Question Answering
Jungo Kasai Keisuke Sakaguchi Y oichi T akahashi Ronan Le Bras Akari Asai
Why was the dataset created? Has the dataset been used already? QA dataset has already been used. QA establishes a framework to benchmark question answering at the present time: answers (e.g., the number of Shohei Ohtani's home runs) change in real time. This could also include the system's interactions with its information retrieval module (for How many instances are there?
QA: What's the Answer Right Now?
We build strong baseline models upon large pretrained language models, including GPT -3 and T5. Our benchmark is an ongoing effort, and this paper presents real-time evaluation results over the past year.
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
Medhini Narasimhan, Svetlana Lazebnik, Alexander Schwing
Accurately answering aquestionabout agivenimage requires combining observations with general knowledge. While this is effortless for humans, reasoning with general knowledge remains analgorithmic challenge. Toadvance research inthisdirection anovel'fact-based' visual question answering (FVQA) taskhas been introduced recently along with a large set of curated facts which link two entities, i.e., two possible answers, via a relation.
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering Supplementary Material Ziyi Bai, Ruiping Wang, Xilin Chen ziyi.bai@vipl.ict.ac.cn, {wangruiping, xlchen }@ict.ac.cn
As mentioned in Section 4.2 Our model can easily adapt to various video backbones. We use QA accuracy as the metric for evaluation. As illustrated in Section 3.2, with event-level annotations, we First, we analyze the effects of different loss functions on model performance. The results are shown in Figure 1. When the coefficient of any loss function is 0, the performance of the model decreases, which indicates their efficiency in event memory extraction. Without it, there is a significant decrease in model performance.
Glance and Focus: Memory Prompting for Multi-Event Video Question Answering Ziyi Bai
Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging.
Overcoming Language Priors in Visual Question Answering with Adversarial Regularization
Sainandan Ramakrishnan, Aishwarya Agrawal, Stefan Lee
Neural Information Processing Systems http://nips.cc/
Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions
Sara Magliacane, Thijs van Ommen, Tom Claassen, Stephan Bongers, Philip Versteeg, Joris M. Mooij
Neural Information Processing Systems http://nips.cc/
Chain of Reasoning for Visual Question Answering
Chenfei Wu, Jinlai Liu, Xiaojie Wang, Xuan Dong
Neural Information Processing Systems http://nips.cc/
RUBi: Reducing Unimodal Biases for Visual Question Answering
Remi Cadene, Corentin Dancette, Hedi Ben younes, Matthieu Cord, Devi Parikh
Human Attentionin Answering: Do Humansand Deep Networks Lookatthe Same Regions?
