Graph data is ubiquitous in the physical world, and it has always been a
challenge to efficiently model graph structures using a unified paradigm for
the understanding and reasoning on various graphs. Moreover, in the era of
large language models, integrating complex graph information into text
sequences has become exceptionally difficult, which hinders the ability to
interact with graph data through natural language instructions.The paper
presents a new paradigm for understanding and reasoning about graph data by
integrating image encoding and multimodal technologies. This approach enables
the comprehension of graph data through an instruction-response format,
utilizing GPT-4V's advanced capabilities. The study evaluates this paradigm on
various graph types, highlighting the model's strengths and weaknesses,
particularly in Chinese OCR performance and complex reasoning tasks. The
findings suggest new direction for enhancing graph data processing and natural
language interaction.

通过整合图像编码和多模态技术，将图数据理解和推理的范式与 GPT-4V 的先进能力相结合，以指令 - 响应格式实现对图数据的理解，评估该范式在不同图类型上的性能并强调模型的优势和劣势，特别是中文 OCR 性能和复杂推理任务，为增强图数据处理和自然语言交互提供了新方向。

图数据与多模态相遇：图理解与推理的新范式

When Graph Data Meets Multimodal: A New Paradigm for Graph Understanding  and Reasoning

This paper proposes an efficient and effective method for joint gaze location
detection (GL-D) and gaze object detection (GO-D), \emph{i.e.}, gaze following
detection. Current approaches frame GL-D and GO-D as two separate tasks,
employing a multi-stage framework where human head crops must first be detected
and then be fed into a subsequent GL-D sub-network, which is further followed
by an additional object detector for GO-D. In contrast, we reframe the gaze
following detection task as detecting human head locations and their gaze
followings simultaneously, aiming at jointly detect human gaze location and
gaze object in a unified and single-stage pipeline. To this end, we propose
GTR, short for \underline{G}aze following detection \underline{TR}ansformer,
streamlining the gaze following detection pipeline by eliminating all
additional components, leading to the first unified paradigm that unites GL-D
and GO-D in a fully end-to-end manner. GTR enables an iterative interaction
between holistic semantics and human head features through a hierarchical
structure, inferring the relations of salient objects and human gaze from the
global image context and resulting in an impressive accuracy. Concretely, GTR
achieves a 12.1 mAP gain ($\mathbf{25.1}\%$) on GazeFollowing and a 18.2 mAP
gain ($\mathbf{43.3\%}$) on VideoAttentionTarget for GL-D, as well as a 19 mAP
improvement ($\mathbf{45.2\%}$) on GOO-Real for GO-D. Meanwhile, unlike
existing systems detecting gaze following sequentially due to the need for a
human head as input, GTR has the flexibility to comprehend any number of
people's gaze followings simultaneously, resulting in high efficiency.
Specifically, GTR introduces over a $\times 9$ improvement in FPS and the
relative gap becomes more pronounced as the human number grows.

该论文提出了一种高效有效的联合注视位置检测（GL-D）和注视对象检测（GO-D）方法，通过统一的单阶段流水线同时检测人类注视位置和注视对象，实现了全面端到端的联合，进一步提高准确率。