Picture for Lele Cheng

Lele Cheng

Paragraph-to-Image Generation with Information-Enriched Diffusion Model

Add code
Nov 29, 2023
Viaarxiv icon

Decouple Content and Motion for Conditional Image-to-Video Generation

Nov 24, 2023
Viaarxiv icon

TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval

Oct 03, 2022
Figure 1 for TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval
Figure 2 for TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval
Figure 3 for TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval
Figure 4 for TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval
Viaarxiv icon

LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval

Jul 11, 2022
Figure 1 for LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
Figure 2 for LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
Figure 3 for LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
Figure 4 for LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
Viaarxiv icon

Weakly Supervised Learning with Side Information for Noisy Labeled Images

Sep 04, 2020
Figure 1 for Weakly Supervised Learning with Side Information for Noisy Labeled Images
Figure 2 for Weakly Supervised Learning with Side Information for Noisy Labeled Images
Figure 3 for Weakly Supervised Learning with Side Information for Noisy Labeled Images
Figure 4 for Weakly Supervised Learning with Side Information for Noisy Labeled Images
Viaarxiv icon

Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification

Nov 02, 2018
Figure 1 for Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
Figure 2 for Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
Figure 3 for Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
Figure 4 for Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
Viaarxiv icon