Picture for Kecheng Zheng

Kecheng Zheng

CoReS: Orchestrating the Dance of Reasoning and Segmentation

Add code
Apr 08, 2024
Viaarxiv icon

DreamLIP: Language-Image Pre-training with Long Captions

Add code
Mar 25, 2024
Viaarxiv icon

Contextual AD Narration with Interleaved Multimodal Sequence

Add code
Mar 19, 2024
Figure 1 for Contextual AD Narration with Interleaved Multimodal Sequence
Figure 2 for Contextual AD Narration with Interleaved Multimodal Sequence
Figure 3 for Contextual AD Narration with Interleaved Multimodal Sequence
Figure 4 for Contextual AD Narration with Interleaved Multimodal Sequence
Viaarxiv icon

TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification

Add code
Dec 26, 2023
Viaarxiv icon

Learning Naturally Aggregated Appearance for Efficient 3D Editing

Add code
Dec 11, 2023
Figure 1 for Learning Naturally Aggregated Appearance for Efficient 3D Editing
Figure 2 for Learning Naturally Aggregated Appearance for Efficient 3D Editing
Figure 3 for Learning Naturally Aggregated Appearance for Efficient 3D Editing
Figure 4 for Learning Naturally Aggregated Appearance for Efficient 3D Editing
Viaarxiv icon

GenDeF: Learning Generative Deformation Field for Video Generation

Add code
Dec 07, 2023
Viaarxiv icon

Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection

Add code
Dec 04, 2023
Viaarxiv icon

AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

Add code
Nov 19, 2023
Figure 1 for AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
Figure 2 for AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
Figure 3 for AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
Figure 4 for AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
Viaarxiv icon

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Add code
Sep 07, 2023
Figure 1 for Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
Figure 2 for Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
Figure 3 for Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
Figure 4 for Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
Viaarxiv icon

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Add code
Aug 15, 2023
Figure 1 for CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
Figure 2 for CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
Figure 3 for CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
Figure 4 for CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
Viaarxiv icon