In this paper, we propose a new dataset, ReasonVQA, for the Visual Question Answering (VQA) task. Our dataset is automatically integrated with structured encyclopedic knowledge and constructed using a low-cost framework, which is capable of generating complex, multi-hop questions. We evaluated state-of-the-art VQA models on ReasonVQA, and the empirical results demonstrate that ReasonVQA poses significant challenges to these models, highlighting its potential for benchmarking and advancing the field of VQA. Additionally, our dataset can be easily scaled with respect to input images; the current version surpasses the largest existing datasets requiring external knowledge by more than an order of magnitude.

We study a low-complexity practical quantize-and-forward (QF) scheme, a special case of the compress-and-forward (CF) transmission for half-duplex relay systems. By adjusting the number of quantization levels, we show that significant performance improvement can be achieved even though the relay node does not exploit any correlation information with the signal received at the destination. We demonstrate the performance of our scheme using 16QAM as the modulation and Turbo Code as the channel coding, and compare its performance against the decode-and-forward (DF) scheme. An approximately 2 dB gain is shown to be achievable at a target error rate of 10-4in the scenario where the relay is close to destination.