Most sign language handshape datasets are severely limited and unbalanced, posing significant challenges to effective model training. In this paper, we explore the effectiveness of augmenting the training data of a handshape classifier by generating synthetic data. We use an EfficientNet classifier trained on the RWTH German sign language handshape dataset, which is small and heavily unbalanced, applying different strategies to combine generated and real images. We compare two Generative Adversarial Networks (GAN) architectures for data generation: ReACGAN, which uses label information to condition the data generation process through an auxiliary classifier, and SPADE, which utilizes spatially-adaptive normalization to condition the generation on pose information. ReACGAN allows for the generation of realistic images that align with specific handshape labels, while SPADE focuses on generating images with accurate spatial handshape configurations. Our proposed techniques improve the current state-of-the-art accuracy on the RWTH dataset by 5%, addressing the limitations of small and unbalanced datasets. Additionally, our method demonstrates the capability to generalize across different sign language datasets by leveraging pose-based generation trained on the extensive HaGRID dataset. We achieve comparable performance to single-source trained classifiers without the need for retraining the generator.

The rise of large language models (LLMs) had a transformative impact on search, ushering in a new era of search engines that are capable of generating search results in natural language text, imbued with citations for supporting sources. Building generative information-seeking models demands openly accessible datasets, which currently remain lacking. In this paper, we introduce a new dataset, HAGRID (Human-in-the-loop Attributable Generative Retrieval for Information-seeking Dataset) for building end-to-end generative information-seeking models that are capable of retrieving candidate quotes and generating attributed explanations. Unlike recent efforts that focus on human evaluation of black-box proprietary search engines, we built our dataset atop the English subset of MIRACL, a publicly available information retrieval dataset. HAGRID is constructed based on human and LLM collaboration. We first automatically collect attributed explanations that follow an in-context citation style using an LLM, i.e. GPT-3.5. Next, we ask human annotators to evaluate the LLM explanations based on two criteria: informativeness and attributability. HAGRID serves as a catalyst for the development of information-seeking models with better attribution capabilities.

Last month, a YouTube user named demonflyingfox uploaded a video titled "Harry Potter by Balenciaga." It showed characters from the Harry Potter films--Hagrid, Ron, Hermione, Snape, McGonagall, Dobby--as gaunt models with aggressive cheekbones (slightly yassified), dressed in gothic capes and leather jackets. Set against a catwalk-worthy electronica beat, the actors blink, nod, and speak lines from the books which have been remixed with fashion references. "You are Balenciaga, Harry," Hagrid says, instead of breaking the news that Harry is a wizard. The video is strange and hilariously sinister.

The use of gestures in human communication plays an important role: gestures can reinforce statements emotionally or completely replace them. What is more, hand gesture recognition (HGR) can be a part of human-computer interaction. Such systems can be used in video conferencing services (Zoom, Skype, Discord, Jazz, etc.), home automation systems, the automotive sector, services for people with speech and hearing impairments, etc. Besides, the system can be a part of a virtual assistant or service for active sign language users -- hearing and speech-impaired people. These areas require the system to work online and be robust to background, scenes, subjects, and lighting conditions. These and several others problems inspired us to create a new HGR dataset.

First and foremost, it is a delicious fruit. But there is a double delight for fruit-lover data scientists! It is also a Python package that implements fast and flexible probabilistic models ranging from individual probability distributions to compositional models such as Bayesian networks and Hidden Markov Models. The central idea behind this package is that all probabilistic models can be viewed as a probability distribution. That means they all yield probability estimates for samples and can be updated/fitted given samples and their associated weights.