7 citations · 29 across the 54 of their papers we have counts for
7 papers · 1 filter
GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation
Shasha Guo, Liang Pang, Xi Wang +3
Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Recent attempts construct auxiliary lines via…
Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
Shicheng Xu, Liang Pang, Yunchang Zhu +2
Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment met…
Event-aware Video Corpus Moment Retrieval
Danyang Hou, Liang Pang, Huawei Shen +1
Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos using the natural languag…
Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
Danyang Hou, Liang Pang, Huawei Shen +1
Video Corpus Moment Retrieval (VCMR) is a new video retrieval task aimed at retrieving a relevant moment from a large corpus of untrimmed videos using a text query. The relevance b…
Visual Reasoning: from State to Transformation
Xin Hong, Yanyan Lan, Liang Pang +2
Most existing visual reasoning tasks, such as CLEVR in VQA, ignore an important factor, i.e.~transformation. They are solely defined to test how well machines understand concepts a…
Visual Transformation Telling
Wanqing Cui, Xin Hong, Yanyan Lan +3
Humans can naturally reason from superficial state differences (e.g. ground wetness) to transformations descriptions (e.g. raining) according to their life experience. In this pape…
Multi-video Moment Ranking with Multimodal Clue
Danyang Hou, Liang Pang, Yanyan Lan +2
Video corpus moment retrieval~(VCMR) is the task of retrieving a relevant video moment from a large corpus of untrimmed videos via a natural language query. State-of-the-art work f…