Search Results for author:
Found 192 papers, 66 papers with code
Intra-class Feature Variation Distillation for Semantic Segmentation
In this paper, different from previous methods performing knowledge distillation for densely pairwise relations, we propose a novel intra-class feature variation distillation (IFVD) to transfer the intra-class feature variation (IFV) of the cumbersome model (teacher) to the compact model (student).
Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion Cause Pair Extraction
Besides, a clause graph is also established to model coarse-grained semantic relations between clauses.
Uncertainty-aware Propagation Structure Reconstruction for Fake News Detection
In this paper, we propose a novel dual graph-based model, Uncertainty-aware Propagation Structure Reconstruction (UPSR) for improving fake news detection.
A Unified Propagation Forest-based Framework for Fake News Detection
Fake news’s quick propagation on social media brings severe social ramifications and economic damage.
Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering
In table question answering (TQA), tables are encoded as either texts or images.
Distance-aware Self-adaptive Graph Convolution for Fine-grained Hierarchical Recommendation
Graph Convolutional Networks (GCNs) are widely used to improve recommendation accuracy and performance by effectively learning the representations of user and item nodes.
Segment Any RGB-Thermal Model with Language-aided Distillation
Given that RGB-T provides a robust solution for scene understanding in adverse weather and lighting conditions, such as low light and overexposure, we propose a novel framework, SARTM, which customizes the powerful SAM for RGB-T semantic segmentation.
LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning
During incremental learning, EIM exploits some lightweight operations, called adapters, to effectively and efficiently learn features for new classes so that it can improve the accuracy of incremental learning while reducing model complexity as well as training overhead.
Behavioral Universe Network (BUN): A Behavioral Information-Based Framework for Complex Systems
Modern digital ecosystems feature complex, dynamic interactions among autonomous entities across diverse domains.
Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction
Therefore, we attempt to simultaneously analyze visual, auditory, and textual modalities in this paper, and propose TAVDiff, a Text-Audio-Visual-conditioned Diffusion Model for video saliency prediction.
DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment
Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motion perception - an increasing number of video quality assessment (VQA) works built upon this framework are proposed.
A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs' behavior in various tasks.
FeatInsight: An Online ML Feature Management System on 4Paradigm Sage-Studio Platform
Feature management is essential for many online machine learning applications and can often become the performance bottleneck (e. g., taking up to 70% of the overall latency in sales prediction service).
CrackSQL: A Hybrid SQL Dialect Translation System Powered by Large Language Models
Dialect translation plays a key role in enabling seamless interaction across heterogeneous database systems.
Feature Calibration enhanced Parameter Synthesis for CLIP-based Class-incremental Learning
Specifically, FCPS introduces a dynamic parameter adjustment mechanism that iteratively calibrates the contribution of original visual features to the final class decision, thus preserving the model's intrinsic generalization capability across modalities.
InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images
This paper presents InteractEdit, a novel framework for zero-shot Human-Object Interaction (HOI) editing, addressing the challenging task of transforming an existing interaction in an image into a new, desired interaction while preserving the identities of the subject and object.
An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding
Firstly, a shared information maximization principle is proposed to learn more sufficient shared representations for all target tasks.
Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions
Thus, perceptual visual quality assessment (PVQA), which focuses on evaluating the quality of multimedia content based on human perception, is essential for optimizing user experiences in advanced communication systems.
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges.
GP-GS: Gaussian Processes for Enhanced Gaussian Splatting
3D Gaussian Splatting has emerged as an efficient photorealistic novel view synthesis method.
CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIP
Blind dehazed image quality assessment (BDQA), which aims to accurately predict the visual quality of dehazed images without any reference information, is essential for the evaluation, comparison, and optimization of image dehazing algorithms.
PromptMono: Cross Prompting Attention for Self-Supervised Monocular Depth Estimation in Challenging Environments
Considerable efforts have been made to improve monocular depth estimation under ideal conditions.
OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML
Efficient and consistent feature computation is crucial for a wide range of online ML applications.
Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering
In this paper, we propose Multi-Agent Collaboration with Tool use (MACT), a framework that requires neither closed-source models nor fine-tuning.
TINQ: Temporal Inconsistency Guided Blind Video Quality Assessment
Temporal inconsistency, referring to irregularities between consecutive frames, is relevant to video quality.
D-Judge: How Far Are We? Evaluating the Discrepancies Between AI-synthesized Images and Natural Images through Multimodal Guidance
In Artificial Intelligence Generated Content (AIGC), distinguishing AI-synthesized images from natural ones remains a key challenge.
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
To address this, we propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically route computation across layers and timesteps for each image token, resulting in efficient DiTs.
From General to Specific: Tailoring Large Language Models for Personalized Healthcare
The rapid development of large language models (LLMs) has transformed many industries, including healthcare.
Ancient DNA from 120-Million-Year-Old Lycoptera Fossils Reveals Evolutionary Insights
Using this method, we identified 243 original in situ DNA (oriDNA) sequences, likely from the Lycoptera genome.
Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
In this paper, we introduce \textbf{FineRob}, a novel fine-grained behavior simulation dataset.
Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey
This review provides a unified framework bridging low-level and high-level perception tasks, systematically analyzes current limitations and solutions, and presents a structured roadmap for integrating emerging technologies, particularly foundation models, to enhance TSS capabilities.
CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
CTC compressor can be an effective approach to integrate audio encoders to decoder-only models, which has gained growing interest for different speech applications.
No-Reference Point Cloud Quality Assessment via Graph Convolutional Network
Finally, reasoning on the constructed graph is performed by GCN to characterize the mutual dependencies and interactions between different projected images, and aggregate feature information of multi-view projected images for final quality prediction.
A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning
To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity.
Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights.
Efficient Streaming LLM for Speech Recognition
Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities.
Perceptual Depth Quality Assessment of Stereoscopic Omnidirectional Images
Experimental results demonstrate that the proposed method outperforms state-of-the-art image quality assessment (IQA) and depth quality assessment (DQA) approaches in predicting the perceptual depth quality when tested using both single-viewport and omnidirectional stereoscopic image databases.
Data-Guided Physics-Informed Neural Networks for Solving Inverse Problems in Partial Differential Equations
In the pre-training phase, a loss function with only the data loss is minimized in a neural network.
Transferring Structure Knowledge: A New Task to Fake news Detection Towards Cold-Start Propagation
To achieve the task, we design a simple but effective Structure Adversarial Net (SAN) framework to learn transferable features from available propagation to boost the detection of content-only samples.
MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts
Currently, the mainstream routing methods include dynamic routing and fixed routing.
Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition
Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency.
Token-Weighted RNN-T for Learning from Flawed Data
ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence.
Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessment
This is not enough for adapting CLIP models to AI generated image quality assessment (AGIQA) since AGIs visually differ from natural images.
LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detection
It is worth noting that LiSD achieves the state-of-the-art performance of 83. 3% mIoU on the nuScenes segmentation benchmark for lidar-only methods.
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM, achieving average perplexity improvements of 5. 6 and 22. 7 points at comparable or lower latency compared to the most competitive quantized LLMs at 3 and 2 bits, respectively, and more than 80% memory and energy reductions over the original LLMs.
Representation Learning with Conditional Information Flow Maximization
This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task.
OCDB: Revisiting Causal Discovery with a Comprehensive Benchmark and Evaluation Framework
Causal discovery offers a promising approach to improve transparency and reliability.
Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
Specifically, by restructuring the training objectives -- removing the answer from outputs and concatenating the question with the rationale as input -- CasCoD's two-step learning process ensures that students focus on learning rationales without interference from the preset answers, thus improving reasoning generalizability.
Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
Further analysis shows that EDIT can generate high-quality CoTs with more correct key reasoning steps.
Perceptual Crack Detection for Rendered 3D Textured Meshes
Extensive experiments on large-scale public datasets of 3D textured meshes demonstrate effectiveness and efficiency of the proposed PCD method in correct localization and detection of crack artifacts.
Exploring Correlations of Self-Supervised Tasks for Graphs
Specifically, we evaluate the performance of the representations trained by one specific task on other tasks and define correlation values to quantify task correlations.
FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering
To investigate these aspects, we create and publish a novel TQA evaluation benchmark in English.
Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment
Specifically, inspired by the characteristics of the human visual system and motivated by the observation that "visual quality" and "authenticity" are characterized by both local and global aspects, AMFF-Net scales the image up and down and takes the scaled images and original-sized image as the inputs to obtain multi-scale features.
STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness.
Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings
Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour.
Multi-view Intent Learning and Alignment with Large Language Models for Session-based Recommendation
To address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views.
Towards Loose-Fitting Garment Animation via Generative Model of Deformation Decomposition
Existing data-driven methods for garment animation, usually driven by linear skinning, although effective on tight garments, do not handle loose-fitting garments with complex deformations well.
Structured Probabilistic Coding
It can enhance the generalization ability of pre-trained language models for better language understanding.
SSTA: Salient Spatially Transformed Attack
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world.
DTA: Distribution Transform-based Attack for Query-Limited Scenario
In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in thousands of trials during an attack.
Are Large Language Models Good Fact Checkers: A Preliminary Study
However, they encounter challenges in effectively handling Chinese fact verification and the entirety of the fact-checking pipeline due to language inconsistencies and hallucinations.
Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Hence, it provides a way to directly generate stego images from secret images without a cover image.
Explore the Potential of LLMs in Misinformation Detection: An Empirical Study
Our empirical studies on eight misinformation detection datasets show that LLM-based detectors can achieve comparable performance in text-based misinformation detection but exhibit notably constrained capabilities in comprehending propagation structure compared to existing models in propagation-based misinformation detection.
Enhancing English Writing Proficiency in China's Polytechnic Students An In-Depth Literature Review on the Application of the Input Hypothesis
The study will include real-life observations and experiments from the previous research.
MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
Experiments reveal that models incorporating the proposed MiLe Loss can gain consistent performance improvement on downstream benchmarks.
CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability
Neural network models are vulnerable to adversarial examples, and adversarial transferability further increases the risk of adversarial attacks.
MeaeQ: Mount Model Extraction Attacks with Efficient Queries
We study model extraction attacks in natural language processing (NLP) where attackers aim to steal victim models by repeatedly querying the open Application Programming Interfaces (APIs).
Model Inversion Attacks on Homogeneous and Heterogeneous Graph Neural Networks
Inspired by this, we propose a novel model inversion attack method on HomoGNNs and HeteGNNs, namely HomoGMI and HeteGMI.
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack
However, the distribution of these fake data lacks diversity and cannot detect the decision boundary of the target model well, resulting in the dissatisfactory simulation effect.
Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?
With the rapid development of GPU (Graphics Processing Unit) technologies and neural networks, we can explore more appropriate data structures and algorithms.
AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings
Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks.
Novelty Detection in Reinforcement Learning with World Models
We refer to the sudden change in visual properties or state transitions as novelties.
Investigating the Effect of Language Models in Sequence Discriminative Training for Neural Transducers
In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers.
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models
Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models.
On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
Empirically, we show that ILM subtraction and sequence discriminative training achieve similar effects across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context.
HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus
In this paper, we demonstrate that detecting model-generated text in semantic-invariant tasks is more challenging.
E$^3$-UAV: An Edge-based Energy-Efficient Object Detection System for Unmanned Aerial Vehicles
We first present an effective evaluation metric for actual tasks and construct a transparent energy consumption model based on hundreds of actual flight data to formalize the relationship between energy consumption and flight parameters.
Dialogue Shaping: Empowering Agents through NPC Interaction
One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where the action space is extensive.
CASEIN: Cascading Explicit and Implicit Control for Fine-grained Emotion Intensity Regulation
However, these high-level semantic probabilities are often inaccurate and unsmooth at the phoneme level, leading to bias in learning.
Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history.
Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations
To address this, we propose a supervised adversarial contrastive learning (SACL) framework for learning class-spread structured representations in a supervised manner.
Ranked #5 on
Emotion Recognition in Conversation
on EmoryNLP
UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis
To alleviate these, we propose a generalized multilingual system SACL-XLMR for sentiment analysis on low-resource languages.
Ranked #1 on
Zero-shot Sentiment Classification
on AfriSenti
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition
Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only.
GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation
Local Transformer uses a dynamic graph to calculate all neighboring point weights by intra-domain cross-attention with dynamically updated graph relations, so that every neighboring point could affect the features of centroid with different weights; Global Transformer enlarges the receptive field of Local Transformer by a global self-attention.
VTPNet for 3D deep learning on point cloud
Recently, Transformer-based methods for point cloud learning have achieved good results on various point cloud learning benchmarks.
Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain
This task is non-trivial, due to three challenges: the logic of the generated text, unstructured style reference, and biased training samples.
Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona Distillation
Specifically, tabular data and persona information are firstly represented as latent variables separately.
JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization
These different actions are defined as conjoint actions, whose rest parts are definite phases, e. g., leaping over the bar in a HighJump.
BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding
Our experiments show that this combination can boost the decoding model's performance on certain tasks like fMRI-text matching and fMRI-to-image generation.
Blind Omnidirectional Image Quality Assessment: Integrating Local Statistics and Global Semantics
Omnidirectional image quality assessment (OIQA) aims to predict the perceptual quality of omnidirectional images that cover the whole 180$\times$360$^{\circ}$ viewing range of the visual environment.
Efficient 3D Object Reconstruction using Visual Transformers
Reconstructing a 3D object from a 2D image is a well-researched vision problem, with many kinds of deep learning techniques having been tried.
Story Shaping: Teaching Agents Human-like Behavior with Stories
We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge from an exemplar story of how to accomplish a task and intrinsically rewards itself for performing actions that make its current environment adhere to that of the inferred story world.
Reduced-Reference Quality Assessment of Point Clouds via Content-Oriented Saliency Projection
Many dense 3D point clouds have been exploited to represent visual objects instead of traditional images or videos.
COOP: Decoupling and Coupling of Whole-Body Grasping Pose Generation
To address this issue, we propose a novel framework called COOP (DeCOupling and COupling of Whole-Body GrasPing Pose Generation) to synthesize life-like whole-body poses that cover the widest range of human grasping capabilities.
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dehazed Image Quality Evaluation: From Partial Discrepancy to Blind Perception
Image dehazing aims to restore spatial details from hazy images.
Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation
Vessel segmentation is crucial in many medical image applications, such as detecting coronary stenoses, retinal vessel diseases and brain aneurysms.
Enhancing and Adversarial: Improve ASR with Speaker Labels
Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training.
Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing.
Monotonic segmental attention for automatic speech recognition
We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
KGCODE-Tab Results for SemTab 2022
This paper presents the results of KGCODE-Tab in the tabular data to knowledge graph matching contest SemTab 2022.
Ranked #1 on
Column Type Annotation
on ToughTables-DBP
Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning
Our proposed framework learns through real-time interactions between the digital human and customers dynamically through the state-of-art RL algorithms, combined with multimodal embedding and graph embedding, to improve the accuracy of personalization and thus enable the digital human agent to timely catch the attention of the customer.
An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data.
FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications
Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes.
Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling
Objective quality assessment of 3D point clouds is essential for the development of immersive multimedia systems in real-world applications.
Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity
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.
RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment
Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA.
Speaker-Guided Encoder-Decoder Framework for Emotion Recognition in 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.
Deep Decomposition and Bilinear Pooling Network for Blind Night-Time Image Quality Evaluation
The DDB-Net contains three modules, i. e., an image decomposition module, a feature encoding module, and a bilinear pooling module.
Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction
Besides, a clause graph is also established to model coarse-grained semantic relations between clauses.
Efficient Training of Neural Transducer for Speech Recognition
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.
HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection
We present the HIT-UAV dataset, a high-altitude infrared thermal dataset for object detection applications on Unmanned Aerial Vehicles (UAVs).
Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech
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.
A Brief Survey on Adaptive Video Streaming Quality Assessment
In this paper, we provide a brief overview of adaptive video streaming quality assessment.
Prediction of Listener Perception of Argumentative Speech in a Crowdsourced Dataset Using (Psycho-)Linguistic and Fluency Features
One of the key communicative competencies is the ability to maintain fluency in monologic speech and the ability to produce sophisticated language to argue a position convincingly.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Multi-agent Reinforcement Learning for Cooperative Lane Changing of Connected and Autonomous Vehicles in Mixed Traffic
In this paper, we formulate the lane-changing decision making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs.
Efficient Learning of Quadratic Variance Function Directed Acyclic Graphs via Topological Layers
Directed acyclic graph (DAG) models are widely used to represent causal relationships among random variables in many application domains.
Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design
It is shown that by adding another transformation, the proposed method is able to synthesize high-quality RAW Bayer images with arbitrary size.
On Language Model Integration for RNN Transducer based Speech Recognition
In this work, we study various ILM correction-based LM integration methods formulated in a common RNN-T framework.
AliMe MKG: A Multi-modal Knowledge Graph for Live-streaming E-commerce
Live streaming is becoming an increasingly popular trend of sales in E-commerce.
GGP: A Graph-based Grouping Planner for Explicit Control of Long Text Generation
With these two synergic representations, we then regroup these phrases into a fine-grained plan, based on which we generate the final long text.
SPMoE: Generate Multiple Pattern-Aware Outputs with Sparse Pattern Mixture of Experts
Each one-to-one mapping is associated with a conditional generation pattern and is modeled with an expert in SPMoE.
Transformer-Encoder-GRU (T-E-GRU) for Chinese Sentiment Analysis on Chinese Comment Text
Chinese sentiment analysis (CSA) has always been one of the challenges in natural language processing due to its complexity and uncertainty.
Label-Specific Dual Graph Neural Network for Multi-Label Text Classification
Multi-label text classification is one of the fundamental tasks in natural language processing.
Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds
Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MPVConv improves the accuracy of the backbone (PointNet) by up to \textbf{36\%}, and achieves higher accuracy than the voxel-based model with up to \textbf{34}$\times$ speedups.
Unsupervised Segmentation for Terracotta Warrior with Seed-Region-Growing CNN(SRG-Net)
Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds.
Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection
Detecting rumors on social media is a very critical task with significant implications to the economy, public health, etc.
A Fixed Version of Quadratic Program in Gradient Episodic Memory
Gradient Episodic Memory is indeed a novel method for continual learning, which solves new problems quickly without forgetting previously acquired knowledge.
PEN4Rec: Preference Evolution Networks for Session-based Recommendation
The process can strengthen the effect of relevant sequential behaviors during the preference evolution and weaken the disturbance from preference drifting.
Ranked #1 on
Session-Based Recommendations
on Last.FM
Challenging distributional models with a conceptual network of philosophical terms
We investigate the possibilities and limitations of using distributional semantic models for analyzing philosophical data by means of a realistic use-case.
Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality Assessment
In the hypergraph construction, we build a location-based hyperedge and a content-based hyperedge for each viewport.
Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness
In this paper, we assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness.
SRLF: A Stance-aware Reinforcement Learning Framework for Content-based Rumor Detection on Social Media
The rapid development of social media changes the lifestyle of people and simultaneously provides an ideal place for publishing and disseminating rumors, which severely exacerbates social panic and triggers a crisis of social trust.
Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34 times speedup.
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech
In recent years, automated approaches to assessing linguistic complexity in second language (L2) writing have made significant progress in gauging learner performance, predicting human ratings of the quality of learner productions, and benchmarking L2 development.
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a number of modeling architectures like encoder-decoder attention models, transducer models and segmental models (direct HMM).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Bayesian Graph Convolutional Network for Traffic Prediction
Under this framework, the graph structure is viewed as a random realization from a parametric generative model, and its posterior is inferred using the observed topology of the road network and traffic data.
No-Reference Quality Assessment for 360-degree Images by Analysis of Multi-frequency Information and Local-global Naturalness
To our knowledge, the proposed model is the first no-reference quality assessment method for 360-degreee images that combines multi-frequency information and image naturalness.
FedH2L: Federated Learning with Model and Statistical Heterogeneity
Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy.
Electronic transport properties and hydrostatic pressure effect of FeSe$_{0.67}$Te$_{0.33}$ single crystals free of phase separation
FeSe$_{1-x}$Te$_{x}$ superconductors manifest some intriguing electronic properties depending on the value of $x$.
Superconductivity Materials Science
Improving robustness of softmax corss-entropy loss via inference information
Several state-of-the-arts start from improving the inter-class separability of training samples by modifying loss functions, where we argue that the adversarial samples are ignored and thus limited robustness to adversarial attacks is resulted.
Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users Based on Weakly Supervised Learning
In this way, we can explicitly exploit the credibility of publishers and users for early fake news detection.
Deep Multi-Scale Features Learning for Distorted Image Quality Assessment
In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction.
Unsupervised Segmentation for Terracotta Warrior Point Cloud (SRG-Net)
Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds.
Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling.
Bayesian Spatio-Temporal Graph Convolutional Network for Traffic Forecasting
The graph structure in our network is learned from the physical topology of the road network and traffic data in an end-to-end manner, which discovers a more accurate description of the relationship among traffic flows.
Ranked #2 on
Traffic Prediction
on SZ-Taxi
Affinity Space Adaptation for Semantic Segmentation Across Domains
Specifically, we perform domain adaptation on the affinity relationship between adjacent pixels termed affinity space of source and target domain.
Residual Spatial Attention Network for Retinal Vessel Segmentation
In this work, we propose the Residual Spatial Attention Network (RSAN) for retinal vessel segmentation.
Empirical Fourier Decomposition: An Accurate Adaptive Signal Decomposition Method
An accurate adaptive signal decomposition method, called the empirical Fourier decomposition (EFD), is proposed to solve the problems in this work.
LIRA: Lifelong Image Restoration from Unknown Blended Distortions
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task.
Adaptive support driven Bayesian reweighted algorithm for sparse signal recovery
For example, sparse Bayesian learning (SBL) was proposed to learn major features from a dictionary of basis functions, which makes identified models interpretable.
Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions.
Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis
Furthermore, we design a Sentiment-based Rethinking mechanism (SR) by refining the HIN with sentiment label information to learn a more sentiment-aware document representation.
Rethinking Distributional Matching Based Domain Adaptation
In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.
DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction
For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance.
AutoSUM: Automating Feature Extraction and Multi-user Preference Simulation for Entity Summarization
In this paper, a novel integration method called AutoSUM is proposed for automatic feature extraction and multi-user preference simulation to overcome the drawbacks of previous methods.
A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e. g. byte-pair encoding (BPE).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks
Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions.
Channel Attention Residual U-Net for Retinal Vessel Segmentation
Retinal vessel segmentation is a vital step for the diagnosis of many early eye-related diseases.
Dense Residual Network for Retinal Vessel Segmentation
But for other retinal imaging modalities, more research is needed to explore vascular extraction.
Gradient-based Feature Extraction From Raw Bayer Pattern Images
In this paper, the impact of demosaicing on gradient extraction is studied and a gradient-based feature extraction pipeline based on raw Bayer pattern images is proposed.
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment
We present a complete training pipeline to build a state-of-the-art hybrid HMM-based ASR system on the 2nd release of the TED-LIUM corpus.
Online Meta-Critic Learning for Off-Policy Actor-Critic Methods
Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks.
Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification
Based on the two types of relations, we use a graph convolutional network to learn the deep correlations between styles automatically.
Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce
Information-seeking conversation system aims at satisfying the information needs of users through conversations.
Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots
Existing works mainly focus on matching candidate responses with every context utterance on multiple levels of granularity, which ignore the side effect of using excessive context information.
Ranked #5 on
Conversational Response Selection
on RRS
ALOHA: Artificial Learning of Human Attributes for Dialogue Agents
We propose Human Level Attributes (HLAs) based on tropes as the basis of a method for learning dialogue agents that can imitate the personalities of fictional characters.
Feature Fusion Detector for Semantic Cognition of Remote Sensing
Based on experiments on the remote sensing dataset from Google Earth, our LFFN has proved effective and practical for the semantic cognition of remote sensing, achieving 89% mAP which is 4. 1% higher than that of FPN.
Jointly embedding the local and global relations of heterogeneous graph for rumor detection
The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal platform for publishing and spreading rumors.
Learning review representations from user and product level information for spam detection
Then, we use orthogonal decomposition and fusion attention to learn a user, review, and product representation from the review information.
Tensor Oriented No-Reference Light Field Image Quality Assessment
Light field image (LFI) quality assessment is becoming more and more important, which helps to better guide the acquisition, processing and application of immersive media.
Binocular Rivalry Oriented Predictive Auto-Encoding Network for Blind Stereoscopic Image Quality Measurement
Stereoscopic image quality measurement (SIQM) has become increasingly important for guiding stereo image processing and commutation systems due to the widespread usage of 3D contents.
Multimedia Image and Video Processing
No-Reference Light Field Image Quality Assessment Based on Spatial-Angular Measurement
In this paper, we propose a No-Reference Light Field image Quality Assessment (NR-LFQA) scheme, where the main idea is to quantify the LFI quality degradation through evaluating the spatial quality and angular consistency.
An Intelligent Testing Strategy for Vocabulary Assessment of Chinese Second Language Learners
In this paper, we propose a novel testing strategy by combining automatic item generation (AIG) and computerized adaptive testing (CAT) in vocabulary assessment for Chinese L2 learners.
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring
LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models.
Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding Theory
In this paper, based on the predictive coding theory of the human vision system (HVS), we propose a stereoscopic omnidirectional image quality evaluator (SOIQE) to cope with the characteristics of 3D 360-degree images.
Spectral Perturbation Meets Incomplete Multi-view Data
In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering.
ESA: Entity Summarization with Attention
Entity summarization aims at creating brief but informative descriptions of entities from knowledge graphs.
Review-Driven Answer Generation for Product-Related Questions in E-Commerce
Then, we devise a mechanism to identify the relevant information from the noise-prone review snippets and incorporate this information to guide the answer generation.
Feature-Critic Networks for Heterogeneous Domain Generalization
The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training.
Ranked #121 on
Domain Generalization
on PACS
Hierarchical Reinforcement Learning for Multi-agent MOBA Game
Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information.
TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500.
Ranked #22 on
Scene Text Detection
on Total-Text
Unsupervised Single Image Deraining with Self-supervised Constraints
Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications.
Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
This paper presents a novel method for analysing the robustness of semantic segmentation models and provides a number of metrics to evaluate the classification performance over a variety of environmental conditions.
Data-driven Discovery of Cyber-Physical Systems
Cyber-physical systems (CPSs) embed software into the physical world.
Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles.
A Deep Relevance Model for Zero-Shot Document Filtering
In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand.
Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
Building multi-turn information-seeking conversation systems is an important and challenging research topic.
Histograms of Gaussian normal distribution for feature matching in clutter scenes
Especially in cluttered scenes there are many feature mismatches between scenes and models.
CFAR Line Detector for Polarimetric SAR Images Using Wilks’ Test Statistic
In this letter, a constant false-alarm rate line detector for polarimetric synthetic aperture radar (Pol-SAR) images is presented based on Wilks’ test statistic, which can be used to test the equality of two covariance matrices following the complex Wishart distribution.
