相关论文: GazeQwen: Lightweight Gaze-Conditioned LLM Modulat…

Appearance-based supervised methods with full-face image input have made tremendous advances in recent gaze estimation tasks. However, intensive human annotation requirement inhibits current methods from achieving industrial level accuracy…

Multi-modal Large Language Models (MLLMs) have advanced greatly in general tasks. However, they still face challenges in geometric reasoning, a task that requires synergistic integration of visual recognition proficiency and complex…

Multimodal Large Language Models (MLLMs) struggle with complex video QA benchmarks like HD-EPIC VQA due to ambiguous queries/options, poor long-range temporal reasoning, and non-standardized outputs. We propose a framework integrating…

Reading is a challenging task for low vision people. While conventional low vision aids (e.g., magnification) offer certain support, they cannot fully address the difficulties faced by low vision users, such as locating the next line and…

Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal remote sensing (RS) images. Although vision-language models (VLMs) have recently been…

Estimating human gaze target from visible images is a critical task for robots to understand human attention, yet the development of generalizable neural architectures and training paradigms remains challenging. While recent advances in…

In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grained motion comprehension - remains under-explored in current benchmarks. To address this gap,…

Long Video Question-Answering (LVQA) presents a significant challenge for Multi-modal Large Language Models (MLLMs) due to immense context and overloaded information, which could also lead to prohibitive memory consumption. While existing…

Monocular depth estimation is a critical function in computer vision applications. This paper shows that large language models (LLMs) can effectively interpret depth with minimal supervision, using efficient resource utilization and a…

Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video frames and their associated information. Efficiently…

Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this work, we present DistilQwen2.5, a family of distilled,…

Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…

Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely attributable to inadequate perception of geometric…

Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale…

Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for vision tasks, typically through fine-tuning to produce universal representations. However, their performance on video remains…

Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a…

Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various…

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

Robust gaze estimation is a challenging task, even for deep CNNs, due to the non-availability of large-scale labeled data. Moreover, gaze annotation is a time-consuming process and requires specialized hardware setups. We propose MTGLS: a…

Multimodal large language models (MLLMs) have made significant progress in visual-language reasoning, but their ability to efficiently handle long videos remains limited. Despite recent advances in long-context MLLMs, storing and attending…