Abstract

Hashtag segmentation is the task of breaking a hashtag into its constituent tokens. Hashtags often encode the essence of usergenerated posts, along with information like topic and sentiment, which are useful in downstream tasks. Hashtags prioritize brevity and are written in unique ways - transliterating and mixing languages, spelling variations, creative named entities. Benchmark datasets used for the hashtag segmentation task - STAN, BOUN - are small in size and extracted from a single set of tweets. However, datasets should reflect the variations in writing styles of hashtags and also account for domain and language specificity, failing which the results will misrepresent model performance. We argue that model performance should be assessed on a wider variety of hashtags, and datasets should be carefully curated. To this end, we propose HashSet, a dataset comprising of: a) 1.9k manually annotated dataset; b) 3.3M loosely supervised dataset. HashSet dataset is sampled from a different set of tweets when compared to existing datasets and provides an alternate distribution of hashtags to build and validate hashtag segmentation models. We show that the performance of SOTA models for Hashtag Segmentation drops substantially on proposed dataset, indicating that the proposed dataset provides an alternate set of hashtags to train and assess models. Datasets and results are released publicly and can be accessed

Abstract

Advancements in adaptive object detection can lead to tremendous improvements in applications like autonomous navigation, as they alleviate the distributional shifts along the detection pipeline. Prior works adopt adversarial learn- ing to align image features at global and local levels, yet the instance-specific misalignment persists. Also, adaptive object detection remains challenging due to visual diver- sity in background scenes and intricate combinations of ob- jects. Motivated by structural importance, we aim to attend prominent instance-specific regions, overcoming the feature misalignment issue. We propose a novel resIduaL seLf- attentive featUre alignMEnt (ILLUME) method for adaptive object detection. ILLUME comprises Self-Attention Fea- ture Map (SAFM) module that enhances structural atten- tion to object-related regions and thereby generates domain invariant features. Our approach significantly reduces the domain distance with the improved feature alignment of the instances. Qualitative results demonstrate the ability of ILLUME to attend important object instances required for alignment. Experimental results on several benchmark datasets show that our method outperforms the existing state-of-the-art approaches.

Abstract

Player detection lays the foundation for many applica- tions in the field of sports analytics including player recog- nition, player tracking, and activity detection. In this work, we study player detection in continuous long shot broad- cast videos. Broadcast match videos are easy to obtain, and detection on these videos is much more challenging. We propose a transductive approach for player detection that treats it as a domain adaptation problem. We show that instance-level domain labels are significant for sufficient adaptation in the case of soccer broadcast videos. An ef- ficient multi-model greedy labelling scheme based on visual features is proposed to annotate domain labels on bounding box predictions made by our inductive model. We use reli- able instances from the inductive model inferences to train a transductive copy of the model. We create and release a fully annotated player detection dataset comprising soccer broadcast videos from the FIFA 2018 World Cup matches to evaluate our method. Our method shows significant im- provements in player detection to the baseline and existing state-of-the-art methods on our dataset. We show, on aver- age, a 16 point improvement in mAP for soccer broadcast videos by annotating domain labels for around a 100 sam- ples per video.

Abstract

Fully entangled fraction (FEF) is a significant figure of merit for density matrices. In bipartite d ⊗ d quantum systems, the threshold value FEF > 1/d, dictates prominent implications for tasks like teleportation and entanglement distillation. Like separability, the value of FEF is also related to the choice of global basis of the underlying Hilbert space. A state having its FEF ≤ 1/d, might give a value > 1/d in another global basis. A change in the global basis corresponds to a global unitary action on the quantum state. In the present work, we find that there are quantum states whose FEF remains less than 1/d, under the action of any global unitary i.e., any choice of global basis. Based on the fixed spectrum of density matrices, we provide necessary and sufficient criteria in two qubit systems which also prove to be sufficient in any d⊗d dimensions, to identify such states. Further, we prove that states having their FEF bounded by 1/d under any global unitary, form a convex and compact set. This entails the distinction of states whose FEF can be increased beyond 1/d, through unitary action. The demarcation is of paramount importance as it provides for the identification of states which can prove to be useful in teleportation and entanglement distillation after the action of global unitary operators, as underpinned by illustrations in our work.

Abstract

n this paper, we develop a robust 3D garment digitiza- tion solution that can generalize well on real-world fashion catalog images with cloth texture occlusions and large body pose variations. We assumed fixed topology parametric template mesh models for known types of garments (e.g., T- shirts, Trousers) and perform mapping of high-quality tex- ture from an input catalog image to UV map panels corre- sponding to the parametric mesh model of the garment. We achieve this by first predicting a sparse set of 2D landmarks on the boundary of the garments. Subsequently, we use these landmarks to perform Thin-Plate-Spline-based tex- ture transfer on UV map panels. Subsequently, we employ a deep texture inpainting network to fill the large holes (dueto view variations & self-occlusions) in TPS output to gen- erate consistent UV maps. Furthermore, to train the su- pervised deep networks for landmark prediction & texture inpainting tasks, we generated a large set of synthetic data with varying texture and lighting imaged from various views with the human present in a wide variety of poses. Addition- ally, we manually annotated a small set of fashion catalog images crawled from online fashion e-commerce platforms to finetune. We conduct thorough empirical evaluations and show impressive qualitative results of our proposed 3D gar- ment texture solution on fashion catalog images. Such 3D garment digitization helps us solve the challenging task of enabling 3D Virtual Try-on

Abstract

Water vapor is the most dominant greenhouse gas in the atmosphere and plays a critical role in Earth’s energy budget and hydrological cycle. This study aims to characterize the long-term seasonal variation of relative humidity (RH), convective available potential energy (CAPE), and convective inhibition (CIN) from surface and radiosonde observations from 1980–2020. The results show that during the monsoon season, very high RH values are depicted while low values are depicted during the pre-monsoon season. West Coast stations represent large RH values compared to other stations throughout the year. Irrespective of the season, the coastal regions show higher RH values during monsoon season. Regardless of season, the coastal regions have higher RH values during the monsoon season. During the pre-monsoon season, the coastal region has high RH values, whereas other regions have high RH values during the monsoon season. The rate of increase in RH in North-West India is 5.4%, followed by the West Coast, Central, and Southern parts of India.. An increase in water vapor leads to raised temperature, which alters the instability conditions. In terms of seasonal variation, our findings show that CAPE follows a similar RH pattern. CAPE increases sharply in Central India and the West Coast region, while it declines in South India. Opposite features are observed in CIN with respect to CAPE variability over India. The results of the study provide additional evidence with respect to the role of RH as an influencing factor for an increase in CAPE over India.

Abstract

—Rural connectivity has been a widely researched topic for several years. In India, around 50% of the population have poor or no connectivity to access digital services. Numerous technological solutions are being tested around the world, as well as in India. The key driving factor for reducing the digital divide is to lower the cost of network deployments and improve service adoption rate by exploring different technological and economical solutions. This survey aims to study rural connectivity and create awareness about the use-cases, state of the art projects and initiatives, challenges, and technologies to improve digital connectivity in rural parts of India. The strengths and weaknesses of different technologies tested for rural connectivity are analysed. The study includes a brief discussion of rural connectivity trials performed in India and around the world. We also explore the rural use-case of the 6G communication system, which would suit the rural Indian scenario

Abstract

Electroencephalography (EEG) provides the temporal resolution required to map the neural activations for studying motor movements and control. This study aims to compare the power amplitude of electrodes covering the central and frontal regions of a 32-channel scalp EEG. The activations from a standard index finger-tapping and a game paradigm are analyzed. Twenty-five right-handed and five left-handed healthy subjects (range = 18–30 years; mean = 24.25 years; SD = 3.96 years) participated in this study. A novel single-frequency filter (SFF) bank was applied to identify the peak amplitude from the power spectral density plots. The results show that the gaming paradigm yields lower or comparable power amplitudes than the standard finger tapping. We observed that the right-hand finger tapping by the left-handed subjects shows lower between-subject dispersion in amplitude. Nonparametric Spearman correlation showed no association between game scores and power amplitude for the right-handed participants. However, for left-handers, both positive and negative associations were observed. This study demonstrates the efficacy of SFF for extracting power amplitudes with a better signalto-noise ratio, which has implications in BCI and motor rehabilitation applications. The findings support the role of game paradigms for motor movement research and in understanding bilateral hemispheric activations in cognitive tasks.

Abstract

In this paper, the intrinsic characteristics of speech modulations are estimated to propose the instant modulation spectral features for efficient emotion recognition. This feature representation is based on single frequency filtering (SFF) technique and higher order nonlinear energy operator. The speech signal is decomposed into frequency sub-bands using SFF, and associated nonlinear energies are estimated with higher order nonlinear energy operator. Then, the feature vector is realized using cepstral analysis. The high-resolution property of SFF technique is exploited to extract the amplitude envelope of the speech signal at a selected frequency with good time-frequency resolution. The fourth order nonlinear energy operator provides noise robustness in estimating the modulation components. The proposed feature set is tested for the emotion recognition task using the i-vector model with the probabilistic linear discriminant scoring scheme, support vector machine and random forest classifiers. The results demonstrate that the performance of this feature representation is better than the widely used spectral and prosody features, achieving detection accuracy of 85.75%, 59.88%, and 65.78% on three emotional databases, EMODB, FAUAIBO, and IEMOCAP, respectively. Further, the proposed features are found to be robust in the presence of additive white Gaussian and vehicular noises.

Abstract

The experience often described as feeling moved, understood chiefly as a social-relational emotion with social bonding functions, has gained significant research interest in recent years. Although listening to music often evokes what people describe as feeling moved, very little is known about the appraisals or musical features contributing to the experience. In the present study, we investigated experiences of feeling moved in response to music using a continuous rating paradigm. A total of 415 US participants completed an online experiment where they listened to seven moving musical excerpts and rated their experience while listening. Each excerpt was randomly coupled with one of seven rating scales (perceived sadness, perceived joy, feeling moved or touched, sense of connection, perceived beauty, warmth [in the chest], or chills) for each participant. The results revealed that musically evoked experiences of feeling moved are associated with a similar pattern of appraisals, physiological sensations, and trait correlations as feeling moved by videos depicting social scenarios (found in previous studies). Feeling moved or touched by both sadly and joyfully moving music was associated with experiencing a sense of connection and perceiving joy in the music, while perceived sadness was associated with feeling moved or touched only in the case of sadly moving music. Acoustic features related to arousal contributed to feeling moved only in the case of joyfully moving music. Finally, trait empathic concern was positively associated with feeling moved or touched by music. These findings support the role of social cognitive and empathic processes in music listening, and highlight the social-relational aspects of feeling moved or touched by music.