相关论文: VideoAtlas: Navigating Long-Form Video in Logarith…

Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively…

Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving barely satisfactory results in simple scenarios. However,…

Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video-language models often overlook precise temporal…

Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture…

While recent advances in reinforcement learning have significantly enhanced reasoning capabilities in large language models (LLMs), these techniques remain underexplored in multi-modal LLMs for video captioning. This paper presents the…

Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed…

Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise…

Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory overhead. These constraints often lead to significant…

Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos…

This paper presents a case study on deploying Large Language Models (LLMs) as an advanced "annotation" mechanism to achieve nuanced content understanding (e.g., discerning content "vibe") at scale within a large-scale industrial short-form…

Large Multimodal Models (LMMs) have demonstrated exceptional performance in video captioning tasks, particularly for short videos. However, as the length of the video increases, generating long, detailed captions becomes a significant…

In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for…

The efficacy of video generation models heavily depends on the quality of their training datasets. Most previous video generation models are trained on short video clips, while recently there has been increasing interest in training long…

Long video understanding presents significant challenges for vision-language models due to extremely long context windows. Existing solutions relying on naive chunking strategies with retrieval-augmented generation, typically suffer from…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative…

Video Anomaly Detection (VAD) aims to localize abnormal events on the timeline of long-range surveillance videos. Anomaly-scoring-based methods have been prevailing for years but suffer from the high complexity of thresholding and low…

Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous information and high token costs associated with multimodal inputs…

Recent advancements in Large Language Models (LLMs) have led to the development of Video Large Multi-modal Models (Video-LMMs) that can handle a wide range of video understanding tasks. These models have the potential to be deployed in…

Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM's context size. To address this…