Picture for Fengyun Rao

Fengyun Rao

Visual Perception by Large Language Model's Weights

Add code
May 30, 2024
Viaarxiv icon

Multi-Modal Generative Embedding Model

May 29, 2024
Viaarxiv icon

ReGenNet: Towards Human Action-Reaction Synthesis

Add code
Mar 18, 2024
Figure 1 for ReGenNet: Towards Human Action-Reaction Synthesis
Figure 2 for ReGenNet: Towards Human Action-Reaction Synthesis
Figure 3 for ReGenNet: Towards Human Action-Reaction Synthesis
Figure 4 for ReGenNet: Towards Human Action-Reaction Synthesis
Viaarxiv icon

Spatial-Semantic Collaborative Cropping for User Generated Content

Add code
Jan 16, 2024
Viaarxiv icon

Inter-X: Towards Versatile Human-Human Interaction Analysis

Add code
Dec 26, 2023
Viaarxiv icon

Text-Only Image Captioning with Multi-Context Data Generation

May 29, 2023
Figure 1 for Text-Only Image Captioning with Multi-Context Data Generation
Figure 2 for Text-Only Image Captioning with Multi-Context Data Generation
Figure 3 for Text-Only Image Captioning with Multi-Context Data Generation
Figure 4 for Text-Only Image Captioning with Multi-Context Data Generation
Viaarxiv icon

A Similarity Alignment Model for Video Copy Segment Matching

Add code
May 25, 2023
Figure 1 for A Similarity Alignment Model for Video Copy Segment Matching
Figure 2 for A Similarity Alignment Model for Video Copy Segment Matching
Figure 3 for A Similarity Alignment Model for Video Copy Segment Matching
Figure 4 for A Similarity Alignment Model for Video Copy Segment Matching
Viaarxiv icon

A Dual-level Detection Method for Video Copy Detection

Add code
May 21, 2023
Figure 1 for A Dual-level Detection Method for Video Copy Detection
Figure 2 for A Dual-level Detection Method for Video Copy Detection
Figure 3 for A Dual-level Detection Method for Video Copy Detection
Figure 4 for A Dual-level Detection Method for Video Copy Detection
Viaarxiv icon

CaSP: Class-agnostic Semi-Supervised Pretraining for Detection and Segmentation

Add code
Dec 09, 2021
Figure 1 for CaSP: Class-agnostic Semi-Supervised Pretraining for Detection and Segmentation
Figure 2 for CaSP: Class-agnostic Semi-Supervised Pretraining for Detection and Segmentation
Figure 3 for CaSP: Class-agnostic Semi-Supervised Pretraining for Detection and Segmentation
Figure 4 for CaSP: Class-agnostic Semi-Supervised Pretraining for Detection and Segmentation
Viaarxiv icon

CLIP4Caption ++: Multi-CLIP for Video Caption

Oct 14, 2021
Figure 1 for CLIP4Caption ++: Multi-CLIP for Video Caption
Figure 2 for CLIP4Caption ++: Multi-CLIP for Video Caption
Figure 3 for CLIP4Caption ++: Multi-CLIP for Video Caption
Viaarxiv icon