Picture for Mengchen Liu

Mengchen Liu

Stephen

Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search

Add code
Mar 15, 2024
Figure 1 for Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search
Figure 2 for Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search
Figure 3 for Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search
Figure 4 for Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search
Viaarxiv icon

An Evaluation of GPT-4V and Gemini in Online VQA

Add code
Dec 17, 2023
Figure 1 for An Evaluation of GPT-4V and Gemini in Online VQA
Figure 2 for An Evaluation of GPT-4V and Gemini in Online VQA
Figure 3 for An Evaluation of GPT-4V and Gemini in Online VQA
Figure 4 for An Evaluation of GPT-4V and Gemini in Online VQA
Viaarxiv icon

Fully Authentic Visual Question Answering Dataset from Online Communities

Add code
Nov 27, 2023
Viaarxiv icon

On the Hidden Waves of Image

Add code
Oct 19, 2023
Figure 1 for On the Hidden Waves of Image
Figure 2 for On the Hidden Waves of Image
Figure 3 for On the Hidden Waves of Image
Figure 4 for On the Hidden Waves of Image
Viaarxiv icon

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Add code
Oct 18, 2023
Figure 1 for Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Figure 2 for Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Figure 3 for Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Figure 4 for Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Viaarxiv icon

Foundation Models Meet Visualizations: Challenges and Opportunities

Add code
Oct 09, 2023
Figure 1 for Foundation Models Meet Visualizations: Challenges and Opportunities
Figure 2 for Foundation Models Meet Visualizations: Challenges and Opportunities
Figure 3 for Foundation Models Meet Visualizations: Challenges and Opportunities
Viaarxiv icon

TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance

Add code
Sep 21, 2023
Figure 1 for TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
Figure 2 for TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
Figure 3 for TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
Figure 4 for TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
Viaarxiv icon

Image is First-order Norm+Linear Autoregressive

Add code
May 25, 2023
Figure 1 for Image is First-order Norm+Linear Autoregressive
Figure 2 for Image is First-order Norm+Linear Autoregressive
Figure 3 for Image is First-order Norm+Linear Autoregressive
Figure 4 for Image is First-order Norm+Linear Autoregressive
Viaarxiv icon

Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations

Add code
Feb 27, 2023
Figure 1 for Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Figure 2 for Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Figure 3 for Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Figure 4 for Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Viaarxiv icon

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning

Add code
Dec 08, 2022
Figure 1 for Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Figure 2 for Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Figure 3 for Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Figure 4 for Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Viaarxiv icon