相关论文: video-SALMONN S: Memory-Enhanced Streaming Audio-V…

Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal…

Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video…

This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, the output is a keyshot sequence. Our key idea is to…

With the rapid development of video Multimodal Large Language Models (MLLMs), numerous benchmarks have been proposed to assess their video understanding capability. However, due to the lack of rich events in the videos, these datasets may…

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…

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…

The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual…

Livestream videos have become a significant part of online learning, where design, digital marketing, creative painting, and other skills are taught by experienced experts in the sessions, making them valuable materials. However, Livestream…

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…

Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering…

While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks, where temporal alignment becomes increasingly inaccurate as…

Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large…

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…

Existing MLLMs encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools to assist a single MLLM in answering long video questions. Despite such…

Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both…

The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly critical. Video summarization addresses this challenge by generating concise yet…

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

We introduce TemporalVLM, a video large language model (video LLM) for temporal reasoning and fine-grained understanding in long videos. Our approach includes a visual encoder for mapping a long-term video into features which are time-aware…

From image to video understanding, the capabilities of Multi-modal LLMs (MLLMs) are increasingly powerful. However, most existing video understanding benchmarks are relatively short, which makes them inadequate for effectively evaluating…

Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…