ArtEmis V2.0 Is Now Available, Removing The Emotional Bias In The Painting Dataset!
ArtEmis V2.0 Is Now Available, Removing The Emotional Bias In The Painting Dataset!
Dataset
Articles
CogVideo, An Open Source Model Capable Of Generating Video From Text, Is Now Available!
CogVideo, An Open Source Model Capable Of Generating Video From Text, Is Now Available!
Video Generation
Multi-agent Reinforcement Learning Algorithm That Can Handle Increasing Or Decreasing Number Of Agents
Multi-agent Reinforcement Learning Algorithm That Can Handle Increasing Or Decreasing Number Of Agen ...
Reinforcement Learning
Text To Speech Methods That Run On Fewer Computational Resources
Text To Speech Methods That Run On Fewer Computational Resources
NAS
A Model That Generates The Listener's Response To A Conversation Is Now Available!
A Model That Generates The Listener's Response To A Conversation Is Now Available!
3D
What Are The Conditions For Effective Teachers In Knowledge Distillation?
What Are The Conditions For Effective Teachers In Knowledge Distillation?
Knowledge Distillation
Multimodal End-to-end Transformer
Multimodal End-to-end Transformer
Transformer
Backdoor Attack On Self-supervised Learning
Backdoor Attack On Self-supervised Learning
Backdoor Attack
BEAT, A Large Data Set For Generating More Human-like Realistic Gestures, Is Now Available!
BEAT, A Large Data Set For Generating More Human-like Realistic Gestures, Is Now Available!
Dataset
Optimal Architecture Search Method In Federated Learning!
Optimal Architecture Search Method In Federated Learning!
NAS
Inverse Synthetic Analysis Model GTA Using Both Graph And SMILES Representations
Inverse Synthetic Analysis Model GTA Using Both Graph And SMILES Representations
Materials Informatics
Zoom In/out Hostile Attack!
Zoom In/out Hostile Attack!
Adversarial Perturbation
Revisiting Weakly Supervised Pre-training In Visual Recognition Models
Revisiting Weakly Supervised Pre-training In Visual Recognition Models
Image Recognition
Should The Kernel Size For CNN Be Larger?
Should The Kernel Size For CNN Be Larger?
Article
How Does Pruning Of The ImageNet Pre-training Model Work In Downstream Tasks?
How Does Pruning Of The ImageNet Pre-training Model Work In Downstream Tasks?
Pruning
What Are The Data Set Requirements For Successful Self-supervised Controlled Learning?
What Are The Data Set Requirements For Successful Self-supervised Controlled Learning?
Dataset
Affine Parameters In Batch Normalization Can Be Detrimental In Few-Shot Learning!
Affine Parameters In Batch Normalization Can Be Detrimental In Few-Shot Learning!
Few-Shot
Architectural Exploration Method For Neural Nets Running On IoT Devices
Architectural Exploration Method For Neural Nets Running On IoT Devices
NAS
Increase Affine Accuracy First! Registration Using ViT: C2FViT
Increase Affine Accuracy First! Registration Using ViT: C2FViT
Medical
TSDFNet For Time Series Forecasting With An Attentive Feature Value Fusion Mechanism
TSDFNet For Time Series Forecasting With An Attentive Feature Value Fusion Mechanism
Time-series
How Should We Link Different Resolution Features? : D3Net Proposed By Sony
How Should We Link Different Resolution Features? : D3Net Proposed By Sony
CVPR
Multimodal Emotion Recognition From Text, Voice And Vision: Sony's Proposed M2FNet!
Multimodal Emotion Recognition From Text, Voice And Vision: Sony's Proposed M2FNet!
Emotion Recognition
Graphs Are So Awesome! Review Of Integration With Deep Learning
Graphs Are So Awesome! Review Of Integration With Deep Learning
GNN
How Is It Different From GAN? Are You Familiar With The Image Generation Model NeRF?
How Is It Different From GAN? Are You Familiar With The Image Generation Model NeRF?
NeRF
Superior To ViT! A New Underlying Model For Large-Scale CNNs! : InternImage
Superior To ViT! A New Underlying Model For Large-Scale CNNs! : InternImage
Deep Learning
Simple But Powerful! Here Comes AugMix, A Data Extension Method That Improves Both Model Generalizability And Uncertainty!
Simple But Powerful! Here Comes AugMix, A Data Extension Method That Improves Both Model Generalizab ...
Data Augmentation
SF-MASK: Benchmark Dataset For Classifying Masked Faces In Low-resolution Surveillance Camera Video
SF-MASK: Benchmark Dataset For Classifying Masked Faces In Low-resolution Surveillance Camera Video
Face Recognition
Do We Really Need Deep Learning Models For Time Series Forecasting?
Do We Really Need Deep Learning Models For Time Series Forecasting?
Time-series
Why Are Vision Transformers So High Performance?
Why Are Vision Transformers So High Performance?
Transformer
Group-CAM: Is Grad-CAM Obsolete? Decision Basis Methods In State-of-the-Art CNNs
Group-CAM: Is Grad-CAM Obsolete? Decision Basis Methods In State-of-the-Art CNNs
Explainable.AI
New Trends In Time Series Analysis : Robust Time Series "Chain" Extraction By Incremental Nearest Neighbor Method TSC22
New Trends In Time Series Analysis : Robust Time Series "Chain" Extraction By Incremental Nearest Ne ...
Time-series