Search

Developing methods for extracting relevant legal information to aid legal practitioners is an active research area. In this regard, research efforts are being made by leveraging different kinds of information, such as meta-data, citations, keywords, sentences, paragraphs, etc. Similar to any text document, legal documents are composed of paragraphs. In this paper, we have analyzed the resourcefulness of paragraph-level information in capturing similarity among judgments for improving the performance of precedence retrieval. We found that the paragraph-level methods could capture the similarity among the judgments with only a few paragraph interactions and exhibit more discriminating power over the baseline document-level method. Moreover, the comparison results on two benchmark datasets for the precedence retrieval on the Indian supreme court judgments task show that the paragraph-level methods exhibit comparable performance with the state-of-the-art methods, Comment: 5 pages , 3 figures, ICAIL 2023

The TIFR Near Infrared Imaging Camera-II (TIRCAM2) is being used at the 3.6 m Devasthal Optical Telescope (DOT) operated by Aryabhatta Research Institute of Observational Sciences (ARIES), Nainital, Uttarakhand, India. Earlier, the TIRCAM2 was used at the main port of the DOT on time shared basis. It has now been installed at the side port of the telescope. Side port installation allows near simultaneous observations with the main port instrument as well as longer operating periods. Thus, the TIRCAM2 serves the astronomical community for a variety of observations ranging from lunar occultations, transient events and normal scheduled observations., Comment: Accepted for publication in the Journal of Astrophysics and Astronomy

We present the design and performance of the TANSPEC, a medium-resolution $0.55-2.5~\mu$m cryogenic spectrometer and imager, now in operation at the 3.6-m Devasthal Optical Telescope (DOT), Nainital, India. The TANSPEC provides three modes of operation which include, photometry with broad- and narrow-band filters, spectroscopy with short slits of 20$^{\prime \prime}$ length and different widths (from 0.5$^{\prime \prime}$ to 4.0$^{\prime \prime}$) in cross-dispersed mode at a resolving power R of $\sim$2750, and spectroscopy with long slits of 60$^{\prime \prime}$ length and different widths (from 0.5$^{\prime \prime}$ to 4.0$^{\prime \prime}$) in prism mode at a resolving power R of $\sim$100-350. TANSPEC's imager mode provides a field of view of 60$^{\prime \prime} \times 60^{\prime \prime}$ with a plate scale of 0.245$^{\prime \prime}$/pixel on the 3.6-m DOT. The TANSPEC was successfully commissioned during April-May 2019 and the subsequent characterization and astronomical observations are presented here. The TANSPEC has been made available to the worldwide astronomical community for science observations from October 2020., Comment: 35 pages, Accepted for publication in - Publications of the Astronomical Society of the Pacific (PASP)

The contactless estimation of the weight of a container and the amount of its content manipulated by a person are key pre-requisites for safe human-to-robot handovers. However, opaqueness and transparencies of the container and the content, and variability of materials, shapes, and sizes, make this estimation difficult. In this paper, we present a range of methods and an open framework to benchmark acoustic and visual perception for the estimation of the capacity of a container, and the type, mass, and amount of its content. The framework includes a dataset, specific tasks and performance measures. We conduct an in-depth comparative analysis of methods that used this framework and audio-only or vision-only baselines designed from related works. Based on this analysis, we can conclude that audio-only and audio-visual classifiers are suitable for the estimation of the type and amount of the content using different types of convolutional neural networks, combined with either recurrent neural networks or a majority voting strategy, whereas computer vision methods are suitable to determine the capacity of the container using regression and geometric approaches. Classifying the content type and level using only audio achieves a weighted average F1-score up to 81% and 97%, respectively. Estimating the container capacity with vision-only approaches and estimating the filling mass with audio-visual multi-stage approaches reach up to 65% weighted average capacity and mass scores. These results show that there is still room for improvement on the design of new methods. These new methods can be ranked and compared on the individual leaderboards provided by our open framework., Comment: Authors' post-print accepted for publication in IEEE Access, see https://doi.org/10.1109/ACCESS.2022.3166906 . 14 pages, 6 tables, 7 figures

The recently commissioned 3.6-m Devasthal optical telescope has been used for various tests and science observations using three main instruments, namely, a charge-coupled device camera, a near-infrared camera, and an optical imager-cum-spectrograph. The published results from these instruments assert that the performance of the telescope at the Devasthal site is at par with the expectations. These back-end instruments open up vast opportunities for high-sensitivity observations of the celestial sky with the telescope. This paper provides a summary of the existing back-end instruments and attempts to highlight the importance of the Devasthal optical telescope in synergy with other telescopes operating at different wavelengths., Comment: Review invited talk in second Belgo-Indian Network for Astronomy & astrophysics (BINA) conference, to appear in Bull. Liege Royal Society of Sciences (2019)

We present results of a search for variable stars in a region of the globular cluster NGC 4147 based on photometric observations with 4k x 4k CCD imager mounted at the axial port of the recently installed 3.6 m Devasthal optical telescope at Aryabhatta Research Institute of Observational Sciences, Nainital, India. We performed time series photometry of NGC 4147 in V and R bands, and identified 42 periodic variables in the region of NGC 4147, 28 of which have been detected for the first time. Seventeen variable stars are located within the half light radius $\lesssim$ 0.48 arcmin, of which 10 stars are newly identified variables. Two of 10 variables are located within the core radius $\lesssim$ 0.09 arcmin. Based on the location in the $V/(V-R)$ colour magnitude diagram and variability characteristics, 7, 8, 5 and 1 newly identified probable member variables are classified as RRc, EA/E, EW and SX Phe, respectively. The metallicity of NGC 4147 estimated from light curves of RRab and RRc stars with the help of Fourier decomposition is found to be characteristics of Oosterhoff II. The distance derived using light curves of RRab stars is consistent with that obtained from the observed $V/(V-R)$ colour-magnitude diagram., Comment: 20 pages, 13 Figures, accepted for publication in Astronomical Journal

A low dispersion spectrograph-cum-imager has been developed and assembled in ARIES, Nainital. The optical design of the spectrograph consists of a collimator and a focal reducer converting the f/9 beam from the 3.6-m Devasthal optical telescope to a nearly f/4.3 beam. The instrument is capable of carrying out broad-band imaging, narrow-band imaging and low-resolution ({\lambda}/{\Delta}{\lambda}<2000) slit spectroscopy in the wavelength range 350-1050 nm. A closed-cycle cryogenically cooled charge-coupled device camera, also assembled in ARIES, is used as the main imaging device for the spectrograph. The first images from the spectrograph on the telescope assert seeing-limited performance free from any significant optical aberration. An i-band image of the galaxy cluster Abell 370 made using the spectrograph shows faint sources down to ~25 mag. The quality and sensitivity of the optical spectrums of the celestial sources obtained from the spectrograph are as per the expectations from a 3.6-m telescope. Several new modes of observations such as polarimetry, fast-imaging, and monitoring of the atmospheric parameters are being included in the spectrograph. Using a test setup, single optical pulses from the Crab pulsar were detected from the telescope. The spectrograph is one of the main back-end instruments on the 3.6-m telescope for high sensitivity observations of celestial objects., Comment: 8 pages, 6 figures, Accepted in Current Science (CSci; Indian Academy of Sciences)

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should learn to associate components in the sketch (say, feet, tail, etc.) with the corresponding components in the image having similar shape characteristics. However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same shape characteristics as in the sketch. As a result, existing methods simply learn to associate sketches with classes seen during training and hence fail to generalize to unseen classes. In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated in novel classes that are not seen during training. We show through extensive experiments that existing models for SBIR that are trained in a discriminative setting learn only class specific mappings and fail to generalize to the proposed zero-shot setting. To circumvent this, we propose a generative approach for the SBIR task by proposing deep conditional generative models that take the sketch as an input and fill the missing information stochastically. Experiments on this new benchmark created from the "Sketchy" dataset, which is a large-scale database of sketch-photo pairs demonstrate that the performance of these generative models is significantly better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task., Comment: Accepted in ECCV 2018, Munich Germany

Video games have become an integral part of most people's lives in recent times. This led to an abundance of data related to video games being shared online. However, this comes with issues such as incorrect ratings, reviews or anything that is being shared. Recommendation systems are powerful tools that help users by providing them with meaningful recommendations. A straightforward approach would be to predict the scores of video games based on other information related to the game. It could be used as a means to validate user-submitted ratings as well as provide recommendations. This work provides a method to predict the G-Score, that defines how good a video game is, from its trailer (video) and summary (text). We first propose models to predict the G-Score based on the trailer alone (unimodal). Later on, we show that considering information from multiple modalities helps the models perform better compared to using information from videos alone. Since we couldn't find any suitable multimodal video game dataset, we created our own dataset named VGD (Video Game Dataset) and provide it along with this work. The approach mentioned here can be generalized to other multimodal datasets such as movie trailers and summaries etc. Towards the end, we talk about the shortcomings of the work and some methods to overcome them., Comment: ICPRAI-18

TIFR Near Infrared Imaging Camera-II is a closed-cycle Helium cryo-cooled imaging camera equipped with a Raytheon 512 x 512 pixels InSb Aladdin III Quadrant focal plane array having sensitivity to photons in the 1-5 microns wavelength band. In this paper, we present the performance of the camera on the newly installed 3.6-m Devasthal Optical Telescope (DOT) based on the calibration observations carried out during 2017 May 11-14 and 2017 October 7-31. After the preliminary characterization, the camera has been released to the Indian and Belgian astronomical community for science observations since 2017 May. The camera offers a field-of-view of ~86.5 arcsec x 86.5 arcsec on the DOT with a pixel scale of 0.169 arcsec. The seeing at the telescope site in the near-infrared bands is typically sub-arcsecond with the best seeing of ~0.45 arcsec realized in the near-infrared K-band on 2017 October 16. The camera is found to be capable of deep observations in the J, H and K bands comparable to other 4-m class telescopes available world-wide. Another highlight of this camera is the observational capability for sources up to Wide-field Infrared Survey Explorer (WISE) W1-band (3.4 microns) magnitudes of 9.2 in the narrow L-band (nbL; lambda_{cen} ~3.59 microns). Hence, the camera could be a good complementary instrument to observe the bright nbL-band sources that are saturated in the Spitzer-Infrared Array Camera ([3.6] <= 7.92 mag) and the WISE W1-band ([3.4] <= 8.1 mag). Sources with strong polycyclic aromatic hydrocarbon (PAH) emission at 3.3 microns are also detected. Details of the observations and estimated parameters are presented in this paper., Comment: 16 pages, 12 figures, 1 table, Accepted for publication in the Journal of Astronomical Instrumentation