research
∙
08/16/2023
SCANet: A Self- and Cross-Attention Network for Audio-Visual Speech Separation
The integration of different modalities, such as audio and visual inform...
share
research
∙
08/05/2023
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation
Semi-supervised semantic segmentation involves assigning pixel-wise labe...
research
∙
07/04/2023
Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling
Recent works have proposed to craft adversarial clothes for evading pers...
research
∙
05/31/2023
Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model
We propose Audio-Visual Lightweight ITerative model (AVLIT), an effectiv...
research
∙
05/28/2023
Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness
Recent works found that deep neural networks (DNNs) can be fooled by adv...
research
∙
05/27/2023
On the Importance of Backbone to the Adversarial Robustness of Object Detectors
Object detection is a critical component of various security-sensitive a...
research
∙
04/20/2023
Meta Semantics: Towards better natural language understanding and reasoning
Natural language understanding is one of the most challenging topics in ...
research
∙
03/10/2023
MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems
Automatic speech recognition (ASR) systems based on deep neural networks...
research
∙
02/13/2023
CFNet: Cascade Fusion Network for Dense Prediction
Multi-scale features are essential for dense prediction tasks, including...
research
∙
01/31/2023
NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning
Semi-supervised learning (SSL) has been widely explored in recent years,...
research
∙
01/30/2023
Anchor-Based Adversarially Robust Zero-Shot Learning Driven by Language
Deep neural networks are vulnerable to adversarial attacks. We consider ...
research
∙
12/21/2022
An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits
Audio-visual approaches involving visual inputs have laid the foundation...
research
∙
12/04/2022
Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks
Adversarial attacks can easily fool object recognition systems based on ...
research
∙
11/30/2022
Extracting Semantic Knowledge from GANs with Unsupervised Learning
Recently, unsupervised learning has made impressive progress on various ...
research
∙
09/30/2022
An efficient encoder-decoder architecture with top-down attention for speech separation
Deep neural networks have shown excellent prospects in speech separation...
research
∙
08/17/2022
On the Privacy Effect of Data Enhancement via the Lens of Memorization
Machine learning poses severe privacy concerns as it is shown that the l...
research
∙
07/28/2022
Visual Recognition by Request
In this paper, we present a novel protocol of annotation and evaluation ...
research
∙
07/23/2022
Active Pointly-Supervised Instance Segmentation
The requirement of expensive annotations is a major burden for training ...
research
∙
07/03/2022
NP-Match: When Neural Processes meet Semi-Supervised Learning
Semi-supervised learning (SSL) has been widely explored in recent years,...
research
∙
06/15/2022
On the Use of Deep Mask Estimation Module for Neural Source Separation Systems
Most of the recent neural source separation systems rely on a masking-ba...
research
∙
05/12/2022
Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real World
Thermal infrared imaging is widely used in body temperature measurement,...
research
∙
03/24/2022
A Manifold View of Adversarial Risk
The adversarial risk of a machine learning model has been widely studied...
research
∙
03/07/2022
An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks
Compared with rate-based artificial neural networks, Spiking Neural Netw...
research
∙
03/07/2022
Adversarial Texture for Fooling Person Detectors in the Physical World
Nowadays, cameras equipped with AI systems can capture and analyze image...
research
∙
02/22/2022
The Winning Solution to the iFLYTEK Challenge 2021 Cultivated Land Extraction from High-Resolution Remote Sensing Image
Extracting cultivated land accurately from high-resolution remote images...
research
∙
12/04/2021
Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
Recent advances in the design of neural network architectures, in partic...
research
∙
10/30/2021
Adjacency constraint for efficient hierarchical reinforcement learning
Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promisin...
research
∙
06/18/2021
RSG: A Simple but Effective Module for Learning Imbalanced Datasets
Imbalanced datasets widely exist in practice and area great challenge fo...
research
∙
06/05/2021
Convolutional Neural Networks with Gated Recurrent Connections
The convolutional neural network (CNN) has become a basic model for solv...
research
∙
05/19/2021
Attack on practical speaker verification system using universal adversarial perturbations
In authentication scenarios, applications of practical speaker verificat...
research
∙
04/17/2021
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have a...
research
∙
04/12/2021
Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
Tremendous efforts have been made on instance segmentation but the mask ...
research
∙
03/02/2021
CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds
It is often desired to train 6D pose estimation systems on synthetic dat...
research
∙
02/23/2021
Rethinking Natural Adversarial Examples for Classification Models
Recently, it was found that many real-world examples without intentional...
research
∙
02/12/2021
Annotation Cleaning for the MSR-Video to Text Dataset
The video captioning task is to describe the video contents with natural...
research
∙
02/11/2021
Frame Difference-Based Temporal Loss for Video Stylization
Neural style transfer models have been used to stylize an ordinary video...
research
∙
01/20/2021
Fooling thermal infrared pedestrian detectors in real world using small bulbs
Thermal infrared detection systems play an important role in many areas ...
research
∙
06/20/2020
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning
Goal-conditioned hierarchical reinforcement learning (HRL) is a promisin...
research
∙
02/12/2020
End-to-End Face Parsing via Interlinked Convolutional Neural Networks
Face parsing is an important computer vision task that requires accurate...
research
∙
01/24/2020
6D Object Pose Regression via Supervised Learning on Point Clouds
This paper addresses the task of estimating the 6 degrees of freedom pos...
research
∙
01/16/2020
Delving Deeper into the Decoder for Video Captioning
Video captioning is an advanced multi-modal task which aims to describe ...
research
∙
10/10/2019
Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization
Pedestrian attribute recognition has been an emerging research topic in ...
research
∙
10/07/2019
Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork
We propose a novel perspective to understand deep neural networks in an ...
research
∙
09/27/2019
Pruning from Scratch
Network pruning is an important research field aiming at reducing comput...
research
∙
08/31/2019
A Semantics-Assisted Video Captioning Model Trained with Scheduled Sampling
Given the features of a video, recurrent neural network can be used to a...
research
∙
05/23/2019
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
The Convolutional Neural Networks (CNNs) generate the feature representa...
research
∙
04/19/2019
Knowledge Distillation via Route Constrained Optimization
Distillation-based learning boosts the performance of the miniaturized n...
research
∙
03/15/2019
Selective Kernel Networks
In standard Convolutional Neural Networks (CNNs), the receptive fields o...
research
∙
03/15/2019
Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation
Human-object interactions (HOI) recognition and pose estimation are two ...
research
∙
06/07/2018