中文
相关论文

相关论文: LE-NeuS: Latency-Efficient Neuro-Symbolic Video Un…

200 篇论文

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…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Sahil Shah , S P Sharan , Harsh Goel , Minkyu Choi , Mustafa Munir , Manvik Pasula , Radu Marculescu , Sandeep Chinchali

Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Saket Gurukar , Asim Kadav

Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…

分布式、并行与集群计算 · 计算机科学 2026-01-08 Shengyuan Ye , Bei Ouyang , Tianyi Qian , Liekang Zeng , Mu Yuan , Xiaowen Chu , Weijie Hong , Xu Chen

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…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Joao Pereira , Vasco Lopes , David Semedo , Joao Neves

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

计算机视觉与模式识别 · 计算机科学 2022-10-13 Yizeng Han , Zhihang Yuan , Yifan Pu , Chenhao Xue , Shiji Song , Guangyu Sun , Gao Huang

The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems.…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Minkyu Choi , Harsh Goel , Mohammad Omama , Yunhao Yang , Sahil Shah , Sandeep Chinchali

Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Ziyi Wang , Haoran Wu , Yiming Rong , Deyang Jiang , Yixin Zhang , Yunlong Zhao , Shuang Xu , Bo XU

Multi-modal Large Language Models (MLLMs) have significantly advanced video reasoning, yet Video Question Answering (VideoQA) remains challenging due to its demand for temporal causal reasoning and evidence-grounded answer generation.…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Kaixin zhang , Xiaohe Li , Jiahao Li , Haohua Wu , Xinyu Zhao , Zide Fan , Lei Wang

Long video understanding remains challenging due to its complex, diverse, and temporally scattered content. Although video large language models (Video-LLMs) can process videos lasting tens of minutes, applying them to truly long sequences…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Yuan Sheng , Yanbin Hao , Chenxu Li , Shuo Wang , Xiangnan He

Objective: To enable context-aware computer assistance in the operating room of the future, cognitive systems need to understand automatically which surgical phase is being performed by the medical team. The primary source of information…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Isabel Funke , Dominik Rivoir , Stefanie Krell , Stefanie Speidel

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…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Xinlei Yu , Chengming Xu , Guibin Zhang , Zhangquan Chen , Yudong Zhang , Yongbo He , Peng-Tao Jiang , Jiangning Zhang , Xiaobin Hu , Shuicheng Yan

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Huaxin Zhang , Xiaohao Xu , Xiang Wang , Jialong Zuo , Xiaonan Huang , Changxin Gao , Shanjun Zhang , Li Yu , Nong Sang

Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Lars Doorenbos , Federico Spurio , Juergen Gall

Research into Video Large Language Models (LLMs) has progressed rapidly, with numerous models and benchmarks emerging in just a few years. Typically, these models are initialized with a pretrained text-only LLM and finetuned on both image-…

计算机视觉与模式识别 · 计算机科学 2025-06-10 George Lydakis , Alexander Hermans , Ali Athar , Daan de Geus , Bastian Leibe

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

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

A recent approach to neurosymbolic reasoning is to explicitly combine the strengths of large language models (LLMs) and symbolic solvers to tackle complex reasoning tasks. However, current approaches face significant limitations, including…

人工智能 · 计算机科学 2026-01-08 Benjamin Callewaert , Simon Vandevelde , Joost Vennekens

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

Seeking high-quality representations with latent variable models (LVMs) to reveal the intrinsic correlation between neural activity and behavior or sensory stimuli has attracted much interest. In the study of the biological visual system,…

神经与进化计算 · 计算机科学 2025-10-27 Liwei Huang , ZhengYu Ma , Liutao Yu , Huihui Zhou , Yonghong Tian

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…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Yuxiang Huang , Mingye Li , Xu Han , Chaojun Xiao , Weilin Zhao , Ao Sun , Ziqi Yuan , Hao Zhou , Fandong Meng , Zhiyuan Liu
‹ 上一页 1 2 3 10 下一页 ›