中文
相关论文

相关论文: FrameOracle: Learning What to See and How Much to …

200 篇论文

Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Jongwoo Park , Kanchana Ranasinghe , Kumara Kahatapitiya , Wonjeong Ryu , Donghyun Kim , Michael S. Ryoo

Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection…

计算机视觉与模式识别 · 计算机科学 2025-03-31 Sicheng Yu , Chengkai Jin , Huanyu Wang , Zhenghao Chen , Sheng Jin , Zhongrong Zuo , Xiaolei Xu , Zhenbang Sun , Bingni Zhang , Jiawei Wu , Hao Zhang , Qianru Sun

Effectively applying Vision-Language Models (VLMs) to Video Question Answering (VideoQA) hinges on selecting a concise yet comprehensive set of frames, as processing entire videos is computationally infeasible. However, current frame…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Yuanhao Zou , Shengji Jin , Andong Deng , Youpeng Zhao , Jun Wang , Chen Chen

Comparing vision language models on videos is particularly complex, as the performances is jointly determined by the model's visual representation capacity and the frame-sampling strategy used to construct the input. Current video…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Marija Brkic , Anas Filali Razzouki , Yannis Tevissen , Khalil Guetari , Mounim A. El Yacoubi

Video question answering (VQA) with vision-language models (VLMs) depends critically on which frames are selected from the input video, yet most systems rely on uniform or heuristic sampling that cannot be optimized for downstream answering…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Xiangyu Bai , Bishoy Galoaa , Sarah Ostadabbas

Recent advances in Multi-Modal Large Language Models (M-LLMs) show promising results in video reasoning. Popular Multi-Modal Large Language Model (M-LLM) frameworks usually apply naive uniform sampling to reduce the number of video frames…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Kai Hu , Feng Gao , Xiaohan Nie , Peng Zhou , Son Tran , Tal Neiman , Lingyun Wang , Mubarak Shah , Raffay Hamid , Bing Yin , Trishul Chilimbi

Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Junbo Zou , Ziheng Huang , Shengjie Zhang , Liwen Zhang , Weining Shen

Video Question Answering (VideoQA) models enhance understanding and interaction with audiovisual content, making it more accessible, searchable, and useful for a wide range of fields such as education, surveillance, entertainment, and…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Himanshu Patil , Geo Jolly , Ramana Raja Buddala , Ganesh Ramakrishnan , Rohit Saluja

While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame sampling and static textual reasoning, which are inefficient and…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Zefeng He , Xiaoye Qu , Yafu Li , Siyuan Huang , Daizong Liu , Yu Cheng

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Sayan Deb Sarkar , Rémi Pautrat , Ondrej Miksik , Marc Pollefeys , Iro Armeni , Mahdi Rad , Mihai Dusmanu

Recent advancements in Video Large Language Models (VideoLLMs) have enabled strong performance across diverse multimodal video tasks. To reduce the high computational cost of processing dense video frames, efficiency-oriented methods such…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Yeonkyung Lee , Dayun Ju , Youngmin Kim , Seil Kang , Seong Jae Hwang

Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current Video QA benchmarks genuinely require temporal frame selection, or can most questions be answered…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Hyunjong Ok , Jaeho Lee

Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampling every recorded frame as if it provided equally useful supervision. We argue that this…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Putu Indah Githa Cahyani , Komang David Dananjaya Suartana , Novanto Yudistira

Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…

机器学习 · 计算机科学 2025-07-04 Anurag Arnab , Ahmet Iscen , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Paul Gavrikov , Wei Lin , M. Jehanzeb Mirza , Soumya Jahagirdar , Muhammad Huzaifa , Sivan Doveh , Serena Yeung-Levy , James Glass , Hilde Kuehne

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…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Ruanjun Li , Yuedong Tan , Yuanming Shi , Jiawei Shao

Large multimodal models (LMMs) have recently demonstrated remarkable performance in video question answering (VideoQA), yet reasoning over video remains challenging due to high inference cost and diluted information. Keyframe selection…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Minchan Kwon , Hyounguk Shon , Junmo Kim

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Ruyi Xu , Guangxuan Xiao , Yukang Chen , Liuning He , Kelly Peng , Yao Lu , Song Han

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

计算机视觉与模式识别 · 计算机科学 2025-10-03 Xuchen Li , Xuzhao Li , Jiahui Gao , Renjie Pi , Shiyu Hu , Wentao Zhang
‹ 上一页 1 2 3 10 下一页 ›