This research is aimed to solve the tweet/user geolocation prediction task and provide a flexible methodology for the geotagging of textual big data. The suggested approach implements neural networks for natural language processing (NLP) to estimate the location as coordinate pairs (longitude, latitude) and two-dimensional Gaussian Mixture Models (GMMs). The scope of proposed models has been finetuned on a Twitter dataset using pretrained Bidirectional Encoder Representations from Transformers (BERT) as base models. Performance metrics show a median error of fewer than 30 km on a worldwide-level, and fewer than 15 km on the US-level datasets for the models trained and evaluated on text features of tweets' content and metadata context.
Wireless communication technology has progressed dramatically over the past 25 years, in terms of societal adoption as well as technical sophistication. In 1998, mobile phones were still in the process of becoming compact and affordable devices that could be widely utilized in both developed and developing countries. There were "only" 300 million mobile subscribers in the world [1]. Cellular networks were among the first privatized telecommunication markets, and competition turned the devices into fashion accessories with attractive designs that could be individualized. The service was circumscribed to telephony and text messaging, but it was groundbreaking in that, for the first time, telecommunication was between people rather than locations. Wireless networks have changed dramatically over the past few decades, enabling this revolution in service provisioning and making it possible to accommodate the ensuing dramatic growth in traffic. There are many contributing components, including new air interfaces for faster transmission, channel coding for enhanced reliability, improved source compression to remove redundancies, and leaner protocols to reduce overheads. Signal processing is at the core of these improvements, but nowhere has it played a bigger role than in the development of multiantenna communication. This article tells the story of how major signal processing advances have transformed the early multiantenna concepts into mainstream technology over the past 25 years. The story therefore begins somewhat arbitrarily in 1998. A broad account of the state-of-the-art signal processing techniques for wireless systems by 1998 can be found in [2], and its contrast with recent textbooks such as [3]-[5] reveals the dramatic leap forward that has taken place in the interim.
Visual Question Answering (VQA) and Image Captioning (CAP), which are among the most popular vision-language tasks, have analogous scene-text versions that require reasoning from the text in the image. Despite the obvious resemblance between them, the two are treated independently, yielding task-specific methods that can either see or read, but not both. In this work, we conduct an in-depth analysis of this phenomenon and propose UniTNT, a Unified Text-Non-Text approach, which grants existing multimodal architectures scene-text understanding capabilities. Specifically, we treat scene-text information as an additional modality, fusing it with any pretrained encoder-decoder-based architecture via designated modules. Thorough experiments reveal that UniTNT leads to the first single model that successfully handles both task types. Moreover, we show that scene-text understanding capabilities can boost vision-language models' performance on VQA and CAP by up to 3.49% and 0.7 CIDEr, respectively.
Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and completely ignore word information. Although Whole Word Masking can alleviate this, the semantics in words is still not well represented. In this paper, we revisit the segmentation granularity of Chinese PLMs. We propose a mixed-granularity Chinese BERT (MigBERT) by considering both characters and words. To achieve this, we design objective functions for learning both character and word-level representations. We conduct extensive experiments on various Chinese NLP tasks to evaluate existing PLMs as well as the proposed MigBERT. Experimental results show that MigBERT achieves new SOTA performance on all these tasks. Further analysis demonstrates that words are semantically richer than characters. More interestingly, we show that MigBERT also works with Japanese. Our code and model have been released here~\footnote{https://github.com/xnliang98/MigBERT}.
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image. This is inherently challenging: it essentially involves estimating the underlying 3D geometry while simultaneously hallucinating unseen textures. To address this challenge, we leverage prior knowledge from a well-trained 2D diffusion model to act as 3D-aware supervision for 3D creation. Our approach, Make-It-3D, employs a two-stage optimization pipeline: the first stage optimizes a neural radiance field by incorporating constraints from the reference image at the frontal view and diffusion prior at novel views; the second stage transforms the coarse model into textured point clouds and further elevates the realism with diffusion prior while leveraging the high-quality textures from the reference image. Extensive experiments demonstrate that our method outperforms prior works by a large margin, resulting in faithful reconstructions and impressive visual quality. Our method presents the first attempt to achieve high-quality 3D creation from a single image for general objects and enables various applications such as text-to-3D creation and texture editing.
We present the first 3D morphable modelling approach, whereby 3D face shape can be directly and completely defined using a textual prompt. Building on work in multi-modal learning, we extend the FLAME head model to a common image-and-text latent space. This allows for direct 3D Morphable Model (3DMM) parameter generation and therefore shape manipulation from textual descriptions. Our method, Text2Face, has many applications; for example: generating police photofits where the input is already in natural language. It further enables multi-modal 3DMM image fitting to sketches and sculptures, as well as images.
We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text. Shallow neural networks map the embeddings to a common dimensionality. Our system, which is an extension of our submission to the Language-based Audio Retrieval Task of the DCASE Challenge 2022, employs the RoBERTa foundation model as the text embedding extractor. A pretrained PANNs model extracts the audio embeddings. To improve the generalisation of our model, we investigate how pretraining with audio and associated noisy text collected from the online platform Freesound improves the performance of our method. Furthermore, our ablation study reveals that the proper choice of the loss function and fine-tuning the pretrained models are essential in training a competitive retrieval system.
Several websites improve their security and avoid dangerous Internet attacks by implementing CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart), a type of verification to identify whether the end-user is human or a robot. The most prevalent type of CAPTCHA is text-based, designed to be easily recognized by humans while being unsolvable towards machines or robots. However, as deep learning technology progresses, development of convolutional neural network (CNN) models that predict text-based CAPTCHAs becomes easier. The purpose of this research is to investigate the flaws and vulnerabilities in the CAPTCHA generating systems in order to design more resilient CAPTCHAs. To achieve this, we created CapNet, a Convolutional Neural Network. The proposed platform can evaluate both numerical and alphanumerical CAPTCHAs
Existing works on open-vocabulary semantic segmentation have utilized large-scale vision-language models, such as CLIP, to leverage their exceptional open-vocabulary recognition capabilities. However, the problem of transferring these capabilities learned from image-level supervision to the pixel-level task of segmentation and addressing arbitrary unseen categories at inference makes this task challenging. To address these issues, we aim to attentively relate objects within an image to given categories by leveraging relational information among class categories and visual semantics through aggregation, while also adapting the CLIP representations to the pixel-level task. However, we observe that direct optimization of the CLIP embeddings can harm its open-vocabulary capabilities. In this regard, we propose an alternative approach to optimize the image-text similarity map, i.e. the cost map, using a novel cost aggregation-based method. Our framework, namely CAT-Seg, achieves state-of-the-art performance across all benchmarks. We provide extensive ablation studies to validate our choices. Project page: https://ku-cvlab.github.io/CAT-Seg/.
The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. Our source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.