Search By Subject

Text-to-image generation aims to generate images from text descriptions. Its main challenge lies in two aspects: (1) Semantic consistency, i.e., the generated images should be semantically consistent with the input text; (2) Visual reality, i.e., the ...

Image-text retrieval aims to take the text (image) query to retrieve the semantically relevant images (texts), which is fundamental and critical in the search system, online shopping, and social network. Existing works have shown the effectiveness of ...

Encoder-decoder model encodes input sentences to hidden representations and decodes the representations to the output in unidirectional way. We introduce a bidirectional encoder decoder model that adds a reverse decoder-encoder for the feedback from ...

Essay writing has become one of the most common learning tasks assigned to students enrolled in various courses at different educational levels, owing to the growing demand for future professionals to effectively communicate information to an audience ...

Interview has been regarded as one of the most crucial step for recruitment. To fully prepare for the interview with the recruiters, job seekers usually practice with mock interviews between each other. However, such a mock interview with peers is ...

Trajectory-User Linking (TUL) aiming to identify users of anonymous trajectories, has recently received increasing attention due to its wide range of applications, such as criminal investigation and personalized recommendation systems. In this paper, we ...

With the progress of Mars exploration, numerous Mars image data are being collected and need to be analyzed. However, due to the severe train-test gap and quality distortion of Martian data, the performance of existing computer vision models is ...

Deep neural networks have achieved remarkable success in HEVC compressed video quality enhancement. However, most existing multiframe-based methods either deliver unsatisfactory results or consume a significant amount of resources to leverage temporal ...

Intelligent transportation systems are predicted to change the way people live in the foreseeable future. Vehicular networks are one of the key enablers for such systems, yet no status-quo solutions of vehicular networks make practical deployments ...

Recent works on single image high dynamic range (HDR) reconstruction fail to hallucinate plausible textures, resulting in information missing and artifacts in large-scale under/over-exposed regions. In this article, a decoupled kernel prediction network ...

Recently, knowledge-grounded dialogue systems have gained increasing attention. Great efforts have been made to build response matching models where all dialogue content and knowledge sentences are leveraged. However, knowledge redundancy and distraction ...

Due to the diversity of the degradation process that is difficult to model, the recovery of mixed distorted images is still a challenging problem. The deep learning model trained under certain degradation declines significantly in other degradation ...

Vanilla Deep Neural Networks (DNN) after training are represented with native floating-point 32 (fp32) weights. We observe that the bit-level sparsity of these weights is very abundant in the mantissa and can be directly exploited to speed up model ...

Obtaining fine-grained structural information about building through ubiquitous sensors is crucial for assessing their aging and damage. However, due to the energy requirements, traditional sensors deployed in the building structure need frequent ...

Mutation faults are the core of mutation testing and have been widely used in many other software testing and debugging tasks. Hence, constructing high-quality mutation faults is critical. There are many traditional mutation techniques that construct ...

The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, which hinders the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression plays a ...

Deep Reinforcement Learning (DRL) achieves great success in various domains. Communication in today's DRL algorithms takes non-negligible time compared to the computation. However, prior DRL frameworks usually focus on computation management while ...

Learning semantic sentence embeddings is beneficial to a variety of natural language processing tasks. Recently, methods using the contrastive learning framework to fine-tune pre-trained language models have been proposed and have achieved significant ...

Dialogues systems endow machines with the ability to converse with humans using natural language. Nonetheless, previous Seq2Seq-based generative dialogue systems often generate safe but meaningless responses, such as ‘I don't know’ or ...

In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative criteria is promising to boost the performance of end-to-end (E2E) ASR ...