Picture for Xiaohan Nie

Xiaohan Nie

Multimodal Instruction Tuning with Hybrid State Space Models

Add code
Nov 13, 2024
Viaarxiv icon

Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows

Add code
Apr 05, 2022
Figure 1 for Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
Figure 2 for Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
Figure 3 for Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
Figure 4 for Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows
Viaarxiv icon

Movies2Scenes: Learning Scene Representations Using Movie Similarities

Add code
Mar 12, 2022
Figure 1 for Movies2Scenes: Learning Scene Representations Using Movie Similarities
Figure 2 for Movies2Scenes: Learning Scene Representations Using Movie Similarities
Figure 3 for Movies2Scenes: Learning Scene Representations Using Movie Similarities
Figure 4 for Movies2Scenes: Learning Scene Representations Using Movie Similarities
Viaarxiv icon

Shot Contrastive Self-Supervised Learning for Scene Boundary Detection

Add code
Apr 28, 2021
Figure 1 for Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
Figure 2 for Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
Figure 3 for Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
Figure 4 for Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
Viaarxiv icon

Cross-view Action Modeling, Learning and Recognition

Add code
May 12, 2014
Figure 1 for Cross-view Action Modeling, Learning and Recognition
Figure 2 for Cross-view Action Modeling, Learning and Recognition
Figure 3 for Cross-view Action Modeling, Learning and Recognition
Figure 4 for Cross-view Action Modeling, Learning and Recognition
Viaarxiv icon