اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDo Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification
112
0
0.0
(
0
)
نشر من قبل
Bharathi Raja Chakravarthi
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
A meme is an part of media created to share an opinion or emotion across the internet. Due to its popularity, memes have become the new forms of communication on social media. However, due to its nature, they are being used in harmful ways such as trolling and cyberbullying progressively. Various data modelling methods create different possibilities in feature extraction and turning them into beneficial information. The variety of modalities included in data plays a significant part in predicting the results. We try to explore the significance of visual features of images in classifying memes. Memes are a blend of both image and text, where the text is embedded into the image. We try to incorporate the memes as troll and non-trolling memes based on the images and the text on them. However, the images are to be analysed and combined with the text to increase performance. Our work illustrates different textual analysis methods and contrasting multimodal methods ranging from simple merging to cross attention to utilising both worlds - best visual and textual features. The fine-tuned cross-lingual language model, XLM, performed the best in textual analysis, and the multimodal transformer performs the best in multimodal analysis.
قيم البحث
اقرأ أيضاً
Recently, a boom of papers have shown extraordinary progress in few-shot learning with various prompt-based models. Such success can give the impression that prompts help models to learn faster in the same way that humans learn faster when provided w
ith task instructions expressed in natural language. In this study, we experiment with over 30 prompts manually written for natural language inference (NLI). We find that models learn just as fast with many prompts that are intentionally irrelevant or even pathologically misleading as they do with instructively good prompts. Additionally, we find that model performance is more dependent on the choice of the LM target words (a.k.a. the verbalizer that converts LM vocabulary prediction to class labels) than on the text of the prompt itself. In sum, we find little evidence that suggests existing prompt-based models truly understand the meaning of their given prompts.
In 2010 the first planet was discovered around star HD 34445. Recently, another five planets were announced orbiting the same star. It is a rather dense multi-planet system with some of its planets having separations of fractions of an au and minimum
masses ranging from Neptune to sub-Jupiter ones. Given the number of planets and the various uncertainties in their masses and orbital elements, the HD 34445 planetary system is quite interesting as there is the potential for mean motion and secular resonances that could render the outcome of its dynamical evolution and fate an open question. In this paper we investigate the dynamical stability of the six planet system in order to check the validity of the orbital solution acquired. This is achieved by a series of numerical experiments, where the dynamical evolution of the system is tested on different timescales. We vary the orbital elements and masses of the system within the error ranges provided. We find that for a large area of the parameter space we can produce stable configurations and therefore conclude it is very likely that the HD 34445 planetary system is real. Some discussion about the potential habitability of the system is also done.
Recently, Yuan et al. (2016) have shown the effectiveness of using Long Short-Term Memory (LSTM) for performing Word Sense Disambiguation (WSD). Their proposed technique outperformed the previous state-of-the-art with several benchmarks, but neither
the training data nor the source code was released. This paper presents the results of a reproduction study of this technique using only openly available datasets (GigaWord, SemCore, OMSTI) and software (TensorFlow). From them, it emerged that state-of-the-art results can be obtained with much less data than hinted by Yuan et al. All code and trained models are made freely available.
Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolut
ion filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $ell_1$-norm distance between filters and input feature as the output response. The influence of this new similarity measure on the optimization of neural network have been thoroughly analyzed. To achieve a better performance, we develop a special back-propagation approach for AdderNets by investigating the full-precision gradient. We then propose an adaptive learning rate strategy to enhance the training procedure of AdderNets according to the magnitude of each neurons gradient. As a result, the proposed AdderNets can achieve 74.9% Top-1 accuracy 91.7% Top-5 accuracy using ResNet-50 on the ImageNet dataset without any multiplication in convolution layer. The codes are publicly available at: https://github.com/huaweinoah/AdderNet.
In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks. Instead of relying on hand-designed splitting strategies t
o obtain visual tokens and processing a large number of densely sampled patches for attention, our approach learns to mine important tokens in visual data. This results in efficiently and effectively finding a few important visual tokens and enables modeling of pairwise attention between such tokens, over a longer temporal horizon for videos, or the spatial content in images. Our experiments demonstrate strong performance on several challenging benchmarks for both image and video recognition tasks. Importantly, due to our tokens being adaptive, we accomplish competitive results at significantly reduced compute amount.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
