English
Related papers

Related papers: Where to Focus: Query-Modulated Multimodal Keyfram…

200 papers

The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While keyframe selection is the dominant strategy…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Shaoguang Wang , Weiyu Guo , Ziyang Chen , Yijie Xu , Xuming Hu , Hui Xiong

Recent studies have shown that long chain-of-thought (CoT) reasoning can significantly enhance the performance of large language models (LLMs) on complex tasks. However, this benefit is yet to be demonstrated in the domain of video…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yuanxin Liu , Kun Ouyang , Haoning Wu , Yi Liu , Lin Sui , Xinhao Li , Yan Zhong , Y. Charles , Xinyu Zhou , Xu Sun

Multimodal information, together with our knowledge, help us to understand the complex and dynamic world. Large language models (LLM) and large multimodal models (LMM), however, still struggle to emulate this capability. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Yuanhan Zhang , Kaichen Zhang , Bo Li , Fanyi Pu , Christopher Arif Setiadharma , Jingkang Yang , Ziwei Liu

Vision-Language Models (VLMs) have enabled substantial progress in video understanding by leveraging cross-modal reasoning capabilities. However, their effectiveness is limited by the restricted context window and the high computational…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Zeyu Xu , Junkang Zhang , Qiang Wang , Yi Liu

While vision-language models (VLMs) excel at tasks involving single images or short videos, they still struggle with Long Video Question Answering (LVQA) due to its demand for complex multi-step temporal reasoning. Vanilla approaches, which…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Sahil Shah , S P Sharan , Harsh Goel , Minkyu Choi , Mustafa Munir , Manvik Pasula , Radu Marculescu , Sandeep Chinchali

Due to excessive memory overhead, most Multimodal Large Language Models (MLLMs) can only process videos of limited frames. In this paper, we propose an effective and efficient paradigm to remedy this shortcoming, termed One-shot video-Clip…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Tao Chen , Shaobo Ju , Qiong Wu , Chenxin Fang , Kun Zhang , Jun Peng , Hui Li , Yiyi Zhou , Rongrong Ji

Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Hongjie Zhang , Lu Dong , Yi Liu , Yifei Huang , Yali Wang , Limin Wang , Yu Qiao

Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal…

Computer Vision and Pattern Recognition · Computer Science 2024-04-29 Enxin Song , Wenhao Chai , Tian Ye , Jenq-Neng Hwang , Xi Li , Gaoang Wang

Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yongdong Luo , Xiawu Zheng , Guilin Li , Shukang Yin , Haojia Lin , Chaoyou Fu , Jinfa Huang , Jiayi Ji , Fei Chao , Jiebo Luo , Rongrong Ji

Having revolutionized natural language processing (NLP) applications, large language models (LLMs) are expanding into the realm of multimodal inputs. Owing to their ability to interpret images, multimodal LLMs (MLLMs) have been primarily…

Computer Vision and Pattern Recognition · Computer Science 2024-02-14 Jusung Lee , Sungguk Cha , Younghyun Lee , Cheoljong Yang

Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Weitong Cai , Jiabo Huang , Shaogang Gong , Hailin Jin , Yang Liu

This paper tackles the intricate challenge of video question-answering (VideoQA). Despite notable progress, current methods fall short of effectively integrating questions with video frames and semantic object-level abstractions to create…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Sai Bhargav Rongali , Mohamad Hassan N C , Ankit Jha , Neha Bhargava , Saurabh Prasad , Biplab Banerjee

Long-form video understanding is complicated by the high redundancy of video data and the abundance of query-irrelevant information. To tackle these challenges, we propose VideoTree, a training-free framework which builds a query-adaptive…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Ziyang Wang , Shoubin Yu , Elias Stengel-Eskin , Jaehong Yoon , Feng Cheng , Gedas Bertasius , Mohit Bansal

Recent progress in multi-modal large language models (MLLMs) has significantly advanced video understanding. However, their performance on long-form videos remains limited by computational constraints and suboptimal frame selection. We…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Wenhui Tan , Ruihua Song , Jiaze Li , Jianzhong Ju , Zhenbo Luo

Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mitigation is to first select a small subset of informative frames before the forward pass;…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Mohamed Eltahir , Lama Ayash , Ali Habibullah , Tanveer Hussain , Naeemullah Khan

Video-guided Multimodal Translation (VMT) has advanced significantly in recent years. However, most existing methods rely on locally aligned video segments paired one-to-one with subtitles, limiting their ability to capture global narrative…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Jian Chen , JinZe Lv , Zi Long , XiangHua Fu

Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Sunqi Fan , Jiashuo Cui , Meng-Hao Guo , Shuojin Yang

Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \texttt{DreamFactory}, an LLM-based framework that tackles this challenge. \texttt{DreamFactory} leverages…

Artificial Intelligence · Computer Science 2024-08-22 Zhifei Xie , Daniel Tang , Dingwei Tan , Jacques Klein , Tegawend F. Bissyand , Saad Ezzini

In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Sosuke Yamao , Natsuki Miyahara , Yuankai Qi , Shun Takeuchi

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets,…

Artificial Intelligence · Computer Science 2025-12-24 Runtao Liu , Ziyi Liu , Jiaqi Tang , Yue Ma , Renjie Pi , Jipeng Zhang , Qifeng Chen