experiments using different kinds of word and phrase level embeddings to solve the problem in an unsupervised manner. We also explore the use of a supplementary financial domain data; either to learn better concept representation or generate more training samples. We discuss both the positive and negative results that we observed while applying these approaches.

Abstract

Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years. With their ever increasing popularity, fine-tuning of pretrained Transformer-based encoder models with a classifier head are gradually becoming the new baseline for natural language classification tasks. In our work, we explore the gains attributed to Task Adaptive Pretraining (TAPT) prior to fine-tuning of Transformer-based architectures. We specifically study two problems, namely,(a) Coarse binary classification of Hindi Tweets into Hostile or Not, and (b) Fine-grained multi-label classification of Tweets into four categories: hate, fake, offensive, and defamation. Building up on an architecture which takes emojis and segmented hashtags into consideration for classification, we are able to experimentally showcase the performance upgrades due to TAPT. Our system (with team name'iREL IIIT') ranked first in the'Hostile Post Detection in Hindi'shared task with an F1 score of 97.16% for coarse-grained detection and a weighted F1 score of 62.96% for fine-grained multi-label classification on the provided blind test corpora.

Abstract

Detecting and classifying instances of hate in social media text has been a problem of interest in NaturalLanguage Processing in the recent years. Our work leverages state of the art Transformer languagemodels to identify hate speech in a multilingual setting. Capturing the intent of a post or a comment onsocial media involves careful evaluation of the language style, semantic content and additional pointerssuch as hashtags and emojis. In this paper, we look at the problem of identifying whether a Twitterpost is hateful and offensive or not. We further discriminate the detected toxic content into one of thefollowing three classes: (a) Hate Speech (HATE), (b) Offensive (OFFN) and (c) Profane (PRFN). With apre-trained multilingual Transformer-based text encoder at the base, we are able to successfully identifyand classify hate speech from multiple languages. On the provided testing corpora, we achieve MacroF1 scores of 90.29, 81.87 and 75.40 for English, German and Hindi respectively while performing hatespeech detection and of 60.70, 53.28 and 49.74 during fine-grained classification. In our experiments, weshow the efficacy of Perspective API features for hate speech classification and the effects of exploitinga multilingual training scheme. A feature selection study is provided to illustrate impacts of specificfeatures upon the architecture’s classification head.

Abstract

Automatic text summarization has been widely studied as an important task in natural language processing. Traditionally, various feature engineering and machine learning based systems have been proposed for extractive as well as abstractive text summarization. Recently, deep learning based, specifically Transformer-based systems have been immensely popular. Summarization is a cognitively challenging task-extracting summary worthy sentences is laborious, and expressing semantics in brief when doing abstractive summarization is complicated. In this paper, we specifically look at the problem of summarizing scientific research papers from multiple domains. We differentiate between two types of summaries, namely,(a) LaySumm: A very short summary that captures the essence of the research paper in layman terms restricting overtly specific technical jargon and (b) LongSumm: A much longer detailed summary aimed at providing specific insights into various ideas touched upon in the paper. While leveraging latest Transformer-based models, our systems are simple, intuitive and based on how specific paper sections contribute to human summaries of the two types described above. Evaluations against gold standard summaries using ROUGE metrics prove the effectiveness of our approach. On blind test corpora, our system ranks first and third for the LongSumm and LaySumm tasks respectively.

Abstract

n this paper, we study current and upcoming frontiers across the landscape of skeleton-based human action recognition. To begin with, we benchmark state-of-the-art models on the NTU-120 dataset and provide multi-layered assessment of the results. To examine skeleton action recognition'in the wild', we introduce Skeletics-152, a curated and 3-D pose-annotated subset of RGB videos sourced from Kinetics-700, a large-scale action dataset. The results from benchmarking the top performers of NTU-120 on Skeletics-152 reveal the challenges and domain gap induced by actions' in the wild'. We extend our study to include out-of-context actions by introducing Skeleton-Mimetics, a dataset derived from the recently introduced Mimetics dataset. Finally, as a new frontier for action recognition, we introduce Metaphorics, a dataset with caption-style annotated YouTube videos of the popular social game Dumb Charades and interpretative dance performances. Overall, our work characterizes the strengths and limitations of existing approaches and datasets. It also provides an assessment of top-performing approaches across a spectrum of activity settings and via the introduced datasets, proposes new frontiers for human action recognition.

Abstract

The problem of bound entanglement detection is a challenging aspect of quantum information theory for higher dimensional systems. Here, we propose an indecomposable positive map for two-qutrit systems, which is shown to generate a class of positive partial transposed (PPT) states. A corresponding witness operator is constructed and shown to be weakly optimal and locally implementable. Further, we perform a structural physical approximation of the indecomposable map to make it a completely positive one, and find a new PPT entangled state which is not detectable by certain other well-known entanglement detection criteria.

Abstract

Self-supervised learning is emerging as an effective substitute for transfer learning from large datasets. In this work, we use kidney segmentation to explore this idea. The anatomical asymmetry of kidneys is leveraged to define an effective proxy task for kidney segmentation via self-supervised learning. A siamese convolutional neural network (CNN) is used to classify a given pair of kidney sections from CT volumes as being kidneys of the same or different sides. This knowledge is then transferred for the segmentation of kidneys using another deep CNN using one branch of the siamese CNN as the encoder for the segmentation network. Evaluation results on a publicly available dataset containing computed tomography (CT) scans of the abdominal region shows that a boost in performance and fast convergence can be had relative to a network trained conventionally from scratch. This is notable given that no additional data/expensive annotations or augmentation were used in training.

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 …