Picture for Zeqian Li

Zeqian Li

A Strong Baseline for Temporal Video-Text Alignment

Add code
Dec 21, 2023
Viaarxiv icon

Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models

Add code
Dec 12, 2023
Figure 1 for Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Figure 2 for Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Figure 3 for Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Figure 4 for Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Viaarxiv icon

Multi-modal Prompting for Low-Shot Temporal Action Localization

Add code
Mar 21, 2023
Figure 1 for Multi-modal Prompting for Low-Shot Temporal Action Localization
Figure 2 for Multi-modal Prompting for Low-Shot Temporal Action Localization
Figure 3 for Multi-modal Prompting for Low-Shot Temporal Action Localization
Figure 4 for Multi-modal Prompting for Low-Shot Temporal Action Localization
Viaarxiv icon

Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection

Add code
Apr 27, 2022
Figure 1 for Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection
Figure 2 for Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection
Figure 3 for Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection
Figure 4 for Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection
Viaarxiv icon

Compositional Affinity Propagation: When Clusters Have Compositional Structure

Add code
Sep 09, 2021
Figure 1 for Compositional Affinity Propagation: When Clusters Have Compositional Structure
Figure 2 for Compositional Affinity Propagation: When Clusters Have Compositional Structure
Figure 3 for Compositional Affinity Propagation: When Clusters Have Compositional Structure
Figure 4 for Compositional Affinity Propagation: When Clusters Have Compositional Structure
Viaarxiv icon

Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers

Add code
Oct 22, 2020
Figure 1 for Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers
Figure 2 for Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers
Figure 3 for Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers
Viaarxiv icon

Compositional Embeddings for Multi-Label One-Shot Learning

Add code
Feb 12, 2020
Figure 1 for Compositional Embeddings for Multi-Label One-Shot Learning
Figure 2 for Compositional Embeddings for Multi-Label One-Shot Learning
Figure 3 for Compositional Embeddings for Multi-Label One-Shot Learning
Figure 4 for Compositional Embeddings for Multi-Label One-Shot Learning
Viaarxiv icon