Picture for Taojiannan Yang

Taojiannan Yang

Dense Connector for MLLMs

Add code
May 22, 2024
Figure 1 for Dense Connector for MLLMs
Figure 2 for Dense Connector for MLLMs
Figure 3 for Dense Connector for MLLMs
Figure 4 for Dense Connector for MLLMs
Viaarxiv icon

AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models

Add code
Apr 30, 2024
Figure 1 for AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
Figure 2 for AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
Figure 3 for AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
Figure 4 for AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
Viaarxiv icon

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

Add code
Apr 11, 2024
Viaarxiv icon

A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition

Add code
Mar 23, 2023
Figure 1 for A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Figure 2 for A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Figure 3 for A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Figure 4 for A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Viaarxiv icon

AIM: Adapting Image Models for Efficient Video Action Recognition

Add code
Feb 06, 2023
Figure 1 for AIM: Adapting Image Models for Efficient Video Action Recognition
Figure 2 for AIM: Adapting Image Models for Efficient Video Action Recognition
Figure 3 for AIM: Adapting Image Models for Efficient Video Action Recognition
Figure 4 for AIM: Adapting Image Models for Efficient Video Action Recognition
Viaarxiv icon

Problem Behaviors Recognition in Videos using Language-Assisted Deep Learning Model for Children with Autism

Add code
Nov 17, 2022
Figure 1 for Problem Behaviors Recognition in Videos using Language-Assisted Deep Learning Model for Children with Autism
Figure 2 for Problem Behaviors Recognition in Videos using Language-Assisted Deep Learning Model for Children with Autism
Figure 3 for Problem Behaviors Recognition in Videos using Language-Assisted Deep Learning Model for Children with Autism
Figure 4 for Problem Behaviors Recognition in Videos using Language-Assisted Deep Learning Model for Children with Autism
Viaarxiv icon

Revisiting Training-free NAS Metrics: An Efficient Training-based Method

Add code
Nov 16, 2022
Figure 1 for Revisiting Training-free NAS Metrics: An Efficient Training-based Method
Figure 2 for Revisiting Training-free NAS Metrics: An Efficient Training-based Method
Figure 3 for Revisiting Training-free NAS Metrics: An Efficient Training-based Method
Figure 4 for Revisiting Training-free NAS Metrics: An Efficient Training-based Method
Viaarxiv icon

Exploring Parameter-Efficient Fine-tuning for Improving Communication Efficiency in Federated Learning

Add code
Oct 04, 2022
Figure 1 for Exploring Parameter-Efficient Fine-tuning for Improving Communication Efficiency in Federated Learning
Figure 2 for Exploring Parameter-Efficient Fine-tuning for Improving Communication Efficiency in Federated Learning
Figure 3 for Exploring Parameter-Efficient Fine-tuning for Improving Communication Efficiency in Federated Learning
Figure 4 for Exploring Parameter-Efficient Fine-tuning for Improving Communication Efficiency in Federated Learning
Viaarxiv icon

HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER

Add code
May 30, 2022
Figure 1 for HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER
Figure 2 for HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER
Figure 3 for HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER
Figure 4 for HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER
Viaarxiv icon

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

Add code
Nov 28, 2021
Figure 1 for Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning
Figure 2 for Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning
Figure 3 for Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning
Figure 4 for Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning
Viaarxiv icon