Picture for Stan Weixian Lei

Stan Weixian Lei

Too Large; Data Reduction for Vision-Language Pre-Training

Add code
Jun 01, 2023
Viaarxiv icon

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Add code
Aug 29, 2022
Figure 1 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Figure 2 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Figure 3 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Figure 4 for Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Viaarxiv icon

GEB+: A benchmark for generic event boundary captioning, grounding and text-based retrieval

Add code
Apr 10, 2022
Figure 1 for GEB+: A benchmark for generic event boundary captioning, grounding and text-based retrieval
Figure 2 for GEB+: A benchmark for generic event boundary captioning, grounding and text-based retrieval
Figure 3 for GEB+: A benchmark for generic event boundary captioning, grounding and text-based retrieval
Figure 4 for GEB+: A benchmark for generic event boundary captioning, grounding and text-based retrieval
Viaarxiv icon

AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant

Add code
Mar 08, 2022
Figure 1 for AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
Figure 2 for AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
Figure 3 for AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
Figure 4 for AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
Viaarxiv icon

AssistSR: Affordance-centric Question-driven Video Segment Retrieval

Add code
Dec 06, 2021
Figure 1 for AssistSR: Affordance-centric Question-driven Video Segment Retrieval
Figure 2 for AssistSR: Affordance-centric Question-driven Video Segment Retrieval
Figure 3 for AssistSR: Affordance-centric Question-driven Video Segment Retrieval
Figure 4 for AssistSR: Affordance-centric Question-driven Video Segment Retrieval
Viaarxiv icon