5 papers
City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning
Penglei Sun, Yaoxian Song, Xiangru Zhu +7
Scene understanding enables intelligent agents to interpret and comprehend their environment. While existing large vision-language models (LVLMs) for scene understanding have prima…
Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Xiangru Zhu, Penglei Sun, Yaoxian Song +6
Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from…
Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval
Haoyu Liu, Yaoxian Song, Xuwu Wang +4
With the explosive growth of multi-modal information on the Internet, unimodal search cannot satisfy the requirement of Internet applications. Text-image retrieval research is need…
A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics
Xiangru Zhu, Penglei Sun, Chengyu Wang +4
Text-to-image (T2I) synthesis has recently achieved significant advancements. However, challenges remain in the model's compositionality, which is the ability to create new combina…
M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base
Zhiwei Zha, Jiaan Wang, Zhixu Li +3
Multimodal knowledge bases (MMKBs) provide cross-modal aligned knowledge crucial for multimodal tasks. However, the images in existing MMKBs are generally collected for entities in…