English
Related papers

Related papers: Video-XL: Extra-Long Vision Language Model for Hou…

200 papers

We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Hongwei Xue , Tiankai Hang , Yanhong Zeng , Yuchong Sun , Bei Liu , Huan Yang , Jianlong Fu , Baining Guo

Large Vision-Language Models (LVLMs) demonstrate remarkable performance in short-video tasks such as video question answering, but struggle in long-video understanding. The linear frame sampling strategy, conventionally used by LVLMs, fails…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Joao Pereira , Vasco Lopes , David Semedo , Joao Neves

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Jusheng Zhang , Xiaoyang Guo , Kaitong Cai , Qinhan Lv , Yijia Fan , Wenhao Chai , Jian Wang , Keze Wang

The core challenge in video understanding lies in perceiving dynamic content changes over time. However, multimodal large language models struggle with temporal-sensitive video tasks, which requires generating timestamps to mark the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Henghao Zhao , Ge-Peng Ji , Rui Yan , Huan Xiong , Zechao Li

We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Mingze Xu , Mingfei Gao , Shiyu Li , Jiasen Lu , Zhe Gan , Zhengfeng Lai , Meng Cao , Kai Kang , Yinfei Yang , Afshin Dehghan

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Aditya Kumar Singh , Hitesh Kandala , Pratik Prabhanjan Brahma , Zicheng Liu , Emad Barsoum

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on…

Computation and Language · Computer Science 2026-02-03 Yibo Wang , Yongcheng Jing , Shunyu Liu , Hao Guan , Rong-cheng Tu , Chengyu Wang , Jun Huang , Dacheng Tao

Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analysis of token compression methods for VideoLLMs reveals two…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Xuyang Liu , Yiyu Wang , Junpeng Ma , Linfeng Zhang

Visual data comes in various forms, ranging from small icons of just a few pixels to long videos spanning hours. Existing multi-modal LLMs usually standardize these diverse visual inputs to a fixed resolution for visual encoders and yield…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Zuyan Liu , Yuhao Dong , Ziwei Liu , Winston Hu , Jiwen Lu , Yongming Rao

The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Yuanbin Man , Ying Huang , Chengming Zhang , Bingzhe Li , Wei Niu , Miao Yin

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jindong Jiang , Amala Sanjay Deshmukh , Kateryna Chumachenko , Karan Sapra , Zhiding Yu , Guilin Liu , Andrew Tao , Pavlo Molchanov , Jan Kautz , Wonmin Byeon

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…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Tzu-Tao Chang , Shivaram Venkataraman

Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Ahmad Mahmood , Ashmal Vayani , Muzammal Naseer , Salman Khan , Fahad Shahbaz Khan

Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Tanveer Hannan , Md Mohaiminul Islam , Jindong Gu , Thomas Seidl , Gedas Bertasius

Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Sitong Gong , Yunzhi Zhuge , Lu Zhang , Zongxin Yang , Pingping Zhang , Huchuan Lu

Video Question Answering (VQA) in long videos poses the key challenge of extracting relevant information and modeling long-range dependencies from many redundant frames. The self-attention mechanism provides a general solution for sequence…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Md Mohaiminul Islam , Tushar Nagarajan , Huiyu Wang , Gedas Bertasius , Lorenzo Torresani

Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Yongxin Guo , Jingyu Liu , Mingda Li , Dingxin Cheng , Xiaoying Tang , Dianbo Sui , Qingbin Liu , Xi Chen , Kevin Zhao

The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs scale quadratically with input sequence length. We propose…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Weili Xu , Enxin Song , Wenhao Chai , Xuexiang Wen , Tian Ye , Gaoang Wang

Vision-Language Models (VLMs) can process visual and textual information in multiple formats: texts, images, interleaved texts and images, or even hour-long videos. In this work, we conduct fine-grained quantitative and qualitative analyses…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Théo Gigant , Camille Guinaudeau , Frédéric Dufaux

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…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Haoji Zhang , Yiqin Wang , Yansong Tang , Yong Liu , Jiashi Feng , Xiaojie Jin