Picture for Kwonjoon Lee

Kwonjoon Lee

Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models

May 30, 2024
Viaarxiv icon

Vamos: Versatile Action Models for Video Understanding

Add code
Nov 22, 2023
Figure 1 for Vamos: Versatile Action Models for Video Understanding
Figure 2 for Vamos: Versatile Action Models for Video Understanding
Figure 3 for Vamos: Versatile Action Models for Video Understanding
Figure 4 for Vamos: Versatile Action Models for Video Understanding
Viaarxiv icon

Object-centric Video Representation for Long-term Action Anticipation

Add code
Oct 31, 2023
Figure 1 for Object-centric Video Representation for Long-term Action Anticipation
Figure 2 for Object-centric Video Representation for Long-term Action Anticipation
Figure 3 for Object-centric Video Representation for Long-term Action Anticipation
Figure 4 for Object-centric Video Representation for Long-term Action Anticipation
Viaarxiv icon

ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models

Oct 09, 2023
Viaarxiv icon

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

Add code
Jul 31, 2023
Figure 1 for AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Figure 2 for AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Figure 3 for AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Figure 4 for AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Viaarxiv icon

ViTGAN: Training GANs with Vision Transformers

Jul 09, 2021
Figure 1 for ViTGAN: Training GANs with Vision Transformers
Figure 2 for ViTGAN: Training GANs with Vision Transformers
Figure 3 for ViTGAN: Training GANs with Vision Transformers
Figure 4 for ViTGAN: Training GANs with Vision Transformers
Viaarxiv icon

Dual Contradistinctive Generative Autoencoder

Nov 19, 2020
Figure 1 for Dual Contradistinctive Generative Autoencoder
Figure 2 for Dual Contradistinctive Generative Autoencoder
Figure 3 for Dual Contradistinctive Generative Autoencoder
Figure 4 for Dual Contradistinctive Generative Autoencoder
Viaarxiv icon

Unaligned Image-to-Sequence Transformation with Loop Consistency

Oct 09, 2019
Figure 1 for Unaligned Image-to-Sequence Transformation with Loop Consistency
Figure 2 for Unaligned Image-to-Sequence Transformation with Loop Consistency
Figure 3 for Unaligned Image-to-Sequence Transformation with Loop Consistency
Figure 4 for Unaligned Image-to-Sequence Transformation with Loop Consistency
Viaarxiv icon

Learning Instance Occlusion for Panoptic Segmentation

Add code
Jun 13, 2019
Figure 1 for Learning Instance Occlusion for Panoptic Segmentation
Figure 2 for Learning Instance Occlusion for Panoptic Segmentation
Figure 3 for Learning Instance Occlusion for Panoptic Segmentation
Figure 4 for Learning Instance Occlusion for Panoptic Segmentation
Viaarxiv icon

Meta-Learning with Differentiable Convex Optimization

Add code
Apr 23, 2019
Figure 1 for Meta-Learning with Differentiable Convex Optimization
Figure 2 for Meta-Learning with Differentiable Convex Optimization
Figure 3 for Meta-Learning with Differentiable Convex Optimization
Figure 4 for Meta-Learning with Differentiable Convex Optimization
Viaarxiv icon