Picture for Kang Zhu

Kang Zhu

MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Add code
Jun 28, 2024
Viaarxiv icon

PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents

Add code
Jun 20, 2024
Viaarxiv icon

SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval

Add code
Jan 24, 2024
Figure 1 for SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
Figure 2 for SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
Figure 3 for SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
Figure 4 for SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
Viaarxiv icon

CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark

Add code
Jan 22, 2024
Figure 1 for CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
Figure 2 for CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
Figure 3 for CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
Figure 4 for CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
Viaarxiv icon

Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection

Add code
Jun 27, 2023
Figure 1 for Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
Figure 2 for Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
Figure 3 for Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
Figure 4 for Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
Viaarxiv icon

Hyperspectral Light Field Stereo Matching

Add code
Sep 04, 2017
Figure 1 for Hyperspectral Light Field Stereo Matching
Figure 2 for Hyperspectral Light Field Stereo Matching
Figure 3 for Hyperspectral Light Field Stereo Matching
Figure 4 for Hyperspectral Light Field Stereo Matching
Viaarxiv icon