Objective quality assessment of 3D point clouds is essential for the development of immersive multimedia systems in real-world applications. Despite the success of perceptual quality evaluation for 2D images and videos, blind/no-reference metrics are still scarce for 3D point clouds with large-scale irregularly distributed 3D points. Therefore, in this paper, we propose an objective point cloud quality index with Structure Guided Resampling (SGR) to automatically evaluate the perceptually visual quality of 3D dense point clouds. The proposed SGR is a general-purpose blind quality assessment method without the assistance of any reference information. Specifically, considering that the human visual system (HVS) is highly sensitive to structure information, we first exploit the unique normal vectors of point clouds to execute regional pre-processing which consists of keypoint resampling and local region construction. Then, we extract three groups of quality-related features, including: 1) geometry density features; 2) color naturalness features; 3) angular consistency features. Both the cognitive peculiarities of the human brain and naturalness regularity are involved in the designed quality-aware features that can capture the most vital aspects of distorted 3D point clouds. Extensive experiments on several publicly available subjective point cloud quality databases validate that our proposed SGR can compete with state-of-the-art full-reference, reduced-reference, and no-reference quality assessment algorithms.
There has been a growing interest in developing image super-resolution (SR) algorithms that convert low-resolution (LR) to higher resolution images, but automatically evaluating the visual quality of super-resolved images remains a challenging problem. Here we look at the problem of SR image quality assessment (SR IQA) in a two-dimensional (2D) space of deterministic fidelity (DF) versus statistical fidelity (SF). This allows us to better understand the advantages and disadvantages of existing SR algorithms, which produce images at different clusters in the 2D space of (DF, SF). Specifically, we observe an interesting trend from more traditional SR algorithms that are typically inclined to optimize for DF while losing SF, to more recent generative adversarial network (GAN) based approaches that by contrast exhibit strong advantages in achieving high SF but sometimes appear weak at maintaining DF. Furthermore, we propose an uncertainty weighting scheme based on content-dependent sharpness and texture assessment that merges the two fidelity measures into an overall quality prediction named the Super Resolution Image Fidelity (SRIF) index, which demonstrates superior performance against state-of-the-art IQA models when tested on subject-rated datasets.
Coronary CT Angiography (CCTA) is susceptible to various distortions (e.g., artifacts and noise), which severely compromise the exact diagnosis of cardiovascular diseases. The appropriate CCTA Vessel-level Image Quality Assessment (CCTA VIQA) algorithm can be used to reduce the risk of error diagnosis. The primary challenges of CCTA VIQA are that the local part of coronary that determines final quality is hard to locate. To tackle the challenge, we formulate CCTA VIQA as a multiple-instance learning (MIL) problem, and exploit Transformer-based MIL backbone (termed as T-MIL) to aggregate the multiple instances along the coronary centerline into the final quality. However, not all instances are informative for final quality. There are some quality-irrelevant/negative instances intervening the exact quality assessment(e.g., instances covering only background or the coronary in instances is not identifiable). Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA. Based on the above two modules, we propose a Reinforced Transformer Network (RTN) for automatic CCTA VIQA based on end-to-end optimization. Extensive experimental results demonstrate that our proposed method achieves the state-of-the-art performance on the real-world CCTA dataset, exceeding previous MIL methods by a large margin.
The emotion recognition in conversation (ERC) task aims to predict the emotion label of an utterance in a conversation. Since the dependencies between speakers are complex and dynamic, which consist of intra- and inter-speaker dependencies, the modeling of speaker-specific information is a vital role in ERC. Although existing researchers have proposed various methods of speaker interaction modeling, they cannot explore dynamic intra- and inter-speaker dependencies jointly, leading to the insufficient comprehension of context and further hindering emotion prediction. To this end, we design a novel speaker modeling scheme that explores intra- and inter-speaker dependencies jointly in a dynamic manner. Besides, we propose a Speaker-Guided Encoder-Decoder (SGED) framework for ERC, which fully exploits speaker information for the decoding of emotion. We use different existing methods as the conversational context encoder of our framework, showing the high scalability and flexibility of the proposed framework. Experimental results demonstrate the superiority and effectiveness of SGED.
Blind image quality assessment (BIQA), which aims to accurately predict the image quality without any pristine reference information, has been highly concerned in the past decades. Especially, with the help of deep neural networks, great progress has been achieved so far. However, it remains less investigated on BIQA for night-time images (NTIs) which usually suffer from complicated authentic distortions such as reduced visibility, low contrast, additive noises, and color distortions. These diverse authentic degradations particularly challenges the design of effective deep neural network for blind NTI quality evaluation (NTIQE). In this paper, we propose a novel deep decomposition and bilinear pooling network (DDB-Net) to better address this issue. The DDB-Net contains three modules, i.e., an image decomposition module, a feature encoding module, and a bilinear pooling module. The image decomposition module is inspired by the Retinex theory and involves decoupling the input NTI into an illumination layer component responsible for illumination information and a reflectance layer component responsible for content information. Then, the feature encoding module involves learning multi-scale feature representations of degradations that are rooted in the two decoupled components separately. Finally, by modeling illumination-related and content-related degradations as two-factor variations, the two multi-scale feature sets are bilinearly pooled and concatenated together to form a unified representation for quality prediction. The superiority of the proposed DDB-Net is well validated by extensive experiments on two publicly available night-time image databases.
The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions and causes as pairs from documents. We observe that the relative distance distribution of emotions and causes is extremely imbalanced in the typical ECPE dataset. Existing methods have set a fixed size window to capture relations between neighboring clauses. However, they neglect the effective semantic connections between distant clauses, leading to poor generalization ability towards position-insensitive data. To alleviate the problem, we propose a novel \textbf{M}ulti-\textbf{G}ranularity \textbf{S}emantic \textbf{A}ware \textbf{G}raph model (MGSAG) to incorporate fine-grained and coarse-grained semantic features jointly, without regard to distance limitation. In particular, we first explore semantic dependencies between clauses and keywords extracted from the document that convey fine-grained semantic features, obtaining keywords enhanced clause representations. Besides, a clause graph is also established to model coarse-grained semantic relations between clauses. Experimental results indicate that MGSAG surpasses the existing state-of-the-art ECPE models. Especially, MGSAG outperforms other models significantly in the condition of position-insensitive data.
As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated neural network models of growing size and increasing training epochs. While strong computation resources seem to be the prerequisite of training superior models, we try to overcome it by carefully designing a more efficient training pipeline. In this work, we propose an efficient 3-stage progressive training pipeline to build highly-performing neural transducer models from scratch with very limited computation resources in a reasonable short time period. The effectiveness of each stage is experimentally verified on both Librispeech and Switchboard corpora. The proposed pipeline is able to train transducer models approaching state-of-the-art performance with a single GPU in just 2-3 weeks. Our best conformer transducer achieves 4.1% WER on Librispeech test-other with only 35 epochs of training.
This paper presents a High-altitude infrared thermal dataset, HIT-UAV, for object detection applications on Unmanned Aerial Vehicles (UAVs). HIT-UAV contains 2898 infrared thermal images extracted from 43470 frames. These images are collected by UAV from schools, parking lots, roads, playgrounds, etc. HIT-UAV provides different flight data for each place, including flight altitude (from 60 to 130 meters), camera perspective (from 30 to 90 degrees), date, and daylight intensity. For each image, the HIT-UAV manual annotates object instances with two types of the bounding box (oriented and standard) to address the challenge that object instances have a significant overlap in aerial images. To the best of our knowledge, HIT-UAV is the first publicly available high-altitude infrared thermal UAV dataset for persons and vehicles detection. Moreover, we trained and evaluated the benchmark detection algorithms (YOLOv4 and YOLOv4-tiny) on HIT-UAV. Compared to the visual light dataset, the detection algorithms have excellent performance on HIT-UAV because the infrared thermal images do not contain a significant quantity of irrelevant information with detection objects. This indicates that infrared thermal datasets can significantly promote the development of object detection applications. We hope HIT-UAV contributes to UAV applications such as traffic surveillance and city monitoring at night. The dataset is available at https://github.com/suojiashun/HIT-UAV-Infrared-Thermal-Dataset.
Recently, leveraging BERT pre-training to improve the phoneme encoder in text to speech (TTS) has drawn increasing attention. However, the works apply pre-training with character-based units to enhance the TTS phoneme encoder, which is inconsistent with the TTS fine-tuning that takes phonemes as input. Pre-training only with phonemes as input can alleviate the input mismatch but lack the ability to model rich representations and semantic information due to limited phoneme vocabulary. In this paper, we propose MixedPhoneme BERT, a novel variant of the BERT model that uses mixed phoneme and sup-phoneme representations to enhance the learning capability. Specifically, we merge the adjacent phonemes into sup-phonemes and combine the phoneme sequence and the merged sup-phoneme sequence as the model input, which can enhance the model capacity to learn rich contextual representations. Experiment results demonstrate that our proposed Mixed-Phoneme BERT significantly improves the TTS performance with 0.30 CMOS gain compared with the FastSpeech 2 baseline. The Mixed-Phoneme BERT achieves 3x inference speedup and similar voice quality to the previous TTS pre-trained model PnG BERT
Quality of experience (QoE) assessment for adaptive video streaming plays a significant role in advanced network management systems. It is especially challenging in case of dynamic adaptive streaming schemes over HTTP (DASH) which has increasingly complex characteristics including additional playback issues. In this paper, we provide a brief overview of adaptive video streaming quality assessment. Upon our review of related works, we analyze and compare different variations of objective QoE assessment models with or without using machine learning techniques for adaptive video streaming. Through the performance analysis, we observe that hybrid models perform better than both quality-of-service (QoS) driven QoE approaches and signal fidelity measurement. Moreover, the machine learning-based model slightly outperforms the model without using machine learning for the same setting. In addition, we find that existing video streaming QoE assessment models still have limited performance, which makes it difficult to be applied in practical communication systems. Therefore, based on the success of deep learned feature representations for traditional video quality prediction, we also apply the off-the-shelf deep convolutional neural network (DCNN) to evaluate the perceptual quality of streaming videos, where the spatio-temporal properties of streaming videos are taken into consideration. Experiments demonstrate its superiority, which sheds light on the future development of specifically designed deep learning frameworks for adaptive video streaming quality assessment. We believe this survey can serve as a guideline for QoE assessment of adaptive video streaming.