Search Results for author:
Found 76 papers, 20 papers with code
Understand before Answer: Improve Temporal Reading Comprehension via Precise Question Understanding
Precise question understanding is critical for temporal reading comprehension.
RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network
This work introduces RW-Net, a novel framework designed to address the challenges above by integrating Rate-Distortion Explanation (RDE) and wavelet transform into a state-of-the-art projection-based 3D object classification architecture.
Impact of Data Distribution on Fairness Guarantees in Equitable Deep Learning
We present a comprehensive theoretical framework analyzing the relationship between data distributions and fairness guarantees in equitable deep learning.
Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition
Moreover, existing methods for ambiguous actions often overemphasize local details, resulting in the loss of crucial global context, which further complicates the task of differentiating ambiguous actions.
Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum
To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system.
Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation
We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments.
3D Distance-color-coded Assessment of PCI Stent Apposition via Deep-learning-based Three-dimensional Multi-object Segmentation
Coronary artery disease poses a significant global health challenge, often necessitating percutaneous coronary intervention (PCI) with stent implantation.
Zero-shot Object Navigation with Vision-Language Models Reasoning
Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data.
RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
To address this challenge, we propose a novel relightable 3D object generative framework that automates the creation of 3D car assets, enabling the swift and accurate reconstruction of a vehicle's geometry, texture, and material properties from a single input image.
$\texttt{dattri}$: A Library for Efficient Data Attribution
Using the developed $\texttt{dattri}$ library, we are able to perform a comprehensive and fair benchmark analysis across a wide range of data attribution methods.
Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud
Our approach first introduces a \textit{\textbf{Curv}ature Diversity-driven Deformation \textbf{Rec}onstruction (CurvRec)} task, which effectively mitigates the gap between the source and target domains by enabling the model to extract salient features from semantically rich regions of a given point cloud.
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
The X-Prompt framework first pre-trains a video object segmentation foundation model using RGB data, and then utilize the additional modality of the prompt to adapt it to downstream multi-modal tasks with limited data.
A Review of Scalable and Privacy-Preserving Multi-Agent Frameworks for Distributed Energy Resources
To address this question, this paper considers two critical issues, namely privacy for processing DER data and scalability in optimizing DER operations, then surveys existing and emerging solutions from a multi-agent framework perspective.
Can LLMs Serve As Time Series Anomaly Detectors?
An emerging topic in large language models (LLMs) is their application to time series forecasting, characterizing mainstream and patternable characteristics of time series.
CUSIDE-array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations
Recently multi-channel end-to-end (ME2E) ASR systems have emerged.
FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification
However, the fairness issue under the setting of domain transfer is almost unexplored, while it is common that clinics rely on different imaging technologies (e. g., different retinal imaging modalities) for patient diagnosis.
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
Existing benchmarks mainly focus on modeling different types of constraints in human instructions while neglecting the composition of different constraints, which is an indispensable constituent in complex instructions.
Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision
We construct a common experimental setup based on the CommonVoice dataset, called CV-Lang10, with 10 seen languages and 2 unseen languages.
Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning.
DCNN: Dual Cross-current Neural Networks Realized Using An Interactive Deep Learning Discriminator for Fine-grained Objects
Accurate classification of fine-grained images remains a challenge in backbones based on convolutional operations or self-attention mechanisms.
Fine-Grained Image Classification
Weakly-supervised Learning
FairCLIP: Harnessing Fairness in Vision-Language Learning
Fairness is a critical concern in deep learning, especially in healthcare, where these models influence diagnoses and treatment decisions.
Towards Independence Criterion in Machine Unlearning of Features and Labels
This work delves into the complexities of machine unlearning in the face of distributional shifts, particularly focusing on the challenges posed by non-uniform feature and label removal.
SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images
To eliminate the reliance on such priors, we propose a novel Structure-aware Mixup and Invariance Learning framework (SA-MixNet) for weakly supervised road extraction that improves the model invariance in a data-driven manner.
Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides
Effective incident management is pivotal for the smooth operation of enterprises-level cloud services.
How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?
In the field of robotics and automation, navigation systems based on Large Language Models (LLMs) have recently shown impressive performance.
Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection
Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels.
Adapting OpenAI's Whisper for Speech Recognition on Code-Switch Mandarin-English SEAME and ASRU2019 Datasets
The Mixed Error Rate results show that the amount of adaptation data may be as low as $1\sim10$ hours to achieve saturation in performance gain (SEAME) while the ASRU task continued to show performance with more adaptation data ($>$100 hours).
Reprogramming Self-supervised Learning-based Speech Representations for Speaker Anonymization
Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity.
GhostVec: A New Threat to Speaker Privacy of End-to-End Speech Recognition System
This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech recognition (ASR) systems.
A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction
By combining the prompt and input image, a large vision-language model (i. e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt.
From Global to Local: Multi-scale Out-of-distribution Detection
Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
DUAW: Data-free Universal Adversarial Watermark against Stable Diffusion Customization
Stable Diffusion (SD) customization approaches enable users to personalize SD model outputs, greatly enhancing the flexibility and diversity of AI art.
SE-Bridge: Speech Enhancement with Consistent Brownian Bridge
Our experiments on multiple datasets demonstrate the effectiveness of SE-Bridge in SE.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Efficient Decision-based Black-box Patch Attacks on Video Recognition
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
An Extended Model for Ecological Robustness to Capture Power System Resilience
The RECO of resilient ecosystems favors a balance of food webs' network efficiency and redundancy.
Fashion Image Retrieval with Multi-Granular Alignment
In this paper, we propose a novel fashion image retrieval method leveraging both global and fine-grained features, dubbed Multi-Granular Alignment (MGA).
Ranked #3 on
Metric Learning
on In-Shop
T-SEA: Transfer-based Self-Ensemble Attack on Object Detection
Then, we analogize patch optimization with regular model optimization, proposing a series of self-ensemble approaches on the input data, the attacked model, and the adversarial patch to efficiently make use of the limited information and prevent the patch from overfitting.
Speech-text based multi-modal training with bidirectional attention for improved speech recognition
To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders.
Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder
Intermediate layer output (ILO) regularization by means of multitask training on encoder side has been shown to be an effective approach to yielding improved results on a wide range of end-to-end ASR frameworks.
Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition
More importantly, we train an end-to-end (E2E) speech recognition model by means of merging two monolingual data sets and observe the efficacy of the proposed ILME-based LM fusion for CSSR.
A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition
Speech emotion recognition (SER) is an essential part of human-computer interaction.
Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation
In this paper, we propose a model which combines the complexed spectrogram domain feature and time-domain feature by a cross-domain encoder (CDE) and adopts the hierarchic temporal convolutional network (HTCN) for multiple music sources separation.
Ranked #8 on
Music Source Separation
on MUSDB18
SHREC 2022: Protein-ligand binding site recognition
This paper presents the methods that have participated in the SHREC 2022 contest on protein-ligand binding site recognition.
Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition
Low-resource speech recognition has been long-suffering from insufficient training data.
Fine-Grained Predicates Learning for Scene Graph Generation
The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e. g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child".
Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions
Deformable image registration plays a critical role in various tasks of medical image analysis.
PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition
To boost the performance of PMT, we propose multi-modeling unit training (MMUT) architecture fusion with PMT (PM-MMUT).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Feature selection revisited in the single-cell era
Feature selection techniques are essential for high-dimensional data analysis.
Part-X: A Family of Stochastic Algorithms for Search-Based Test Generation with Probabilistic Guarantees
Requirements driven search-based testing (also known as falsification) has proven to be a practical and effective method for discovering erroneous behaviors in Cyber-Physical Systems.
Meta-Learning 3D Shape Segmentation Functions
We show in experiments that our meta-learning approach, denoted as Meta-3DSeg, leads to improvements on unsupervised 3D shape segmentation over the conventional designs of deep neural networks for 3D shape segmentation functions.
Minimum word error training for non-autoregressive Transformer-based code-switching ASR
Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones.
Adaptive Wavelet Transformer Network for 3D Shape Representation Learning
We present a novel method for 3D shape representation learning using multi-scale wavelet decomposition.
3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation
In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers.
Reasoning over Entity-Action-Location Graph for Procedural Text Understanding
Procedural text understanding aims at tracking the states (e. g., create, move, destroy) and locations of the entities mentioned in a given paragraph.
An Ecological Robustness-Oriented Approach for Power System Network Expansion
Power systems are critical infrastructure for reliable and secure electric energy delivery.
Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment
Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings.
G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.
E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition
In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously.
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes
Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models.
RPATTACK: Refined Patch Attack on General Object Detectors
Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually.
Toward Efficient Wide-Area Identification of Multiple Element Contingencies in Power Systems
Based on each selected branch, the approach constructs the subgraph with parameters of distance and search level, while using branches' LODF metrics as the weights.
Multi-Source Data Fusion for Cyberattack Detection in Power Systems
We perform multi-source data fusion for training IDS in a cyber-physical power system testbed where we collect cyber and physical side data from multiple sensors emulating real-world data sources that would be found in a utility and synthesizes these into features for algorithms to detect intrusions.
Real-time Power System Simulation with Hardware Devices through DNP3 in Cyber-Physical Testbed
The usage and configuration of DNP3 with real-world equipment in to achieve power system monitoring and control of a large-scale synthetic electric grid via this DNP3 communication is presented.
Mixed-Integer Optimization for Bio-Inspired Robust Power Network Design
This paper presents an approach to address this challenge through bio-inspired power system network design to improve system reliability and resilience against disturbances.
Considerations in the Automatic Development of Electric Grid Restoration Plans
Power system restoration is a highly complex task that must be performed in a timely manner following a blackout.
Multilingual Approach to Joint Speech and Accent Recognition with DNN-HMM Framework
Experimental results on an 8-accent English speech recognition show both methods can yield WERs close to the conventional ASR systems that completely ignore the accent, as well as desired AR accuracy.
3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence
In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.
RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion
Many graph embedding approaches have been proposed for knowledge graph completion via link prediction.
Robust Image Matching By Dynamic Feature Selection
Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.
Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech
Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre.
Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems
In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance.
Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
We design a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation in order to integrate advantages and avoid limitations of these two categories of approaches.
Event Ticket Price Prediction with Deep Neural Network on Spatial-Temporal Sparse Data
However, given all the historical transaction records, it is challenging to predict the sale price of the remaining seats at any future timestamp, not only because that the sale price is relevant to a lot of features (seat locations, date-to-event of the transaction, event date, team performance, etc.
Failure Analysis on Multivariate Time-series Data given Uncertain Labels
Machine failure analysis and detection is critical to today’s industrial society.
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition
Video action recognition, a critical problem in video understanding, has been gaining increasing attention.
Automatically Redundant Features Removal for Unsupervised Feature Selection via Sparse Feature Graph
The redundant features existing in high dimensional datasets always affect the performance of learning and mining algorithms.
