Related papers: Long-VMNet: Accelerating Long-Form Video Understan…
Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports broadcasting. However, it remains computationally…
Real-time understanding of long video streams remains challenging for multimodal large language models (VLMs) due to redundant frame processing and rapid forgetting of past context. Existing streaming systems rely on fixed-interval decoding…
We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual…
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…
Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV) cache expands linearly over time, leading to substantial…
Long-context video understanding and generation pose a significant computational challenge for Transformer-based video models due to the quadratic complexity of self-attention. While existing sparse attention methods employ coarse-grained…
Most of the existing methods for video understanding primarily focus on videos only lasting tens of seconds, with limited exploration of techniques for handling long videos. The increased number of frames in long videos poses two main…
The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…
Video classification problem has been studied many years. The success of Convolutional Neural Networks (CNN) in image recognition tasks gives a powerful incentive for researchers to create more advanced video classification approaches. As…
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…
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…
Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image classification community and the use of deep convolutional networks…
Long video understanding remains challenging for multimodal large language models (MLLMs) due to limited context windows, which necessitate identifying sparse query-relevant video segments. However, existing methods predominantly localize…
This paper introduces VideoScan, an efficient vision-language model (VLM) inference framework designed for real-time video interaction that effectively comprehends and retains streamed video inputs while delivering rapid and accurate…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…
Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient…
Learning multimodal video understanding typically relies on datasets comprising video clips paired with manually annotated captions. However, this becomes even more challenging when dealing with long-form videos, lasting from minutes to…
The surge in video and social media content underscores the need for a deeper understanding of multimedia data. Most of the existing mature video understanding techniques perform well with short formats and content that requires only…
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…
Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and…