Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGenerating Racing Game Commentary from Vision, Language, and Structured Data
توليد تعليق لعبة سباق من الرؤية واللغة والبيانات المنظمة
160
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقترح مهمة توليد التعليقات تلقائيا عن السباقات في لعبة سباق السيارات، من الرؤية والبيانات العددية والنصية المنظمة. توفر التعليقات معلومات لدعم المتفرجين في فهم الأحداث في السباقات. تحتاج نماذج توليد التعليق إلى تفسير وضع السباق وإنشاء المحتوى الصحيح في اللحظة المناسبة. نحن نقسم المهمة إلى قسمين فرعيين: تحديد توقيت الكلام وتوليد الكلام. نظرا لأن مجموعات البيانات الحالية لا تملك محاذاة بيانات في طرائق متعددة، لم يتم استكشاف هذا الإعداد بعمق. في هذه الدراسة، نقدم مجموعة بيانات جديدة واسعة النطاق تحتوي على بيانات الفيديو المحاذاة، والبيانات العددية المنظمة، والتعليقات المسجلة التي تتكون من 129226 كلمة في 1389 سباقا في لعبة. يكشف تحليلنا أن خصائص التعليقات تتغير مع مرور الوقت أو من وجهات النظر. تشير تجاربنا في المساحات الفرعية إلى أنه لا يزال يمثل تحديا لتشميز رؤية أحدث لرؤية معلومات مفيدة من مقاطع الفيديو لتوليد تعليقات دقيقة. نجعل مجموعة بيانات وتنفيذ خط الأساس متاحة للجمهور لمزيد من البحث.
We propose the task of automatically generating commentaries for races in a motor racing game, from vision, structured numerical, and textual data. Commentaries provide information to support spectators in understanding events in races. Commentary generation models need to interpret the race situation and generate the correct content at the right moment. We divide the task into two subtasks: utterance timing identification and utterance generation. Because existing datasets do not have such alignments of data in multiple modalities, this setting has not been explored in depth. In this study, we introduce a new large-scale dataset that contains aligned video data, structured numerical data, and transcribed commentaries that consist of 129,226 utterances in 1,389 races in a game. Our analysis reveals that the characteristics of commentaries change over time or from viewpoints. Our experiments on the subtasks show that it is still challenging for a state-of-the-art vision encoder to capture useful information from videos to generate accurate commentaries. We make the dataset and baseline implementation publicly available for further research.
References used
https://aclanthology.org/
rate research
Read More
Linguistic representations derived from text alone have been criticized for their lack of grounding, i.e., connecting words to their meanings in the physical world. Vision-and- Language (VL) models, trained jointly on text and image or video data, ha
ve been offered as a response to such criticisms. However, while VL pretraining has shown success on multimodal tasks such as visual question answering, it is not yet known how the internal linguistic representations themselves compare to their text-only counterparts. This paper compares the semantic representations learned via VL vs. text-only pretraining for two recent VL models using a suite of analyses (clustering, probing, and performance on a commonsense question answering task) in a language-only setting. We find that the multimodal models fail to significantly outperform the text-only variants, suggesting that future work is required if multimodal pretraining is to be pursued as a means of improving NLP in general.
Phrase grounding aims to map textual phrases to their associated image regions, which can be a prerequisite for multimodal reasoning and can benefit tasks requiring identifying objects based on language. With pre-trained vision-and-language models ac
hieving impressive performance across tasks, it remains unclear if we can directly utilize their learned embeddings for phrase grounding without fine-tuning. To this end, we propose a method to extract matched phrase-region pairs from pre-trained vision-and-language embeddings and propose four fine-tuning objectives to improve the model phrase grounding ability using image-caption data without any supervised grounding signals. Experiments on two representative datasets demonstrate the effectiveness of our objectives, outperforming baseline models in both weakly-supervised and supervised phrase grounding settings. In addition, we evaluate the aligned embeddings on several other downstream tasks and show that we can achieve better phrase grounding without sacrificing representation generality.
The limits of applicability of vision-and language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from task-specific d
atasets. This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We use an auxiliary training objective that encourages the learned representations to align with graph embeddings of matching entities in a KB. We empirically study the relevance of various KBs to multiple tasks and benchmarks. The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models. More surprisingly, the technique also benefits visual reasoning tasks (NLVR2, SNLI-VE). We perform probing experiments and show that the injection of additional knowledge regularizes the space of embeddings, which improves the representation of lexical and semantic similarities. The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.
Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In this paper,
we observe several key disadvantages of MLM in this setting. First, as captions tend to be short, in a third of the sentences no token is sampled. Second, the majority of masked tokens are stop-words and punctuation, leading to under-utilization of the image. We investigate a range of alternative masking strategies specific to the cross-modal setting that address these shortcomings, aiming for better fusion of text and image in the learned representation. When pre-training the LXMERT model, our alternative masking strategies consistently improve over the original masking strategy on three downstream tasks, especially in low resource settings. Further, our pre-training approach substantially outperforms the baseline model on a prompt-based probing task designed to elicit image objects. These results and our analysis indicate that our method allows for better utilization of the training data.
Writing mammography reports can be error-prone and time-consuming for radiologists. In this paper we propose a method to generate mammography reports given four images, corresponding to the four views used in screening mammography. To the best of our
knowledge our work represents the first attempt to generate the mammography report using deep-learning. We propose an encoder-decoder model that includes an EfficientNet-based encoder and a Transformer-based decoder. We demonstrate that the Transformer-based attention mechanism can combine visual and semantic information to localize salient regions on the input mammograms and generate a visually interpretable report. The conducted experiments, including an evaluation by a certified radiologist, show the effectiveness of the proposed method.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
